JP2021059451A - Discrimination device, discrimination system, and discrimination method - Google Patents

Abstract

To provide a discrimination device that is capable of suitably discriminating the paper type of a sheet even when the paper type is not registered with a paper type database in advance.SOLUTION: The discrimination device includes an acquisition unit and a discrimination unit. The acquisition unit acquires: the value of a regular reflection light amount related to the light volume of the regular reflection light that is irradiated with a light source via an optical system onto a recording medium at a predetermined incident angle and is regularly reflexed on the surface of the recording medium; the value of a diffuse reflection light amount related to the light volume of the diffuse reflection light that is diffusely reflected on the surface of the recording medium at at least one reflection angle; and the values related to the basis weight of the recording medium and the thickness or density of the recording medium. The discrimination unit discriminates the type of the recording medium by putting the respective values acquired by the acquisition unit into a machine-learned, learned model for paper type discrimination.SELECTED DRAWING: Figure 21

Description

The present invention relates to a discrimination device, a discrimination system, and a discrimination method.

In recent years, in the color printing industry, image forming devices such as electrophotographic printers have been widely used. In the field of PP (production printing) corresponding to the color printing industry, adaptation to various types of paper is required as compared with the case of being used in the office. Then, in order to perform high-quality printing on these various types of paper, the paper characteristics stored in the paper feed tray are set for a plurality of items, and the image is printed under the image forming conditions according to the set items. There is a forming device.

In order to make such various paper settings, there is an image forming apparatus including a sensor that automatically detects the characteristics of the paper used for printing. For example, in Patent Document 1, an arithmetic expression for obtaining smoothness from a plurality of detected output amounts (signal strengths) that detect a physical property value of paper is obtained in advance as a first-order regression equation, and the smoothness is obtained using the arithmetic expression. It has been proposed to calculate the paper type to determine the paper type. Further, in the above technique, the physical property value and smoothness value of the paper detected from the paper type database (paper profile) stored in the image forming apparatus in advance, and the registered physical property value and smoothness. Candidates for the paper type (brand) with the closest value to are determined and displayed.

JP-A-2017-223692

However, the technique of Patent Document 1 has a problem that a candidate for a paper type (brand) cannot be determined for a new paper that is not registered in the paper type database stored in advance.

The present invention has been made in view of the above circumstances, and provides a discriminating device, a discriminating system, and a discriminating method capable of appropriately discriminating a paper type even for a type of paper that has not been registered in advance. The purpose is.

The above object of the present invention is achieved by the following means.

(1) A positively reflected light amount value relating to the amount of positively reflected light that is positively reflected on the surface of the recording medium by irradiating the recording medium from a light source via an optical system at a predetermined incident angle, and at least 1 on the surface of the recording medium. An acquisition unit that acquires a diffuse reflection light amount value regarding the amount of diffuse reflection light diffusely reflected at one reflection angle, a value regarding the basis weight of the recording medium, and a value regarding the thickness or density of the recording medium, and the acquisition unit. A discriminating device having a discriminating unit that discriminates the type of the recording medium by inputting each value acquired by the above into a machine-learned trained model for discriminating the paper type.

(2) The discriminator according to (1) above, wherein the trained model is composed of a random forest.

(3) The discriminator according to (1) above, wherein the trained model is composed of a neural network.

(4) The discriminating device according to any one of (1) to (3) above, the positively reflected light amount value, the diffusely reflected light amount value, the value related to the thickness and basis weight of the recording medium, or the recording medium. A discrimination system having a learning unit that generates the trained model by performing machine learning using the value related to the density of the teacher data as an input factor of the teacher data and the type of the recording medium as an output factor of the teacher data.

(5) The discrimination system according to (4) above, further comprising an image forming apparatus for forming an image on the recording medium.

(6) The image forming apparatus has a light source, an optical system that irradiates the surface of a recording medium in an irradiation region with light from the light source at a predetermined angle of incidence, and a positive surface of the recording medium in the irradiation region. A first light receiving unit that detects the amount of reflected positively reflected light, and at least one second that detects the amount of diffusely reflected light that is diffusely reflected at at least one reflection angle on the surface of the recording medium in the irradiation region. The discrimination system according to (5) above, further comprising a light receiving unit, and a detection unit that detects a value related to the basis weight of the recording medium and a value related to the thickness or density of the recording medium.

(7) The discrimination system according to (5) or (6) above, wherein the learning unit executes machine learning at a timing when the image forming process is not executed in the image forming apparatus.

(8) The control unit of the image forming apparatus does not receive an instruction for executing the image forming process while the machine learning is being executed in the learning unit. Described discrimination system.

(9) The discrimination system according to any one of (5) to (8) above, wherein the learning unit executes machine learning at a preset timing.

(10) An output unit that outputs a discrimination result by the discrimination unit, a reception unit that receives an instruction from a user for changing the discrimination result, and a storage unit that stores the teacher data for executing the machine learning. The learning unit further uses the changed information including the changed discriminant result and the information input to the trained model in order to obtain the discriminant result as the teacher data. The discrimination system according to any one of (5) to (9) above, which further machine-learns the trained model.

(11) The storage unit and the learning unit are provided on a server connected to the image forming apparatus via a network, and the acquisition unit, the discriminating unit, the output unit, and the receiving unit form the image. The image forming apparatus provided in the apparatus transmits the change information received by the reception unit to the server, and the server stores the change information transmitted from the image forming apparatus as the teacher data. The trained model is further machine-learned by the learning unit using the stored teacher data, and the machine-learned trained model is transmitted to the image forming apparatus to be transmitted to the image forming apparatus. The discriminating unit according to (10) above, wherein the discriminating unit discriminates the type of the recording medium using the learned model transmitted from the server.

(12) The storage unit, the learning unit, and the discriminating unit are provided in a server connected to the image forming apparatus via a network, and the acquisition unit, the output unit, and the receiving unit form the image. The image forming apparatus provided in the apparatus transmits each value acquired by the acquisition unit to the server, and the discriminating unit of the server has the respective values transmitted from the image forming apparatus and the learning. The discrimination system according to (10) above, which discriminates the type of the recording medium using a completed model.

(13) The change information transmitted from the image forming apparatus is stored in the storage unit as the teacher data, and the learning unit uses the stored teacher data based on preset execution conditions. The discrimination system according to (11) or (12) above, which further machine-learns the trained model.

(14) A positively reflected light amount value relating to the amount of positively reflected light that is positively reflected on the surface of the recording medium by irradiating the recording medium from a light source via an optical system at a predetermined incident angle, and at least 1 on the surface of the recording medium. The step (a) of acquiring the diffusely reflected light amount value regarding the amount of diffusely reflected light diffusely reflected at one reflection angle, the value regarding the basis weight of the recording medium, and the value regarding the thickness or density of the recording medium, and the above-mentioned step (a). A discrimination method including a step (b) in which each value acquired in step (a) is input to a machine-learned trained model for paper type discrimination to discriminate the type of the recording medium.

According to the discriminating device according to the present invention, the value of the positively reflected light amount related to the amount of positively reflected light normally reflected on the surface of the recording medium and the amount of diffusely reflected light diffusely reflected on the surface of the recording medium at at least one reflection angle are related. Acquire the diffuse reflected light amount value, the value related to the basis weight of the recording medium, and the value related to the thickness or density of the recording medium, and input each acquired value into the trained model for machine-learned paper type discrimination. To determine the type of recording medium. As a result, the paper type can be appropriately determined even for the type of paper that is not registered in the database in advance.

It is a figure which shows the schematic structure of the image formation system which includes the image formation apparatus which concerns on this embodiment. It is a side view which shows the structure of the media sensor arranged in the transport path. It is a perspective view which shows the structure of the basis weight sensor and the surface sensor. It is sectional drawing of the surface sensor. It is a perspective view which shows the internal structure of the surface sensor. It is sectional drawing of the surface sensor which shows the state which the shutter is open. It is a schematic diagram which shows the arrangement position of a light emitting part and a light receiving part. It is sectional drawing which shows the incident angle of the irradiation light and the arrangement angle of the light receiving part. It is a schematic diagram which shows the state of the pulp fiber on the paper surface. It is a schematic diagram which shows the fluctuation state of the microscopic fiber orientation angle of a paper. It is a schematic diagram which shows the surface distribution of paper and the diffusion state of irradiation light. It is a schematic diagram which shows the irradiation diameter of the irradiation light and the arrangement position of the light emitting part (light source). It is a graph which shows the variation of the detected light amount by the difference of the irradiation diameter when a plurality of points of a paper surface are measured. It is a graph which shows the transition of the detection accuracy when an error is added to the input data. It is a graph which shows the robustness of the mounting accuracy of a light emitting part. It is a graph which shows the robustness of the mounting accuracy of a light emitting part. It is a table which shows the degree of correlation between the wavelength of light of a light emitting part, and Beck smoothness. It is a graph which shows the comparison result of the Beck smoothness with 4 kinds of paper types (gloss coated paper, matte coated paper, plain paper, high quality paper), and the predicted value by a measurement result. It is a block diagram which shows the structure of an image forming apparatus. It is a block diagram which shows the functional structure of the whole control part of the image forming apparatus which concerns on 1st Embodiment. It is a flowchart which shows the printing process of an image forming apparatus. It is a subroutine flowchart which shows the paper setting process (step S10). It is a control block diagram which shows the determination process (S107). It is a figure for demonstrating the procedure of a paper setting process. This is an example of an operation screen that accepts an instruction to start the determination process. This is an example of an operation screen that accepts an instruction to execute a determination process. This is an example of an operation screen showing the determination result (paper type / basis weight classification). This is an example of an operation screen showing a judgment result (registration profile). This is an example of an operation screen that accepts an instruction to start the determined paper setting change process. This is an example of an operation screen that accepts an instruction to change the determined paper setting. This is an example of an operation screen that accepts an instruction to register the determined paper setting. It is a figure which shows an example of the information registered in the database of teacher data. It is a figure which shows an example of the trained model of the random forest generated by the machine learning using the teacher data. It is a block diagram which shows the functional structure of the whole control part of the image forming apparatus which concerns on 2nd Embodiment. It is a flowchart which shows the addition processing to the teacher data of the change information executed in the image forming apparatus which concerns on 2nd Embodiment. It is a flowchart which shows the generation and update process of the paper type discrimination model and the paper type discrimination algorithm executed in the image forming apparatus which concerns on 2nd Embodiment. It is a figure which shows the procedure of the generation process of the paper type discrimination model, and the conversion process of a paper type discrimination model into a binary file. This is an example of a screen that accepts the setting of the execution condition for updating the paper type discrimination model. This is an example of a screen that accepts the selection of the paper type discrimination model. It is a block diagram which shows the configuration of a server. 3-1 It is a block diagram which shows the functional structure of the control part of the server which concerns on embodiment. FIG. 3 is a block diagram showing a functional configuration of an overall control unit of the image forming apparatus according to the third embodiment. 3-1 It is a flowchart which shows the transmission process of the change information executed in the image forming apparatus which concerns on embodiment. 3-1 is a flowchart showing additional processing of teacher data executed on the server according to the embodiment. 3-1 It is a flowchart which shows the generation process of the paper type discriminating model and the paper type discriminating algorithm executed in the server which concerns on embodiment. 3-1 It is a flowchart which shows the update process of the paper type discrimination algorithm executed in the image forming apparatus which concerns on embodiment. It is a block diagram which shows the functional structure of the control part of the server which concerns on 3-2nd Embodiment. It is a block diagram which shows the functional structure of the whole control part of the image forming apparatus which concerns on 3-2nd Embodiment. It is a flowchart which shows the paper setting process (corresponding to step S10 of FIG. 19) which is executed in the image forming apparatus which concerns on 3-2nd Embodiment. It is a flowchart which shows the discriminating process such as a paper type executed in the server which concerns on 3rd-2nd Embodiment. It is a flowchart which shows the registration process of the change information which is executed in the server which concerns on 3rd-2nd Embodiment. It is a block diagram which shows the functional structure of the control part of the server which concerns on 3rd-3rd Embodiment. It is a block diagram which shows the functional structure of the whole control part of the image forming apparatus which concerns on 3rd-3rd Embodiment. It is a flowchart which shows the registration process of the change information which is executed in the server which concerns on 3rd-3rd Embodiment. It is a flowchart which shows the generation and update process of the paper type discrimination model and the paper type discrimination algorithm executed in the server which concerns on 3rd-3rd Embodiment. It is a figure which shows the example which discriminates the paper type using the trained model of the neural network which machine-learned using the teacher data. It is a figure which illustrates the photographing mechanism for acquiring a surface image. It is a figure which shows an example of the surface image and characteristic of gloss-coated paper, matte-coated paper, wood-free paper, and plain paper acquired by a photographing mechanism. It is a schematic diagram which shows the structure of the basis weight sensor. It is a block diagram which shows the functional structure of a basis weight sensor and a control part. It is a figure which shows the determination standard which shows the relationship between the 1st transmittance and the nominal basis weight. It is a figure which shows the determination standard which shows the relationship between the 2nd transmittance and the nominal basis weight. It is a figure which shows the correlation between the transmittance at a wavelength and the nominal basis weight. It is a figure which shows the index which shows the correspondence relationship between the transmittance and the basis weight difference, and the basis weight threshold. It is a figure which shows an example of the paper profile information.

Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. In the description of the drawings, the same elements are designated by the same reference numerals, and duplicate description will be omitted. In addition, the dimensional ratios in the drawings are exaggerated for convenience of explanation and may differ from the actual ratios. In the drawings, the vertical direction is the Z direction, the front and back directions of the image forming apparatus are the X directions, and the directions orthogonal to these X and Z directions are the Y directions. The X direction is also referred to as a width direction or a rotation axis direction. Further, in the vicinity of the media sensor (media sensor 15 described later), the transport direction of the recording medium parallel to the plane of the transport path (transport path 143 described later) inclined with respect to the horizontal plane and orthogonal to the X direction is the Y'direction. , The direction orthogonal to this is called the Z'direction (see FIG. 2 etc.). In the present embodiment, the recording medium includes printing paper (hereinafter, simply referred to as paper) and various films. In particular, the paper includes those produced using plant-derived mechanical pulp and / or chemical pulp. The types of recording media include coated gloss paper and matte paper (gloss coated paper and matte coated paper), and uncoated plain paper and high-quality paper.

(First Embodiment)
FIG. 1 is a diagram showing a schematic configuration of an image forming system 1 including an image forming apparatus 10 according to the present embodiment. As shown in FIG. 1, the image forming system 1 includes an image forming device 10, a paper feeding device 20, and a post-processing device 30 that are mechanically and electrically connected to each other.

(Image forming apparatus 10)
The image forming apparatus 10 includes a control unit 11, a storage unit 12, an image forming unit 13, a paper feed transport unit 14, a media sensor 15, an operation panel 18, a communication unit (not shown), and the like. These are connected to each other via a signal line such as a bus for exchanging signals. FIG. 2 is a side view showing the configuration of the media sensor 15 arranged in the transport path 143. The media sensor 15 is composed of a paper thickness sensor 40, a basis weight sensor 50, a surface sensor 60, and a paper pressing portion 70, and measures paper characteristics. The surface sensor 60 functions as an optical sensor device and detects paper characteristics, particularly paper surface properties. Details of the media sensor 15 including the surface sensor 60 will be described later. In this embodiment, the media sensor 15 functions as a detection unit. Further, the control unit 11 functions as a discrimination device. Further, the control unit 11 functions as an output unit and a reception unit.

(Control unit 11)
The control unit 11 is composed of a CPU, ROM, RAM, etc., and executes various processes by executing a program stored in the ROM or the storage unit 12 described later, and controls each unit of the device and various types according to the program. Performs arithmetic processing.

(Memory unit 12)
The storage unit 12 includes an auxiliary storage unit such as a ROM for storing various programs and various data in advance, a RAM for temporarily storing programs and data as a work area, and a hard disk for storing various programs and various data. Further, the storage unit 12 stores the paper information stored in each paper feed tray. Paper information includes information on paper brand, size (paper width, paper length), basis weight (weight), and paper type (gloss coated paper, matte coated paper, plain paper, high quality paper, rough paper, etc.). , It is set by the paper type determination process described later. Further, the storage unit 12 may store the paper brand, the learned model used for determining the paper type, and the paper profile (both described later).

(Image forming unit 13)
The image forming unit 13 forms an image by, for example, an electrophotographic method. The image forming unit 13 is composed of a writing unit 131 corresponding to each of the basic colors of Y (yellow), M (magenta), C (cyan), and K (black), a photoconductor drum 132, and toners and carriers of each color. A developer 133, etc., which accommodates a two-component developer, and the like are provided. Further, the image forming unit 13 further includes an intermediate transfer belt 134, a secondary transfer unit 135, and a fixing unit 136. The toner images formed on the photoconductor drum 132 by the developer 133 of each color are superposed on the intermediate transfer belt 134 and transferred to the paper S conveyed by the secondary transfer unit 135. The toner image on the paper S is fixed on the paper S by being heated and pressurized by the fixing portion 136 on the downstream side.

(Paper feed transport unit 14)
The paper feed transport unit 14 includes a plurality of paper feed trays 141, 142, transport paths 143, 144, and the like. The transport paths 143 and 144 include a plurality of transport roller pairs provided along these transport paths and a drive motor (not shown) for driving these transport roller pairs. It is equipped with a delivery roller that feeds out the highest-ranked paper among the plurality of sheets S loaded and placed in the paper feed trays 141 and 142, and feeds the paper S in the paper feed tray one by one to the transport path on the downstream side. .. The media sensor 15 is arranged on the upstream side of the resist roller on the transport path 143. As shown in FIG. 2, in the vicinity of the media sensor 15, the transport path 143 includes an upper guide 1431 and a lower guide 1432 formed of sheet metal, and the paper S passes between these guides facing each other at predetermined intervals.

The paper feed transport unit 14 transports the paper S fed from the paper feed tray 141 or the like. The paper S conveyed through the transport path 143 is ejected onto the output tray 342 via the subsequent post-processing device 30 after the image is formed by the image forming unit 13. When performing double-sided printing in which an image is also formed on the back surface of the paper S, the paper S having an image formed on one side is conveyed to a transport path 144 for forming a double-sided image at the lower part of the main body of the apparatus. The paper S transported to the transport path 144 is inverted on the front and back by the switchback path, then merges with the transport path 143 for one side, and the image forming unit 13 again forms an image on the other side of the paper S. To.

(Operation panel 18)
The operation panel 18 is provided with a touch panel, a numeric keypad, a start button, a stop button, etc., displays the status of the image forming apparatus 10 or the image forming system 1, and is a type of paper placed on the paper feed tray 141 or the like from the user. It is used for setting etc. and inputting instructions.

(Paper Feeding Device 20)
As shown in FIG. 1, the paper feed device 20 includes a paper feed transfer unit 24. Further, the paper feed device 20 includes a control unit, a storage unit, and a communication unit (none of which are shown) in addition to the paper feed transport unit 24, and these include signal lines such as a bus for exchanging signals. They are connected to each other via. The paper feed transport unit 24 includes a plurality of paper feed trays 241, 242, 243, and a transport path 244. The paper S conveyed from each paper feed tray is conveyed to the image forming apparatus 10 on the downstream side, and the paper characteristics are measured by the media sensor 15 and the image is formed by the image forming unit 13.

(Post-processing device 30)
As shown in FIG. 1, the post-processing device 30 includes a post-processing unit 31, a transport path 341, and a paper ejection tray 342. The post-processing unit 31 performs processing such as stapling processing, cutting processing, punching processing (punching holes), and the like on the paper S conveyed from the image forming apparatus 10. Further, the post-processing device 30 includes a control unit, a storage unit, and a communication unit (none of which are shown) in addition to these components, and these include a signal line such as a bus for exchanging signals. To be connected to each other.

(Media sensor 15)
As described above, the media sensor 15 is composed of a paper thickness sensor 40, a basis weight sensor 50, a surface sensor 60, and a paper pressing portion 70. With reference to FIG. 2, among these components, the paper thickness sensor 40 is arranged on the most upstream side in the transport direction. The paper thickness sensor 40 includes a pair of transport rollers 411 and 412, and a pressing mechanism 42 including an actuator, an encoder, and a light emitting / receiving unit. The upper transport roller 411 is urged toward the lower transport roller 412 by the pressing mechanism 42. By transporting the paper S to the nips of the transport rollers 411 and 412, the transport roller 411 moves upward by a height corresponding to the thickness of the paper S. The pressing mechanism 42 detects the paper thickness of the paper S based on the amount of displacement of the transport roller 411 in the height direction (thickness direction).

FIG. 3 is a perspective view showing the configurations of the basis weight sensor 50 and the surface sensor 60. As shown in FIGS. 2 and 3, the basis weight sensor 50 and the surface sensor 60 are arranged side by side in the X direction (width direction) between the transport roller pairs 1433 and 1434.

The basis weight sensor 50 is a sensor that detects the basis weight of the paper, includes a light emitting unit and a light receiving unit, and measures the amount of attenuation of light transmitted through the paper S. For example, the basis weight sensor 50 has a light emitting unit (see FIG. 54: first light emitting unit 51a, second light emitting unit 51b) arranged below the transport path 143 and a light receiving unit (see FIG. 54: light receiving unit 52) above. , The basis weight of the paper S is detected by the intensity of the light received by the light receiving unit. Details of the basis weight sensor 50 will be described later with reference to FIG. 54.

(Surface sensor 60)
Next, the configuration of the surface sensor 60 will be described with reference to FIGS. 4 to 8 together with FIGS. 2 and 3. FIG. 4 is a cross-sectional view of the surface sensor 60, and FIG. 5 is a perspective view showing the internal configuration of the surface sensor 60. In FIG. 5, the description of the cover (housing 61) that covers the entire surface sensor 60 is omitted.

As shown in these figures, the surface sensor 60 includes a housing 61, a light emitting unit 62, a collimating lens 63, a plurality of light receiving units 64 (light receiving units 641, 642), and an opening / closing mechanism 65. The housing 61 covers other components and shields external light. The housing 61 is not on the bottom surface, and when attached, the upper guide 1431 functions as a member that covers the bottom surface of the surface sensor 60. Details of the light emitting unit 62, the collimating lens 63, and the plurality of light receiving units 64 (light receiving units 641, 642) will be described later. In this embodiment, a collimating lens is used as the optical system arranged between the light source and the irradiation region, but a lens other than the collimating lens may be arranged. For example, when a bullet-shaped LED is used, an optical lens is mounted on the LED. Further, a convex lens or the like may be arranged between the LED and the collimator lens.

The opening / closing mechanism 65 includes a shutter 651, a connection portion 652, a rotating shaft 653, a worm gear 654, and a drive motor 655. The power of the drive motor 655 is transmitted to the shutter 651 through the worm gear 654, the rotating shaft 653, and the connecting portion 652. The shutter 651 moves around the rotation axis 653 in the direction of the arrow. The upper guide 1431 is provided with an opening a1, and the lower guide 1432 is provided with an opening a20. 4 and 5 show a state in which the paper characteristics of the paper S in the normal state are not measured. At this time, the opening a1 is closed by the plate-shaped shutter 651 which is a flat plate member. The opening / closing operation of the opening a1 of the shutter 651 is performed by the control unit 11 controlling the drive motor 655.

FIG. 6 is a schematic cross-sectional view of the surface sensor 60 showing a state in which the shutter is open. FIG. 6 shows the state of the measurement mode for measuring the paper characteristics. In FIG. 6, the description of the configuration of the opening / closing mechanism 65 other than the shutter 651 is omitted. The opening a1 has a substantially rectangular shape, and the hole size is, for example, several tens of mm in the horizontal direction (X direction) and several tens of mm in the vertical direction (Y'direction). A plurality of ribs r1 (see FIG. 6) are provided on the lower surface of the shutter 651 so as not to interfere with the transport of the paper S in the transport path 143. Each rib r1 is inclined along the transport direction so that the lower surface of the upper guide 1431 is retracted on the upstream side in the transport direction and slightly protrudes on the downstream side. With such a rib r1, the paper S can be smoothly conveyed. Further, a reference plate 6501 as a member for calibration is attached to the upper surface of the shutter 651. The reference plate 6501 is, for example, a white plate having a predetermined surface property, and the surface property sensor 60 can be calibrated by measuring the reference plate 6501 of the closed shutter 651 before measuring the paper characteristics. Do.

The opening a20 is wider than the opening a1 and is at substantially the same position in the XY'plane, and the opening a20 includes the opening a1. A paper pressing portion 70 is arranged below the lower guide 1432. The paper pressing portion 70 includes a pressing plate 71 having an upper surface parallel to the XY'plane, and a driving mechanism (not shown) for moving the pressing plate 71 up and down. The drive mechanism is composed of a drive motor, a cam, a spring, and the like. Normally, the shape has a cut portion (inclined surface) in which the corner on the upstream side in the transport direction of the pressing plate 71 is slanted so that the paper S to be conveyed does not get caught in the corner, and the pressing plate 71 (excluding the cut portion) is formed. The upper surface is located at the same height as the paper passing surface of the lower guide 1432, or at a height slightly lower than this. The upper surface of the pressing plate 71 is sufficiently larger than the opening a1. In the measurement mode of FIG. 6, the tip of the paper S is transported to a position beyond the openings a1 and a20 in the transport direction, and then the paper S is temporarily stopped. After that, the pressing plate 71 is lifted by the driving mechanism of the paper pressing portion 70. As a result, the paper S is fixed between the upper surface of the pressing plate 71 and the lower surface (reference surface) of the upper guide 1431 with a predetermined urging force. For example, the upper surface of the pressing plate 71 has a size larger than a dozen mm width or more over the entire circumference of the opening a1, and the paper S is pressed in the width region around the pressing plate 71.

FIG. 7 is a schematic view showing the arrangement positions of the light emitting unit 62 and the plurality of light receiving units 64, and FIG. 8 is a cross section showing the incident angle (irradiation angle) of the irradiation light by the light emitting unit 62 and the arrangement angle of the light receiving unit. It is a schematic diagram. In the present embodiment, the arrangement angle of the light emitting unit 62 is set so that the incident angle of the irradiation light with respect to the reference plane is 75 °. The incident angle of 75 ° is an angle used for measuring the glossiness of blank paper according to JIS, and is an angle that is less affected by the color of the object to be measured. The reference surface is a virtual surface including the lower surface of the upper guide 1431 as described above, and at the time of measurement, the surface of the paper S to be measured is arranged on the reference surface. The light emitting unit 62 is arranged on the substrate b1. The light emitting unit 62 includes a light emitting element as a light source such as an LED that emits light having a predetermined wavelength (for example, an average wavelength of 445 nm or more and 500 nm or less), and the irradiation light emitted from the light source (point light source) is abbreviated by the collimating lens 63. It becomes parallel light and irradiates the irradiation area. The irradiation region is an inner region of the opening a1 when viewed from the Z'direction, and the center (optical axis) of the irradiation region and the reference plane parallel to the XY'plane intersect at the intersection p1. As the light emitting unit 62, a surface light emitting type LED may be used, or a bullet type LED may be used. Further, when a bullet-shaped LED is used, a desired irradiation diameter (also referred to as a beam diameter) can be obtained by designing a lens suitable for the bullet-shaped directivity.

Each of the plurality of light receiving units 64 includes a light receiving element such as a photodiode, a phototransistor, etc., and a first light receiving unit 64 (light receiving unit 641) that receives specularly reflected light from the irradiation region and diffuse reflection from the irradiation region. Includes one or more second light receiving units 64 (light receiving units 642) that receive light. As shown in FIG. 7 (see also FIG. 8 for the angles of incidence and reflection), the first light receiving unit 641 is located at a reflection angle of 75 ° corresponding to the incident angle of 75 ° of the light emitting unit 62. It is placed in and receives specularly reflected light. Further, the second light receiving unit 642 can be arranged at any position of the reflection angle except the position of 75 ° within the range of the reflection angle of 0 ° or more and less than 90 °, and receives diffuse reflected light. The arrangement positions are preferably reflection angles of 60 °, 30 °, and 0 °, and more preferably two locations of 60 ° and 30 °, or one location of 60 °. In the examples of FIGS. 4, 6 and 7, a first light receiving unit 641 for receiving specular reflected light having a reflection angle of 75 ° and a second light receiving unit 642 for receiving diffuse reflected light having a reflection angle of 30 ° are arranged. An example of this is shown. In these figures, the light receiving unit 641 is arranged on the substrate b2, and the light receiving unit 642 is arranged on the substrate b3.

The housing 61 is provided with openings a3 and a4 on the light receiving path of the light receiving portions 641 and 642. Since the openings a3 and a4 have the same structure, the structure of the openings a3 will be described below as a representative. As shown in the partially enlarged view of FIG. 7, the opening a3 is, for example, a circular slit having a diameter of 3 mm when viewed from the intersection p1 side, and an inclined surface 61a is provided on the light incident side. The inclined surface is configured so that the distance from the optical axis increases toward the incident side, and has a mortar-shaped shape as a whole. The inclination angle is about 45 ° with respect to the incident angle of light. By providing such an inclined surface 61a, it is possible to prevent the light reflected by the edge of the opening a3 (slit) from being incident on the light receiving portion 641, and by extension, the characteristics of the recording medium can be detected with high accuracy.

(Irradiation diameter)
FIG. 9 is a schematic view showing a microscopic variation state of fiber orientation of paper, and FIG. 10 is a schematic view showing a state of pulp fibers on the surface of paper. Generally, paper is made by randomly entwining pulp fibers extracted from plants such as wood in all directions (isotropic), so that the surface becomes uneven and the surface surface has uneven distribution. (Also called "formation" in industry terms). This texture depends on the length and thickness of the pulp fibers of the paper. The unevenness is larger in B of FIG. 9 than in A of FIG. Pulp fibers derived from softwood and hardwood are used as the material of the paper, and the pulp fibers have an average length of 3.32 mm to 0.79 mm (maximum of about 5.7 mm) and an average width (thickness). 39 μm to 19 μm (maximum approx. 97 μm) (Reference: Paper “Measurement of Surface Shape of Paper” (Paper Pulp Gikyo Magazine Vol. 18, No. 2, February 1964), Oji Paper Co., Ltd. Central Research Institute Hata By Kotoku). Further, as shown in FIG. 10, the surface properties become non-uniform due to the length of the pulp fibers and the formation of binding fibers (entanglement of fibers) between the pulp fibers.

Therefore, if the irradiation diameter is narrowed down too much from the length of the pulp fiber and the shape of the binding fiber, the detected light amount of the specular reflected light and the diffused light differs depending on the position of the reflected light on the paper, that is, the uneven state on the paper surface, which is the same. It is a sensor that is highly sensitive to the surface condition of the paper even on the paper surface. Therefore, an error occurs in each reflected light amount, and if the paper type is discriminated using the data while the error is included, there is a possibility that the paper type is erroneously discriminated. For example, matte coated paper is misidentified as high-quality paper.

11A and 11B are schematic views showing the surface distribution of the paper and the diffusion state of the irradiation light, and FIGS. 12A and 12B are schematic views showing the irradiation diameter of the irradiation light and the arrangement position of the light emitting portion 62. 12 (a) is a side view, and FIG. 12 (b) is a top view. In the present embodiment, from such a situation, it is better to irradiate a wide area as shown in FIG. 11 (b) than to irradiate a narrow area as shown in FIG. 11 (a). The influence of can be reduced. In other words, by setting the irradiation diameter of the irradiation light to a size that irradiates an area sufficiently wider than the area where the pulp fibers that cause the distribution of the paper surface are entangled, the average of the paper surface including the unevenness of the paper surface is obtained. The amount of reflected light can be reduced, and the influence of the distribution on the paper surface can be reduced. Specifically, the irradiation diameter in the irradiation region is set to 6 mm or more, which is larger than the maximum length of the pulp fiber of 5.7 mm described above. The irradiation diameter referred to here is the diameter of the light (beam) in a plane orthogonal to the optical axis at the intersection p1 where the optical axis intersects the irradiation surface (reference plane). Generally, the focal length of the lens, the size of the light source, and the spread of the irradiation diameter are
(Expansion of irradiation diameter) ≒ (light source size) / (lens focal length) ... It is expressed by equation (1). From this equation, the longer the focal length, the closer to parallel light, but the amount of irradiation light decreases, so it is necessary to brighten the lens. Generally, as an expression expressing the brightness of a lens,
(Brightness of lens) = (Focal length of lens) / (Diameter of lens) ... It is expressed by equation (2). From equation (1), the irradiation diameter can be expanded by having a certain size of the light source. That is, in order to obtain the set irradiation diameter and irradiation light amount, the above-mentioned conditions are obtained from the optical design.

In this embodiment, the irradiation diameter is set to φ13 mm as shown in FIG. 12 (a). In order to obtain such an irradiation diameter, when the lens specifications are used with a focal length of 20.7 mm and a lens diameter of φ7.5 mm from optical design and optical simulation, the distance from the light emitting portion 62 to the intersection p1 is 50 to 70 mm. It is within the range, for example 60 mm. As shown in FIG. 12B, the irradiation diameter when designed in this way is φ13 mm for the minor axis (length in the Y'direction) and the major axis (length in the X direction) in the top view (on the XY'plane). Is 50.2 mm (= 13 / cos 75 °). With such an irradiation area (512.6 mm ² ), it is possible to detect the amount of specularly reflected light or diffused light with low sensitivity to the surface surface distribution of the paper, resulting in non-uniform fiber orientation. Less sexual influence.

FIG. 13 is a graph showing the variation in the amount of detected light due to the difference in the irradiation diameter when the surface of the paper is measured at a plurality of points. The figure shows the sample numbers at two levels, the irradiation diameter of φ13 mm and the irradiation diameter of φ1 mm. 1-NO. Up to 10, the variation in the amount of detected light when measuring the positions of 10 different points on one sheet of plain paper is shown. ± 8% shown in the figure is a threshold value at which false detection of paper discrimination is likely to occur as described below. If the irradiation diameter is small, it is easily affected by the texture of the paper S, and erroneous determination of the paper type is likely to occur. As shown in FIG. 13, the irradiation diameter of φ13 mm has less variation in false positives than the irradiation diameter of φ1 mm, and is within the threshold value of ± 8%.

FIG. 14 is a graph showing the transition of the detection accuracy when an error is added to the input data when the paper is discriminated by using the machine-learned model (FIGS. 18A to 20 described later). The figure shows an example in which a gloss-coated paper “coat ball” is used as the paper type. The "coated ball" was used because it is the paper that is most likely to be erroneously discriminated with respect to the reflection angle of 75 ° among 58 types of paper including this. When an error is artificially input to the value measured by the first light receiving unit 641 for detecting specular reflected light with a reflection angle of 75 °, the first candidate for judgment is from the original (correct judgment) gloss coated paper. It shows a threshold value that causes a false judgment as a matte coated paper different from the above (minus side of X-axis error). If an error having an absolute value larger than −8% is input, an erroneous determination will occur in the first candidate for determination, so the threshold value of the specularly reflected light detection unit having a reflection angle of 75 ° is set to ± 8%. That is, the sensor detection accuracy of the reflection angle of 75 ° was set within ± 8%. In the above, the reflection angle of 75 ° has been described, but as a result of performing the same verification for each of the reflection angles of 30 ° and 60 ° (not shown), the threshold value at which the first candidate is erroneously determined is larger than ± 8%. From the verification results, ± 15% was adopted as the respective threshold values of the reflection angles of 30 ° and 60 °. That is, the sensor detection accuracy of the reflection angles of 30 ° and 60 ° was set within ± 15%.

(Position of light source with respect to focal length)
With reference to FIG. 12B again, the arrangement position of the light emitting unit 62 as the light source of the surface sensor 60 (optical sensor device) according to the present embodiment will be described. A collimating lens 63 is arranged immediately downstream of the light emitting unit 62. In general, by arranging a point light source at the focal position of a collimating lens, that is, by arranging the light source at the same distance as the focal length with respect to the collimating lens on the optical axis, the irradiation light from the point light source is emitted. Make it parallel light. In the first embodiment, the light source is arranged at the position of the focal length in this way. However, in the second embodiment, the light emitting unit 62 is intentionally arranged on the side closer to the collimating lens 63 at a distance shorter than the focal length. That is, the focal length f> the light source distance t0 is set (where t0 is the distance between the light emitting portion 62 and the center position of the collimating lens 63 on the optical axis, and f is the focal length of the collimating lens 63. is there).

15A and 15B are graphs showing the robustness of the mounting accuracy of the light emitting unit 62. FIG. 15A is a diagram showing the output error sensitivity to the mounting error in the rotation direction, and FIG. 15B is a diagram showing the output error sensitivity to the mounting error in the optical axis direction. Along with Example 2, data when a light source is arranged at a focal length is also shown as Example 1 to be compared. Here, the mounting error in the rotation direction is an angle when the axis perpendicular to the optical axis is rotated as the rotation axis (corresponding to YAW). The mounting error in the optical axis direction is the distance in the front-rear direction along the optical axis. As shown in FIGS. 15A and 15B, as compared with Example 1, Example 2 in which the light source is arranged at a distance shorter than the focal length of the collimating lens has less variation with respect to error, has higher robustness, and is superior. You can see that.

(Wavelength of light from light source)
For the light wavelength of the light emitting unit 62, a light source having a blue wavelength that is not absorbed by the pigment on the surface layer of the coated paper is selected. From the experimental verification of the LED, the following results were obtained.
405 nm (purple): Coated paper can be identified (specular reflection). Diffuse light makes it difficult to identify high-quality, plain paper.
465 nm (blue): Coated paper can be identified (specular reflection). Diffused light can be identified at 30 ° and 60 °.
525 nm (green): Coated paper can be identified (specular reflection). Diffuse light can be identified at 60 °.
680 nm (red): Difficult to distinguish, especially with diffused light.

In addition, as shown below, regarding the correlation with Beck smoothness, the correlation with each wavelength was also verified.

FIG. 16 is a table showing the degree of correlation between the wavelength of light of the light emitting unit 62 and the Beck smoothness, and FIG. 17 shows 12 types of paper (gloss coated paper, matte coated paper, plain paper, woodfree paper). It is a graph which shows the comparison result with the Beck smoothness of, and the predicted value by the measurement result. Here, Beck smoothness (sec) is a measurement method specified in JIS. After applying a pressure of 0.1 MPa from above and reducing the pressure to half atm with a vacuum pump, 10 cc of air passes through a distance of 13 mm. Measures the time of inflow from the gap between the sample surface and the glass surface.

The light emitting unit 62 was arranged at a position where the incident angle was 75 °, and three types of LEDs having wavelengths of 405 nm, 465 nm, and 525 nm were used as the light source. Further, the light receiving portions 64 were arranged at three locations having reflection angles of 30, 60, and 75 ° (note that they were arranged at all four locations in the test at a wavelength of 525 nm, and further arranged at 0 °).

As the paper type, four types of gloss-coated paper, matte-coated paper, plain paper, and high-quality paper were used, and four different brands of paper were used (a total of 16 brands of paper). On the horizontal axis of FIG. 17, four brands of gloss coated paper are G1 to G4, four brands of matte coated paper are M1 to M4, four brands of plain paper are R1 to R4, and four brands of woodfree paper are F1 to F4, respectively. Shown.

As shown in FIG. 16, the smoothness predicted value calculated by multiplying the measured value from each light receiving unit 64 by a predetermined coefficient for each of the 16 brands of paper, and the measured value of the Beck smoothness of each paper ( When the correlation with log) was compared, it was found that the value of the multiple correlation R was the highest when the LED having an average wavelength of 465 nm was used (indicated by the broken line frame). From this, the wavelength of the light source is preferably in the range of more than 405 nm and less than 525 nm, more preferably in the range of 445 nm or more and 500 nm or less, and the most preferable wavelength is around 465 nm.

FIG. 17 shows the correspondence between the predicted value when the 465 nm LED is used and the Beck smoothness (log). The predicted value here is
Predicted value = 3.4518 × V75-3.9595 × V60 + 1.5383 × V30-0.4789. Here, V75, V60, and V30 are the output values of the light receiving unit 64 at the positions of the reflection angles 75, 60, and 30 °, respectively. As shown in FIG. 17, it can be seen that there is a high correlation.

In the optical sensor device (surface sensor 60) according to the present embodiment, the irradiation diameter in the irradiation region of the irradiation light by the light emitting unit 62 becomes the irradiation area in which the influence of the non-uniformity of the fiber orientation of the recording medium is reduced. Is set to. More specifically, the irradiation diameter (minor diameter) in the irradiation region (intersection point p1) is set to 6 mm or more, which is longer than the maximum length of the pulp fibers. This provides an optical sensor device that can accurately detect the characteristics of the recording medium without being affected by the surface distribution of the recording medium.

Further, the collimating lens 63 is arranged immediately downstream of the light emitting unit 62, and the light emitting unit 62 is arranged at a distance shorter than this focal length with respect to the collimating lens 63 on the optical axis. This makes it possible to improve the robustness of the light emitting unit 62 with respect to the mounting accuracy.

Further, by setting the emission wavelength of the light emitting unit 62 to 445 nm or more and 500 nm or less, the surface property can be detected with high accuracy. Specifically, it is possible to obtain detection data having a high correlation with Beck smoothness.

Further, the optical sensor device according to the present embodiment is provided with a shutter 651 that opens and closes the opening a1 constituting the irradiation region. For example, when the optical sensor device is arranged in the paper transport path, the paper dust of the paper S to be transported may adhere to optical parts such as the collimating lens 63 and the light receiving portion 64, and the measurement accuracy may be lowered. When the surface property of the recording medium is not measured, by closing the opening a1 with such a shutter 651, it is possible to prevent the optical components of the optical sensor device from being contaminated by paper dust, and thus to prevent the measurement accuracy from being lowered.

(Paper type judgment processing)
Next, the paper type determination process performed by the image forming apparatus 10 will be described with reference to FIGS. 18A to 29. FIG. 18A is a block diagram showing a configuration of an image forming apparatus. FIG. 18B is a block diagram showing a functional configuration of an overall control unit of the image forming apparatus according to the first embodiment. FIG. 19 is a flowchart showing a printing process of the image forming apparatus.

As shown in FIG. 18A, the image forming apparatus 10 is connected to the server 80 and other image forming apparatus 10b and 10c through the network L. In the figure, since the configurations other than the control unit 11 of the image forming apparatus 10 have already been described in FIG. 1 and the like, the description will be omitted by adding the same reference numerals.

The control unit 11 functions as an overall control unit 110, an engine control unit 120, a media sensor control unit 130, a post-processing option control unit 140, a paper feed option control unit 150, and a transport control / image formation control unit 160. The date / time management unit 121 manages the date and time used in the image forming apparatus 10. When the control unit 11 executes a process that requires the date and time, the control unit 11 acquires the date and time from the date / time management unit 121 and executes various processes. For example, the date and time managed by the date / time management unit 121 may be used when determining the execution timing of the generation or update process of the paper type determination model or the paper type determination algorithm described later. The date and time managed by the date / time management unit 121 can be appropriately updated / timed by communicating with an external time adjustment server (not shown) or the like via a network, for example.

As shown in FIG. 18B, the overall control unit 110 functions as the acquisition unit 111 and the determination unit 112. The acquisition unit 111 has a specular reflected light amount value regarding the amount of specular reflected light reflected on the surface of the paper, a diffuse reflected light amount value related to the amount of diffuse reflected light diffusely reflected on the surface of the paper, a value related to the thickness of the paper, and the paper. Obtain the value related to the basis weight of. The discriminating unit 112 has learned the values related to the specular reflected light amount value, the diffusely reflected light amount value, the paper thickness, and the basis weight of the paper acquired by the acquisition unit 111 for machine-learned paper type discrimination. Enter in the model to determine the paper type.

When a print job is input by an instruction sent from an operation panel 18 or an external terminal such as a network-connected PC operated by the user, the overall control unit 110 is based on the input print setting information of the print job. , The engine control unit 120 executes a print job. The overall control unit 110 executes the paper type determination process by using the paper type determination engine (paper type determination model which is a learned model) stored in the storage unit 12 and the paper profile. Here, the "paper profile" is a measured value related to the physical characteristics of the paper obtained from the media sensor 15 of the paper, the calculated value of the positioning value, and the characteristic data, the paper size, and any arbitrary value input by the user. It is registered in advance by associating an identification name (for example, a paper brand), etc. The measured values and calculated values from the media sensor 15 include, for example, the measured values of the reflected light at 75 ° and 30 ° of the surface property sensor 60 of the paper physical properties, and the basis weight based on the measured values of the basis weight sensor 50, which will be described later. There is a calculated value of, / or a calculated value of the basis weight difference, and a calculated value of the paper thickness based on the measured value of the paper thickness sensor 40. In addition, the characteristic data input by the user includes transport system characteristic data (front and back adjustment values, offset correction values, etc.), image formation characteristic data (fixation temperature value, density adjustment value, γ correction value, etc.), Various control parameter values such as paper feed system characteristic values (paper feed tray handling fan air volume adjustment value) are included.

The "paper type discrimination engine" is also called a learned model, and a teacher using teacher data with the detection output by the media sensor 15 of the paper S as an input value and the paper type information set by the user of the paper S as a correct label. It is a trained model generated by Yes training. As the teacher data, the data of other image forming devices 10b, 10c, etc. connected to the network L may be aggregated by the server 80. The trained model is generated by, for example, a learning method using a random forest. The learning method is not limited to this, and various methods can be adopted in the case of supervised learning. For example, a neural network, a support vector machine (SVM), a boosting, a Bayesian network linear discrimination method, a non-linear discrimination method, and the like can be applied. Further, as a learning machine for executing machine learning, a stand-alone high-performance computer using a CPU and a GPU (Graphics Processing Unit) processor or a cloud computer can be used. The method of generating the paper type discrimination model by machine learning will be described in detail later.

The engine control unit 120 performs processing related to image formation by controlling the post-processing option control unit 140, the paper feed option control unit 150, and the transport control / image formation control unit 160. The post-processing option control unit 140 controls the post-processing device 30. Specifically, the paper transport timing, post-processing setting information of the paper to be transported, and the like are transmitted to the post-processing device 30. The paper feed option control unit 150 controls the paper feed device 20. Specifically, by communicating with the paper feed device 20, the paper feed tray to be used, the paper transfer timing, and the like are transmitted and received.

The transport control / image formation control unit 160 controls the paper feed transport of the paper S by controlling the paper feed transport unit 14 (including drive motors such as the transport paths 143 and 144 and the fixing unit 136). In addition, the image forming unit 13 is controlled to control the image forming conditions and the image forming timing according to the paper position.

The media sensor control unit 130 controls the paper thickness sensor 40, the basis weight sensor 50, and the surface sensor 60 in response to an execution instruction request from the engine control unit 120 to execute measurement of paper characteristics. Further, the media sensor control unit 130 controls the operation of the paper pressing unit 70.

Next, the paper type determination process will be described with reference to FIG. Steps S10 to S30 are print preparation processes. The user performs this print preparation process before performing the main printing of the print job.

(Step S10)
The user operates the paper setting button on the operation screen (not shown) displayed on the operation panel 18. The control unit 11 starts the paper setting by accepting this operation from the user. The start instruction of the paper setting includes selection information of one or more paper feed trays (paper feed trays 141, 142, 241 to 243) in which the target paper is loaded. Details of this paper setting process will be described later with reference to FIG.

(Step S20)
According to the end of the paper setting, set the image formation conditions according to the set paper characteristics, and press the print button (start button) (not shown) to perform test printing (test printing) of the print job.

(Step S30)
When the user is unsatisfied with the result of the test print, or when a plurality of types of paper are used in one print job, the user repeats the process of step S10 or less for another paper (step S30: NO). On the other hand, when the result of the test print is satisfactory and the confirmation regarding all the paper types is completed (YES), the control unit 11 advances the process to step S40 by accepting the operation of the preparation completion by the user. ..

(Step S40)
The control unit 11 completes the printing process (end) by controlling the image forming unit 13 and the like to execute a print job (main printing).

(Paper setting process)
(Steps S100, S101)
FIG. 20 is a subroutine flowchart showing the paper setting process (step S10). The transport control / image formation control unit 160 of the control unit 11 opens the shutter 651 by the opening / closing mechanism 65, and then the paper feed tray selected by the user (for example, the paper feed tray 141 (hereinafter, simply “selection tray””). )), The paper S is fed and transported to the transport path 143.

(Step S102a)
The media sensor control unit 130 detects the paper thickness of the paper S by the paper thickness sensor 40, and passes the detection data (hereinafter, referred to as “measured value 1”) to the overall control unit 110.

(Steps S102b, S102c)
The media sensor control unit 130 detects the basis weight and surface quality of the paper by the basis weight sensor 50 and the surface surface sensor 60, and controls the detection data (hereinafter referred to as “measured values 2 and 3”, respectively) as a whole. Hand over to unit 110. In this measurement, when the tip of the paper S passes the detection positions of the predetermined amount, the basis weight sensor 50, and the surface sensor 60, the paper transport is stopped at one end, the pressing plate 71 of the paper pressing portion 70 is lifted, and the surface is measured. The paper S located in the irradiation area of the sex sensor 60 is fixed. Before this first measurement, the surface sensor 60 may be calibrated by the reference plate 6501.

(Step S103)
If the measurement has not been performed a predetermined number of N times, the processes of steps S102b and S102c are repeated. Before performing the next measurement, the same paper is obtained by moving the paper pressing portion 70 up and down and transporting the paper S for a predetermined distance (for example, an arbitrary distance of about several mm to 50 mm) each time. Measure another position of S. The N times is, for example, 5 times, and when the measurement for 5 times is completed (YES), the process proceeds to step S104.

(Step S104)
When the rear end of the paper S has passed through the media sensor 15, specifically, when the paper sensor (not shown) detects that the rear end of the paper S has passed through the transport roller 1434 (YES), the process is performed. Proceed to step S105.

(Step S105)
Here, the control unit 11 closes the shutter 651 by the opening / closing mechanism 65 to bring it into a closed state. This prevents the surface sensor 60 from being contaminated by paper dust or the like due to the paper S that is conveyed when the measurement is not performed by the media sensor 15.

(Step S106)
Here, averaging processing is performed on the detection data (measured values 2 and 3) of the basis weight and surface properties of N times acquired in steps S102b and S102c.

(Step S107)
The overall control unit 110 determines the paper type by using the measured values 1 to 3 (or the average data thereof) acquired in steps S102a to S102c, the trained model (paper type determination engine), and the basis weight division probability calculation process. , And the basis weight classification is determined. Further, the candidate of the paper profile having a high degree of approximation is determined from the registered paper profile data by using the measured values 1 to 3 (or the average data thereof) acquired in steps S102a to S102c and the profile selection process.

The paper type determination and the basis weight classification determination process will be described in more detail with reference to FIG. FIG. 21 is a control block diagram showing a determination process (S107). In FIG. 21, in addition to the paper type determination and the basis weight classification determination process, the determination process of the registered profile candidate determined by using the paper profile created for each user (for each device) is also shown.

(S701 to S703)
The overall control unit 110 obtains a basis weight conversion value, a paper thickness conversion value, and a surface property measurement value by using the measurement values 1 to 3 acquired in steps S102a to S102c. Here, the basis weight conversion value is the first basis weight and the first basis weight based on the coefficient and calculation formula determined by the surface property measurement value (S703) of the measurement value 3 and the ambient environment information (temperature, humidity) of the image forming system 1. From the value of 2 tsubo, calculate the tsubo and the difference in tsubo. Here, the basis weight difference = 1st basis weight − 2nd basis area. The basis weight sensor 50 includes a plurality of LEDs that irradiate irradiation light having different wavelengths. The first basis weight is determined by the amount of transmitted light passing through the paper S of the irradiation light using the first LED that outputs the irradiation light having a wavelength (750 nm to 900 nm). The second basis weight is determined by the amount of transmitted light passing through the paper S of the irradiation light using the second LED that outputs the irradiation light having a wavelength (400 nm to 470 nm). The basis weight is sent to steps S711, S712, S714, and the basis weight difference (first basis weight-second basis weight) is sent to steps S713, S714. The paper thickness is sent to steps S712 and S713. The surface quality measurements are sent to steps S701, S713, S714.

(Step S711)
The overall control unit 110 calculates the basis weight classification probability from the basis weight calculated in step S701. Examples of the basis weight classification are the following 12 classifications.
~ 61g / m ²
62-75 g / m ²
76-81 g / m ²
82-92 g / m ²
93-106 g / m ²
107-136 g / m ²
137-177 g / m ²
178-217 g / m ²
218-257 g / m ²
258-301 g / m ²
302-351 g / m ²
352 g / m ²
The calculated basis weight is assumed to vary with a predetermined standard deviation according to a normal distribution, and the probability of each division is determined. For example, when it is close to the center of any of the divisions, the division probability is high and is close to 100%. On the other hand, the farther from the center of the division, that is, the closer to the boundary, the lower the probability. The division probability is sent to step S721 as a basis weight division score.

(Step S712)
The overall control unit 110 calculates the density (= basis weight / paper thickness) using the basis weight and the paper thickness. The calculated density is sent to step S713.

(Step S713)
The overall control unit 110 discriminates the paper type by using the paper characteristic data of the measured values of density, paper thickness, and surface property and the trained model. The determination result is sent to step S721 as a paper type score.

(Step S714)
The overall control unit 110 uses the paper characteristic data of the measured values of density, paper thickness, and surface property and the list of paper profiles registered in advance by the user or the like, and selects a registered profile having a high conformance rate from the list. .. This list of paper profiles has data representing the physical characteristics of the paper, which consists of the basis weight value, the paper thickness value, the basis weight difference value, and the surface property measurement value (for example, the measurement value from the light receiving units 641 and 642). Using the measured values 1 to 3 (or these calculation data) acquired in steps S102a to S102c, the overall control unit 110 uses the paper profiles in the order closest to the registered paper physical property data from the registered paper profiles. Select candidates for. Regarding the method of determining the proximity, for example, the overall control unit 110 calculates the distance between the numerical values of each data item, determines that the sum of the values obtained by multiplying the calculation result by the weighting coefficient is closer in ascending order, and selects the closest ones. Select as a candidate. The selection result is sent to step S722 as a candidate paper profile list with a matching rate score.

(Step S721)
The overall control unit 110 displays one or a plurality of paper type / basis weight candidates in descending order of probability according to the basis weight classification score and the paper type score, and presents them to the user. Details of this process will be described later with reference to FIG.

(Step S722)
The overall control unit 110 displays one or a plurality of registered profile candidates in descending order of the score according to the precision score, and presents the candidates to the user. Details of this process will be described later with reference to FIG.

(Step S108)
See FIG. 20 again. Here, the overall control unit 110 displays the determination result. This process corresponds to FIGS. 22, 24, and steps S721 and S722 described above.

(Step S109)
If the user changes the paper type (YES), the process proceeds to step S110, and if the determination result is accepted without the change (NO), the process proceeds to step S111.

(Step S110)
The overall control unit 110 accepts an input operation from the user through the operation panel 18, and sets the accepted changed paper type as the paper type information of the selection tray.

(Step S111)
When the setting is not changed (for example, when the operation of the button 84 is accepted in FIG. 22), the overall control unit 110 sets the determination result performed in step S107 as the paper type information of the selection tray.

(Step S112)
The print condition of the selected tray is set to the print condition corresponding to the set paper type, and the process returns to the process of FIG. 19 and the process of step S10 or less is performed (return).

Next, the procedure of the process executed by the user in the above-mentioned paper setting process will be described including an example of a screen displayed on the image forming apparatus 10.

FIG. 22 is a diagram for explaining the procedure of the paper setting process. FIG. 23 is an example of an operation screen that receives an instruction to start the determination process. FIG. 24 is an example of an operation screen that receives an instruction to execute the determination process. FIG. 25 is an example of an operation screen showing the determination result (paper type / basis weight classification). FIG. 26 is an example of an operation screen showing a determination result (registration profile). FIG. 27 is an example of an operation screen that accepts an instruction to start the determined paper setting change process. FIG. 28 is an example of an operation screen that accepts an instruction to change the determined paper setting. FIG. 29 is an example of an operation screen that accepts an instruction to register the determined change of the paper setting.

(Step S1)
As shown in FIG. 22, the user first sets the paper to be measured in the tray and selects the automatic paper setting button 180a on the screen as shown in FIG. 23 displayed on the operation panel 18 of the image forming apparatus 10. ..

(Step S2)
A screen as shown in FIG. 24 is displayed on the operation panel 18, and the paper setting process is started when the user selects a tray in which paper is loaded and selects the paper type detection button 180b.

(Step S3)
Subsequently, the image forming apparatus 10 executes paper transport, measurement, and determination processing as shown in FIG.

(Step S4)
Subsequently, the determination result is displayed on the screens as shown in FIGS. 25 and 26.

(Step S5)
The user selects the one to be used from the displayed candidates and applies the setting to the image forming apparatus 10.

FIG. 25 is an example of an operation screen showing the determination result (paper type / basis weight classification) displayed on the operation panel 18. On the operation screen of FIG. 25, two paper type / basis weight candidates are displayed in descending order of score. When the user accepts the determination result of the first candidate column 181 (gloss coated paper / basis weight 177 to 216), the user operates the button 184 to select the tray 1 (paper feed tray 141). The determination result in column 181 is applied. When applying the second candidate column 182 (plain paper / basis weight 172 to 216), the user operates the button 184 after selecting the column 182. On the other hand, when it is desired to apply the selected determination result to both trays 1 and 2, the user operates the button 185. Further, by operating the button 183, the determination result can be discarded without being adopted. If the user is not satisfied with the image quality and the transport after performing the test printing, the user reselects the second candidate field 182, operates the button 184 or the button 185 to reapply the tray, and then performs the test printing. The determination result selected by the user may be stored as correct answer data in the storage unit of the image forming apparatus 10 or the server 80 or the like, and may be used as teacher data for subsequent machine learning. Further, the modification may be accepted by the manual setting in which the user directly inputs various settings.

FIG. 26 is an example of an operation screen showing the determination result (registration profile) displayed on the operation panel 18. On the operation screen of FIG. 26, three registration profile candidates are displayed in descending order of score. The registration profile registers the paper characteristics previously measured by the media sensor 15 or the paper characteristics manually input through the operation panel 18 in association with the media name. If the paper characteristics are the same as those measured in the past, the registered media name is displayed as the first candidate. When accepting the determination result of the column 186 (paper profile data 21) which is the first candidate, the determination result of the selected column 186 is applied to the tray 1 or the like by operating the buttons 184, 185 and the like. To. As a candidate for the registration profile, a preset profile registered in advance in the device may be displayed based on a user's instruction or the like. Further, if the image quality and the paper feed transfer process do not meet the user's request as a result of performing the test printing (test printing) of S20 of FIG. 19 by various settings applied based on the results determined as described above. The user can reselect the second candidate and perform a test print. In addition, the user may manually set various setting values (manual setting). The various manually set settings may be stored in the image forming apparatus 10 or the like, or may be added to the teacher database described later together with the various measured values, etc., according to the user's instruction or the like. The process of determining the registration profile will be described in detail later.

Here, the user can also modify the determined paper setting content and set it in the image forming apparatus 10. For example, on the paper setting screen as shown in FIG. 27, it is displayed that the paper type is determined to be "gloss coated paper". When the user selects the setting change button 187 on the screen of FIG. 27, a screen for changing the paper setting as shown in FIG. 28 is displayed. On the screen of FIG. 28, a list of setting items and current setting contents are shown on the left side. Since the paper type item is selected as the item to change the setting, on the right side of the screen of FIG. 28, the current setting of the paper type, "gloss coated paper", and the candidate for changing the paper type are displayed. It is displayed. Here, as in the screen shown in FIG. 29, when "high quality paper" is selected from the candidates for changing the paper type on the right side of the screen, the paper type is also displayed in the list of setting items on the left side of the screen. It is displayed that it will be changed to "Woodfree paper". In this way, by changing the paper type (paper type) selected by the user from "gloss coated paper" to "high quality paper" and pressing the "OK" or "registration & OK" button, "high quality paper" Is applied and registered in the image forming apparatus 10. As will be described later, the contents registered at this time may be added as teacher data for machine learning. Further, a button or the like for receiving an instruction from the user for adding as teacher data for machine learning may be separately provided. As will be described later, when the paper type is changed to a predetermined type such as "color paper", "envelope", or "embossed paper", it may not be added to the machine learning teacher data.

As described above, in the image forming apparatus 10 according to the present embodiment, the acquired measured values including the specular reflected light amount value and the diffuse reflected light amount value are input to the machine-learned trained model for paper type discrimination to make paper. Determine the species. As a result, the paper type candidates can be appropriately determined even for the types of paper that are not registered in the paper type database in advance.

(Generation of paper type discrimination model by machine learning)
FIG. 30 is a diagram showing an example of information registered in the teacher data database. FIG. 31 is a diagram showing an example of a trained model of a random forest generated by machine learning using teacher data.

As shown in FIG. 30, the input factors of the teacher data used for machine learning are the reflected light 75 ° (normally reflected light) and the reflected light 60 ° (diffuse reflected light), which are the amounts of light acquired from the surface sensor 60. ), The reflected light 30 ° (diffuse reflected light), and the information on the basis weight difference (first basis weight-second basis weight) and density obtained from the paper thickness sensor 40 and the basis weight sensor 50 are used. Basis weight and paper thickness information may be used instead of density. The paper type (paper type) is used as the output factor of the teacher data. In the example of FIG. 30, more than 800 sets of teacher data are prepared.

By performing machine learning using a random forest model using the teacher data as shown in FIG. 30, a trained model (paper type discrimination model) as illustrated in FIG. 31 is generated. To. In this embodiment, the number of nodes is generated as a paper type discrimination model of about 500. Since the generation of the random forest model using the teacher data and the discrimination method using the random forest model are known, detailed description thereof will be omitted. Since the random forest model has a tree-like structure and branches (determines) according to the threshold condition at each node (Node), it is implemented as a simple conditional branch when incorporated into a program as a discrimination algorithm. Therefore, there is an advantage that the processing time required for discrimination is short, and there is no problem even when the image forming apparatus 10 or the like incorporates the processing as real-time processing. In the present embodiment, the generated paper type discrimination model is converted into a paper type discrimination algorithm, incorporated into a program in advance, and executed by the overall control unit 110 of the image forming apparatus 10.

(Selection of input factors for teacher data)
As a result of diligent studies on the parameters used in machine learning to generate a paper type discrimination model capable of accurately discriminating the paper type based on the information that can be measured from the paper, the present inventors have obtained the teacher data shown in FIG. We found that the input factor is effective. Hereinafter, the method of selecting the input factor will be described in detail.

First, for various physical property values that can be measured from paper, the determination accuracy as an input factor of the paper type discrimination model was examined. From the viewpoint of discrimination accuracy, it was found that the contributions were higher in the order of air permeability, density, Beck smoothness, friction coefficient, rigidity, whiteness, surface resistance, and water content (Table 1 below). Furthermore, even when the air permeability, which has the highest contribution, was excluded from the input factors, further selection was made after confirming that there was no problem with the discrimination accuracy. The air permeability was excluded from the input factors because the air permeability sensor that can be mounted on an image forming apparatus or the like is not yet at a practical level.

In the selection, the paper type is discriminated based on the output of each sensor actually mounted on the image forming apparatus 10, and the effective input factor that gives the best value from the viewpoint of contribution, discrimination accuracy, and reproducibility is selected. Selected. In addition, multiple factors with similar meanings were narrowed down to one because they cause over-judgment. Density was selected as an input factor because it has a high contribution and can be calculated from the basis weight and paper thickness. As a result of verification, it has been found that the Beck smoothness correlates with the amount of specular and diffuse reflected light measured by the surface sensor 60, and therefore, as described above, the specular and diffuse reflected light The amount of light was selected as the input factor. As an input factor, data such as the ratio of the amount of specular reflected light to the amount of diffuse reflected light was also examined, but it was excluded as a result of the examination.

In this way, the above eight input factors are narrowed down to four input factors, and finally, they are acquired from the specular reflected light amount (75 °), the diffuse reflected light amount (30 °), and the basis weight sensor 50. Basis weight difference (1st grammage-2nd grammage: amount of transmitted light on paper) and density (results calculated from basis weight and thickness may be used) were selected (Table 2 below). Since it was found as a result of verification that the basis weight difference (1st basis weight-2nd basis weight) can be used for distinguishing between glossy paper and non-glossy paper as described later, it was adopted as an input factor. Details of the method for obtaining the first and second basis weights and an example of use for determining the paper type will be described later with reference to FIGS. 54 to 59. The judgment accuracy of the paper type discrimination model obtained by machine learning using the teacher data created by associating the input factor selected as described above with the paper type which is the output factor is 98% (reproducibility). 97%) (Table 3 below).

Since there is a correlation between the amount of specularly reflected light and diffusely reflected light and the smoothness, the specularly reflected light and the above-mentioned smoothness estimation formula (obtained by the result of compound multiple regression analysis) are used. The smoothness may be calculated by inputting the amount of diffusely reflected light, and the calculated smoothness value may be used as an input factor for machine learning. The value used as the parameter of the teacher data is not limited to the above example, and any parameter effective for determining the paper type can be adopted.

(Second Embodiment)
In the first embodiment, an example in which the paper type discrimination algorithm is incorporated in the image forming apparatus 10 in advance to perform the paper discrimination processing has been described. In the second embodiment, an example in which machine learning is performed in the image forming apparatus 10 to generate and update a paper type discrimination model and a paper type discrimination algorithm will be described.

The configuration of the image forming apparatus 10 of the second embodiment is the same as that of the image forming apparatus 10 of the first embodiment, and a database of teacher data for performing machine learning as shown in FIG. 30 is stored in the storage unit 12. In that respect, it differs from the image forming apparatus 10 of the first embodiment. In the present embodiment, the image forming apparatus 10 or the control unit 11 (overall control unit 110) functions as a discrimination device or a discrimination system.

FIG. 32 is a block diagram showing a functional configuration of an overall control unit of the image forming apparatus according to the second embodiment.

As shown in FIG. 32, the overall control unit 110 of the image forming apparatus 10 of the second embodiment functions as an acquisition unit 111, a discrimination unit 112, and a learning unit 113.

Since the functions of the acquisition unit 111 and the determination unit 112 are the same as those in the first embodiment, the description thereof will be omitted.

The learning unit 113 performs machine learning using the teacher data as shown in FIG. 30, and generates a paper type discrimination model by a random forest model as shown in FIG. 31. Further, when the result determined by the paper type determination model (or the converted paper type determination algorithm) is changed by the user, the learning unit 113 adds the changed content as teacher data, and the added teacher data. A new paper type discrimination model can be generated by further performing machine learning using. The processing of the learning unit 113 as described above will be described in detail below.

(Addition of change information to teacher data)
First, the process of adding the change information to the teacher data will be described.

FIG. 33 is a flowchart showing additional processing of change information executed in the image forming apparatus according to the second embodiment to the teacher data. Hereinafter, description will be made with reference to FIG. 33.

(Step S201)
The overall control unit 110 of the image forming apparatus 10 determines whether or not the determination result of the paper type or the like by the determination unit 112 has been changed by the user.

If it has not been changed (step S201: NO), the overall control unit 110 ends the process.

If it has been changed (step S201: YES), the overall control unit 110 proceeds to the process of step S202.

(Step S202)
The overall control unit 110 sets the changed paper type or the like as the paper setting used for image formation.

(Step S203)
The overall control unit 110 acquires the corresponding measured value information. The corresponding measured value information is information on measured values such as paper thickness, basis weight (density), and paper surface property, which are input to the trained model in order to determine the paper type or the like in the discriminating unit 112.

(Steps S204, S205)
The general control unit 110 reads the address information of the teacher database stored in the storage unit 12 and acquires the final address of the teacher database.

(Step S206)
The general control unit 110 adds the information of the paper type changed by the user and the corresponding measured value information as new teacher data to the address next to the final address of the teacher database. For example, in the teacher database of FIG. 30, when the teacher data recorded at the final address is the teacher data of "No. 802", the new teacher data is No. 802. It is added as 803 data. Subsequently, the overall control unit 110 counts up (increments) the update number N1 which is the number of times the teacher data is added by one, stores it in the storage unit 12, and ends the process.

(Generation and update of paper type discrimination model and paper type discrimination algorithm)
Next, the generation and update processing of the paper type discrimination model and the paper type discrimination algorithm will be described.

FIG. 34 is a flowchart showing the generation and update processing of the paper type discrimination model and the paper type discrimination algorithm executed in the image forming apparatus according to the second embodiment. Hereinafter, description will be made with reference to FIG. 34.

(Step S211)
The overall control unit 110 of the image forming apparatus 10 reads the update number N1 of the teacher data from the storage unit 12.

(Step S212).

The overall control unit 110 executes the paper type determination model update for determining whether or not the update number N1 of the teacher data is equal to or more than a predetermined number of times preset in the storage unit 12 as the execution condition for the paper type determination model update. Details of the setting of the conditions will be described later with reference to FIGS. 36A and 36B.

When the number of updates N1 of the teacher data is not equal to or more than a predetermined number of times (step S212: NO), the overall control unit 110 ends the process.

When the number of updates N1 of the teacher data is equal to or greater than a predetermined number of times (step S212: YES), the overall control unit 110 proceeds to the process of step S213.

(Step S213)
The overall control unit 110 sets the number of updates N1 of the teacher data to zero.

(Step S214)
The overall control unit 110 determines whether or not the update timing set in advance in the storage unit 12 as an execution condition is the “standby state”.

When the update timing preset as the execution condition is the "standby state" (step S214: YES), the overall control unit 110 proceeds to the process of step S215.

When the update timing preset as the execution condition is not the "standby state" (step S214: NO), the overall control unit 110 proceeds to the process of step S216.

(Step S215)
The overall control unit 110 determines whether or not the image forming apparatus 10 is in the standby state.

When not in the standby state (step S215: NO), the overall control unit 110 continues the process of monitoring the state of the image forming apparatus 10 until the image forming apparatus 10 enters the standby state. Alternatively, the overall control unit 110 may temporarily end the process and re-execute the process of FIG. 34 at a predetermined timing.

In the standby state (step S215: YES), the overall control unit 110 proceeds to the process of step S218.

(Step S216)
The overall control unit 110 determines whether or not the update timing preset as the execution condition is the "designated time".

When the update timing preset as the execution condition is the "designated time" (step S216: YES), the overall control unit 110 proceeds to the process of step S217.

If the update timing preset as the execution condition is not the "designated time" (step S216: NO), the overall control unit 110 ends the process assuming that the update execution condition has not been set. Alternatively, the overall control unit 110 may determine the update execution condition based on a predetermined default setting or the like.

(Step S217)
The overall control unit 110 refers to the date and time managed by the date / time management unit 121, and determines whether or not a preset designated time has arrived.

When the designated time has not arrived (step S217: NO), the overall control unit 110 continues the process of monitoring the time when the designated time arrives. Alternatively, the overall control unit 110 may temporarily end the process and re-execute the process of FIG. 34 at a predetermined timing.

When the designated time has arrived (step S217: YES), the overall control unit 110 proceeds to the process of step S218.

(Step S218)
The overall control unit 110 prohibits the acceptance of instructions from the user or the like regarding the printing operation, the adjusting operation, or the like of the image forming apparatus 10.

(Step S219)
The overall control unit 110 generates a paper type discrimination model (FIG. 31) by a random forest based on the teacher database (FIG. 30) stored in the storage unit 12.

(Step S220)
The overall control unit 110 generates a paper type discrimination algorithm that can be executed as a program based on the generated paper type discrimination model. Details of the processes in steps S219 and S220 will be described later with reference to FIG. 35.

(Step S221)
The overall control unit 110 writes the generated paper type determination algorithm to the designated segment of the flash memory of the CPU included in the overall control unit 110.

(Step S222)
The overall control unit 110 permits (releases) the acceptance of instructions from the user or the like regarding the printing operation or adjustment operation of the image forming apparatus 10 prohibited in step S218.

The overall control unit 110 may manage the version information of the generated paper type determination model or the paper type determination algorithm, and display the version information in use on the operation panel 18. Further, the overall control unit 110 may display the above list of version information on the operation panel 18 as an update history. As version information, for example, serial numbers are automatically assigned. In the list, version information, update date and time (creation date and time), etc. are displayed. For example, if the user is not satisfied with the results of the updated version of the paper classification model, he or she can revert to the previous version of the paper classification model by selecting the previous version information displayed in the list. .. Further, as will be described later with reference to FIG. 36B, the user can return to the previous version of the paper type determination model or the next version of the paper type determination model.

(Generation of paper type discrimination model and conversion to paper type discrimination algorithm)
FIG. 35 is a diagram showing a procedure of a paper type discrimination model generation process and a paper type discrimination model conversion process to a binary file.

The process shown in FIG. 35 can be executed, for example, by running R on Linux using a CPU on which LinuxOS is installed. It should be noted that Phthon may be used instead of R to generate a paper type discrimination model or the like.

As shown in the upper part of FIG. 35, when teacher data is input, after data loss processing, data analysis processing, etc. are performed, a discrimination model by a random forest is generated and output as a Tree information file representing a node state. Ru. Subsequently, as shown in the lower part of FIG. 35, a paper type determination algorithm (binary file) that can be incorporated into the executable file is generated from the output Tree information file, and is output as a Tree binary file. The paper type discrimination algorithm (binary file) is written in a rewritable area (segment) dedicated to the paper type discrimination algorithm, which is provided in advance in the flash memory area inside the CPU.

(Setting of execution conditions for updating the paper type discrimination model)
FIG. 36A is an example of a screen that accepts the setting of the execution condition for updating the paper type discrimination model. FIG. 36B is an example of a screen that accepts the selection of the paper type discrimination model.

The image forming apparatus 10 displays, for example, a screen as shown in FIG. 36A on the operation panel 18, and receives from the user the setting of the execution condition for updating the paper type determination model.

On the screen of FIG. 36A, the user can select the "standby state" or the "designated time" for the update timing (update time), which is the execution condition, by operating the touch panel button. When "specified time" is selected as the update timing, the user can set the update time (time when the update is performed) by pressing the up / down buttons of the touch panel buttons "△" and "▽", or by showing the figure. Specify using a numeric keypad or soft key that is not available. As the update time, a day of the week, a date, or the like may be set in addition to the time. Alternatively, the elapsed time from the previous update may be set as the update time. Further, the user can set the number of processes related to the update number N1 of the teacher data, which is the execution condition, by the same setting method as the update time setting. In the example of FIG. 36A, the predetermined number of times is set to 10, and when 10 sets of new teacher data are added, the execution condition regarding the number of times the teacher data is updated is satisfied. In addition, the user can specify whether to update the paper type determination model or select the previous version by selecting the button in the paper type determination model column on the screen of FIG. 36A. When the "Select previous version" button is operated on the screen of FIG. 36A, a screen as shown in FIG. 36B is displayed, for example. On the screen of FIG. 36B, the user can select whether to use the previous version of the paper type determination model, the next version of the paper type determination model, the default model, and the like. .. Each time the user presses the touch panel button of "Select the previous model", the user can go back from the currently selected version of the paper type determination model to the previous version of the paper type determination model. On the contrary, each time the touch panel button of "Select one model after" is pressed, the paper type discrimination model can be returned to the direction of the latest updated version. Also in this case, although not shown, a display is provided that displays the date on which the version of the paper type discrimination model is registered so that the user can recognize the version of the paper type discrimination model selected by the user. Also, if you keep pressing the touch panel button of "Select the previous model" or "Select the next model" and there are no more selection candidates for the paper type discrimination model, it means that there are no more selection candidates. A warning may be displayed, or a warning may be displayed indicating that the default model of the paper type determination model is selected, the latest version of the paper type determination model is selected, and the like.

According to the second embodiment, the discrimination process can be executed by using the latest updated paper type discrimination algorithm. Further, by incorporating the paper type discrimination model into the program as the paper type discrimination algorithm, the time required for the discrimination processing can be shortened. Therefore, the paper setting process according to the present embodiment can be included in the work sequence of the site where the image forming apparatus 10 is used. On the other hand, the generation of the paper type discrimination model, which takes a long time to process, the conversion to the paper type discrimination algorithm, and the embedded processing in the program are performed in a state other than the standby state of the image forming apparatus 10 or the operating state such as printing / adjustment. Thereby, the influence on the normal use of the image forming apparatus 10 can be minimized.

Further, according to the second embodiment, since the paper type discrimination model is generated for each image forming apparatus 10, it is possible to generate an appropriate paper type discrimination model according to the usage situation for each image forming apparatus 10.

(Third Embodiment)
In the first and second embodiments, an example in which the image forming apparatus 10 performs paper discrimination processing, machine learning processing, and the like by itself has been described. In the third embodiment, an example in which each image forming apparatus 10 performs various processes in cooperation with the server 80 connected via the network L will be described. The third embodiment will be described separately from the 3-1st embodiment to the 3rd-3rd embodiment according to the functions executed by each configuration.

(Third 3-1 Embodiment)
In the 3-1st embodiment, the server 80 is provided with a teacher database and a machine learning function, and the server 80 generates a paper type discrimination model and a paper type discrimination algorithm which are trained models. The generated paper type discrimination algorithm is transmitted from the server 80 to the image forming apparatus 10, and the image forming apparatus 10 executes the paper discriminating process using the paper type discriminating algorithm. Hereinafter, the configuration and processing of the third embodiment will be described in detail.

Since the hardware configuration of the image forming apparatus 10 of the 3-1 embodiment is the same as that of the image forming apparatus 10 of the first and second embodiments, detailed description thereof will be omitted.

(Server 80)
FIG. 37 is a block diagram showing a server configuration.

As shown in FIG. 37, the server 80 includes a control unit 81, a communication unit 82, and a storage unit 83 (also referred to as a database), and each configuration is communicably connected to each other by a bus. The server 80 may be provided at the same location as the image forming apparatus 10, or may be provided at a remote location and connected via a network. For example, the server 80 may be a cloud server virtually constructed by a plurality of servers arranged on a network such as the Internet. In the present embodiment, the server 80 or the control unit 81 constitutes a discrimination system in cooperation with the image forming apparatus 10. Further, in the present embodiment, the image forming apparatus 10 or the control unit 11 (overall control unit 110) functions as a discriminating device.

The control unit 81 includes a CPU, RAM, ROM, and the like as the same configuration as the control unit 11 of the image forming apparatus 10.

The communication unit 82 is capable of wired communication based on a standard such as Ethernet (registered trademark) and wireless communication using a standard such as Wi-Fi.

The storage unit 83 stores various information such as setting information required for image formation in each image forming apparatus 10 and a database of teacher data used for machine learning.

FIG. 38 is a block diagram showing a functional configuration of the control unit of the server according to the 3-1 embodiment. FIG. 39 is a block diagram showing a functional configuration of an overall control unit of the image forming apparatus according to the 3-1 embodiment.

As shown in FIG. 38, the control unit 81 of the server 80 functions as the acquisition unit 811 and the learning unit 812. The acquisition unit 811 acquires the measured value information, the paper type information, and the like which are the teacher data from the image forming apparatus 10 and the like. The learning unit 812 performs machine learning based on the teacher data, and generates a paper type discrimination model and a paper type discrimination algorithm which are trained models. Since the function of the learning unit 812 is the same as the processing in the learning unit 113 of the overall control unit 110 of the image forming apparatus 10 described in FIG. 32, detailed description thereof will be omitted.

As shown in FIG. 39, the overall control unit 110 of the image forming apparatus 10 functions as an acquisition unit 111, a discrimination unit 112, an output unit 114, and a reception unit 115. Since the functions of the acquisition unit 111 and the determination unit 112 are the same as those of the image forming apparatus 10 of the first and second embodiments, detailed description thereof will be omitted. The output unit 114 outputs the determination result by the determination unit 112 by displaying it on the operation panel 18 or the like. The reception unit 115 receives an instruction for changing the determination result output by the output unit 114.

The processes executed by each configuration will be described below.

(Sending change information to the server in the image forming device)
FIG. 40 is a flowchart showing a change information transmission process executed in the image forming apparatus according to the 3-1 embodiment. Hereinafter, description will be made with reference to FIG. 40.

(Step S301)
The overall control unit 110 of the image forming apparatus 10 determines whether or not the determination result of the paper type or the like by the determination unit 112 has been changed by the user.

If it has not been changed (step S301: NO), the overall control unit 110 ends the process.

If it has been changed (step S301: YES), the overall control unit 110 proceeds to the process of step S302.

(Step S302)
The overall control unit 110 sets the changed paper type or the like as the paper setting used for image formation.

(Step S303)
The overall control unit 110 determines whether or not a paper type other than the four types is selected (set). In the present embodiment, gloss-coated paper, matte-coated paper, plain paper, and high-quality paper are set as the four types of paper.

When a paper type other than four types is selected (step S303: YES), for example, in the example of FIG. 29, when the paper type is changed to "color paper", "envelope", or "embossed paper", the overall control unit 110 changes the paper type. End the process.

When four types of paper are selected (step S303: NO), the overall control unit 110 proceeds to the process of step S304 and executes the process of adding to the teacher database. In the present embodiment, an example of determining whether or not the changed paper types are the predetermined four types has been described, but the number and types of the predetermined paper types are not limited to this.

(Step S304)
The overall control unit 110 corresponds to acquire the corresponding measured value information. The measured value information is information on measured values such as paper thickness, basis weight (density), and paper surface property, which are input to the trained model in order to determine the paper type and the like in the discriminating unit 112.

(Step S305)
The overall control unit 110 transmits the information of the paper type changed by the user and the corresponding measured value information to the server 80 as new teacher data (additional teacher data) to be added to the teacher database. At this time, the overall control unit 110 may transmit identification information such as a serial number for identifying the image forming apparatus 10 to the server 80 together with the additional teacher data. As a result, the server 80 can grasp which image forming apparatus 10 is the additional teacher data transmitted and manage the additional history of the teacher data for each image forming apparatus 10. As a result, the server 80 can also create a teacher database for each image forming apparatus 10 and generate a paper type discrimination model for each image forming apparatus 10.

(Adding change information on the server to the teacher data)
FIG. 41 is a flowchart showing additional processing of teacher data executed on the server according to the 3-1 embodiment. Hereinafter, description will be made with reference to FIG. 41.

(Step S311)
The control unit 81 of the server 80 determines whether or not there is additional teacher data transmitted from the image forming apparatus 10.

When there is no additional teacher data (step S311: NO), the control unit 81 ends the process.

If there is additional teacher data (step S311: YES), the control unit 81 proceeds to the process of step S312.

(Steps S312, S313)
The control unit 81 reads the address information of the teacher database stored in the storage unit 83 and acquires the final address of the teacher database.

(Step S314)
The control unit 81 writes the information of the paper type changed by the user and the additional teacher data which is the corresponding measured value information to the address next to the final address of the teacher database.

(Step S315)
The control unit 81 counts up (increments) the update number N1 which is the number of times the teacher data is added by one, stores it in the storage unit 83, and ends the process.

(Generation of paper type discrimination model and paper type discrimination algorithm on the server)
FIG. 42 is a flowchart showing a generation process of the paper type discrimination model and the paper type discrimination algorithm executed in the server according to the 3-1 embodiment. Hereinafter, description will be made with reference to FIG. 42.

(Step S321)
The control unit 81 of the server 80 reads the update number N1 of the teacher data from the storage unit 83.

(Step S322)
The control unit 81 determines whether or not the update number N1 of the teacher data is equal to or more than a predetermined number of times set in advance in the storage unit 83 as the execution condition of the paper type determination model update. The execution conditions for updating the paper type determination model are the same as those in the second embodiment, and are set by the user via the image forming apparatus 10 or a setting PC (not shown) and stored in the storage unit 83 of the server 80. Will be done.

When the number of update times N1 of the teacher data is not equal to or more than a predetermined number of times (step S322: NO), the control unit 81 ends the process.

When the number of updates N1 of the teacher data is equal to or greater than a predetermined number of times (step S322: YES), the control unit 81 proceeds to the process of step S323.

(Step S323)
The control unit 81 sets the number of updates N1 of the teacher data to zero.

(Step S324)
The control unit 81 generates a paper type discrimination model (FIG. 31) by a random forest based on the teacher database (FIG. 30) stored in the storage unit 83. The control unit 81 may generate a paper type discrimination model at a timing preset as an execution condition.

(Step S325)
The control unit 81 generates a paper type discrimination algorithm that can be executed as a program based on the generated paper type discrimination model. Since the processing of step S325 and step S326 is the same as the processing of step S219 and step S220 of FIG. 34, detailed description thereof will be omitted. The control unit 81 may generate a paper type determination algorithm at a timing preset as an execution condition.

(Step S326)
The control unit 81 stores the generated paper type determination algorithm in the storage unit 83 as a reference algorithm together with the version information.

(Update of paper type discrimination algorithm in image forming device)
FIG. 43 is a flowchart showing an update process of the paper type determination algorithm executed in the image forming apparatus according to the 3-1 embodiment. Hereinafter, description will be made with reference to FIG. 43.

(Step S331)
The overall control unit 110 of the image forming apparatus 10 accesses the server 80 and acquires the update information of the paper type determination algorithm. For example, the overall control unit 110 acquires the latest version information of the paper type determination algorithm stored in the server 80.

(Step S332)
The overall control unit 110 updates the paper type discrimination algorithm by comparing the latest paper type discrimination algorithm version information acquired from the server 80 with the version information of the paper type discrimination algorithm used by the own machine. Judge whether or not.

If it has not been updated (step S332: NO), the overall control unit 110 ends the process.

If it has been updated (step S332: YES), the overall control unit 110 proceeds to the process of step S333.

(Step S333)
The overall control unit 110 acquires information regarding the execution conditions for updating the paper type determination model from the server 80, the storage unit 12 of the image forming apparatus 10, or the like.

(Step S334)
The overall control unit 110 determines whether or not the update timing preset as the execution condition is the "standby state".

When the update timing preset as the execution condition is the "standby state" (step S334: YES), the overall control unit 110 proceeds to the process of step S335.

When the update timing preset as the execution condition is not the "standby state" (step S334: NO), the overall control unit 110 proceeds to the process of step S336.

(Step S335)
The overall control unit 110 determines whether or not the image forming apparatus 10 is in the standby state.

If it is not in the standby state (step S335: NO), the overall control unit 110 continues the process of monitoring the state of the image forming apparatus 10 until the image forming apparatus 10 is in the standby state. Alternatively, the overall control unit 110 may temporarily end the process and re-execute the process of FIG. 43 at a predetermined timing.

In the standby state (step S335: YES), the overall control unit 110 proceeds to the process of step S338.

(Step S336)
The overall control unit 110 determines whether or not the update timing preset as the execution condition is the "designated time".

When the update timing preset as the execution condition is the "designated time" (step S336: YES), the overall control unit 110 proceeds to the process of step S337.

If the update timing preset as the execution condition is not the "designated time" (step S336: NO), the overall control unit 110 ends the process assuming that the update execution condition has not been set. Alternatively, the overall control unit 110 may determine the update execution condition based on a predetermined default setting or the like.

(Step S337)
The overall control unit 110 refers to the date and time managed by the date / time management unit 121, and determines whether or not a preset designated time has arrived.

When the designated time has not arrived (step S337: NO), the overall control unit 110 continues the process of monitoring the time when the designated time arrives. Alternatively, the overall control unit 110 may temporarily end the process and re-execute the process of FIG. 43 at a predetermined timing.

When the designated time has arrived (step S337: YES), the overall control unit 110 proceeds to the process of step S338.

(Step S338)
The overall control unit 110 prohibits the acceptance of instructions from the user or the like regarding the printing operation, the adjusting operation, or the like of the image forming apparatus 10.

(Step S339)
The overall control unit 110 requests and acquires the latest paper type determination algorithm from the server 80.

(Step S340)
The overall control unit 110 writes the latest paper type determination algorithm acquired from the server 80 into a designated segment of the flash memory of the CPU of the overall control unit 110.

(Step S341)
The overall control unit 110 permits (releases) the acceptance of instructions from the user or the like regarding the printing operation or adjustment operation of the image forming apparatus 10 prohibited in step S338.

According to the third embodiment, since the generation process of the paper type discrimination model, which takes a long processing time, is executed on the server 80, the blockage time of the printing process of the image forming apparatus 10 and the like accompanying the generation process of the paper type discrimination model Is shortened. Further, since the server 80 generates and holds the latest updated paper type discrimination algorithm, a plurality of image forming devices 10 connected to the server 80 can share the latest paper type discrimination algorithm. Further, by creating a teacher database for each image forming apparatus 10 on the server 80, it is possible to generate a paper type discrimination algorithm according to the usage status of each image forming apparatus 10.

(Third 3-2 Embodiment)
In the third-2nd embodiment, the paper type discrimination algorithm which is a trained model is implemented in the server 80, and the paper discrimination processing is executed in the server 80. Hereinafter, the configuration and processing of the 3-2nd embodiment will be described in detail.

The hardware configurations of the image forming apparatus 10 and the server 80 of the 3-2nd embodiment are the same as those of the 3-1st embodiment.

FIG. 44A is a block diagram showing a functional configuration of a control unit of the server according to the third to second embodiment.

As shown in FIG. 44A, the control unit 81 of the server 80 functions as the acquisition unit 811 and the determination unit 813. Since the function of the acquisition unit 811 is the same as that of the acquisition unit 811 of the server 80 of the 3-1 embodiment described with reference to FIG. 37, detailed description thereof will be omitted. Since the function of the discrimination unit 813 is the same as the processing in the discrimination unit 112 of the overall control unit 110 of the image forming apparatus 10 described with reference to FIG. 18B, detailed description thereof will be omitted. In the present embodiment, the server 80 or the control unit 81 functions as a discriminating device.

FIG. 44B is a block diagram showing a functional configuration of an overall control unit of the image forming apparatus according to the third to second embodiment.

As shown in FIG. 44B, the overall control unit 110 of the image forming apparatus 10 functions as an acquisition unit 111, an output unit 114, and a reception unit 115. Since the functions of the acquisition unit 111, the output unit 114, and the reception unit 115 are the same as those of the image forming apparatus 10 of the 3-1 embodiment, detailed description thereof will be omitted.

The processes executed by each configuration will be described below.

(Paper setting process in the image forming device)
FIG. 45 is a flowchart showing a paper setting process (corresponding to step S10 in FIG. 19) executed in the image forming apparatus according to the third-2 embodiment. Hereinafter, description will be made with reference to FIG. 45.

(Steps S350, S351)
The transport control / image formation control unit 160 of the control unit 11 opens the shutter 651 by the opening / closing mechanism 65, then feeds the paper S from the selection tray and transports the paper S to the transport path 143.

(Step S352a)
The media sensor control unit 130 detects the paper thickness of the paper S by the paper thickness sensor 40, and passes the detection data (measured value 1) to the overall control unit 110.

(Steps S352b, S352c)
The media sensor control unit 130 detects the basis weight and surface quality of the paper by the basis weight sensor 50 and the surface surface sensor 60, and passes the detection data (measured values 2 and 3) to the overall control unit 110. Since the processes of steps S352b and S352c are the same as those of steps S102b and S102c of FIG. 20, detailed description thereof will be omitted.

(Step S353)
The overall control unit 110 determines whether or not the measurement has been performed a predetermined number of N times.

If the measurement has not been performed a predetermined number of N times (step S353: NO), the overall control unit 110 repeats the processes of steps S352b and S352c.

If the measurement has been performed a predetermined number of N times (step S353: YES), the overall control unit 110 proceeds to the process of step S354.

(Step S354)
When the rear end of the paper S has passed through the media sensor 15, specifically, when the paper sensor (not shown) detects that the rear end of the paper S has passed through the transport roller 1434 (YES), the process is performed. Proceed to step S355.

(Step S355)
Here, the control unit 11 closes the shutter 651 by the opening / closing mechanism 65 to bring it into a closed state. This prevents the surface sensor 60 from being contaminated by paper dust or the like due to the paper S that is conveyed when the measurement is not performed by the media sensor 15.

(Step S356)
The overall control unit 110 performs an averaging process on the detection data (measured values 2 and 3) of the basis weight and surface properties of N times acquired in steps S352b and S352c. The overall control unit 110 stores the information acquired in the processes of steps S352a to S356 in the storage unit 12 as measured value information.

(Step S357)
The overall control unit 110 transmits the measured value information to the server 80.

(Step S358)
The overall control unit 110 acquires the determination result such as the paper type / basis weight classification determined by the server 80 based on the measured value information from the server 80. The discrimination process on the server 80 will be described later.

(Step S359)
The overall control unit 110 acquires the determination result of the registration profile determined on the server 80 based on the measured value information from the server 80.

(Step S360)
The overall control unit 110 displays the determination result acquired from the server 80 on the operation panel 18, and receives instructions from the user such as application or change of the paper type, registration profile, control parameters, and the like.

(Step S361)
The overall control unit 110 determines whether or not the information such as the paper type acquired as the determination result has been changed by the user.

When the information acquired as the determination result is accepted without being changed (step S361: NO), the overall control unit 110 proceeds to the process of step S362.

When the information acquired as the determination result is changed (step S361: YES), the overall control unit 110 proceeds to the process of step S363.

(Step S362)
The overall control unit 110 sets the acquired information such as the paper type in the selection tray of the image forming apparatus 10.

(Step S363)
The overall control unit 110 sets information such as the changed paper type in the selection tray of the image forming apparatus 10, and transmits a registration instruction of the change information to the server 80.

(Step S364)
The overall control unit 110 sets the print conditions of the selected tray to the print conditions corresponding to the set information such as the paper type.

(Discrimination process on the server)
FIG. 46 is a flowchart showing a paper type determination process executed on the server according to the third to second embodiment. Hereinafter, description will be made with reference to FIG. 46.

(Step S371)
The control unit 81 of the server 80 acquires the measured value information transmitted from the image forming apparatus 10 in the process of step S357 of FIG. 45.

(Step S372)
The control unit 81 determines the paper type and the basis weight classification based on the measured value information. Since the process of step S372 is the same as the paper type determination process and the basis weight classification determination process of step S107 of FIG. 20, detailed description thereof will be omitted.

(Step S373)
The control unit 81 reads out a preset profile which is a registered profile stored in advance in the storage unit 83.

(Step S374)
The control unit 81 determines the candidate of the preset profile to be used based on the paper type and the basis weight classification determined in step S372.

(Step S375)
The control unit 81 reads out a user profile, which is a registration profile registered by the user and stored in the storage unit 83.

(Step S376)
The control unit 81 determines the candidate of the user profile to be used based on the paper type and the basis weight classification determined in step S372. The details of the determination process of the profile candidate to be used will be described later with reference to FIG. 60.

(Step S377)
The control unit 81 transmits to the image forming apparatus 10 information indicating the paper type and basis weight classification determined in step S372, the preset profile determined in step S374, the user profile candidates determined in step S376, and the like. ..

(Registration process of change information on the server)
FIG. 47 is a flowchart showing a change information registration process executed on the server according to the third-2 embodiment. Hereinafter, description will be made with reference to FIG. 47.

(Step S381)
The control unit 81 of the server 80 determines whether or not the registration instruction of the change information transmitted from the image forming apparatus 10 is received in the process of step S363 of FIG. 45.

If not received (step S381: NO), the control unit 81 ends the process.

When receiving (step S381: YES), the control unit 81 proceeds to the process of step S382.

(Steps S382, S383)
The control unit 81 acquires change information including information such as the changed paper type, registration profile, and control parameters from the image forming apparatus 10, and registers the acquired change information in the storage unit 83.

According to the third-2nd embodiment, since the discrimination process is executed on the server 80, the discrimination process can be shared among the plurality of image forming devices 10 connected via the network, and different image forming devices can be shared. Even if it is 10, the same determination result can be obtained.

Further, setting information such as a user profile and control parameters stored for each image forming apparatus 10 can be stored in the server 80 for each image forming apparatus 10, for example, a specific user registered in a certain image forming apparatus 10. The user profile and control parameters of are also available in the other image forming apparatus 10.

(Third 3rd Embodiment)
In the 3rd-3rd embodiment, as in the 3-1st embodiment, the server 80 is provided with the teacher database and the machine learning function, and the paper type discrimination model and the paper type discrimination algorithm which are the trained models are generated in the server 80. Will be done. Further, in the 3rd-3rd embodiment, as in the 3rd-2nd embodiment, the generated paper type discrimination algorithm is implemented in the server 80, and the paper discrimination processing using the paper type discrimination algorithm is executed in the server 80. The algorithm. Hereinafter, the configuration and processing of the third to third embodiments will be described in detail.

The hardware configurations of the image forming apparatus 10 and the server 80 of the 3rd-3rd embodiment are the same as those of the 3-1st embodiment and the 3rd-2nd embodiment.

FIG. 48A is a block diagram showing a functional configuration of the control unit of the server according to the third to third embodiment.

As shown in FIG. 48A, the control unit 81 of the server 80 functions as an acquisition unit 811, a learning unit 812, and a discrimination unit 813. Since the functions of the acquisition unit 811 and the learning unit 812 are the same as those of the acquisition unit 811 of the server 80 of the 3-1 embodiment described with reference to FIG. 37, detailed description thereof will be omitted. Further, since the function of the discriminating unit 813 is the same as that of the discriminating unit 813 of the server 80 of the third-2 embodiment described with reference to FIG. 44, detailed description thereof will be omitted. In the present embodiment, the server 80 or the control unit 81 functions as a discrimination device or a discrimination system.

FIG. 48B is a block diagram showing a functional configuration of an overall control unit of the image forming apparatus according to the third to third embodiments.

As shown in FIG. 48B, the overall control unit 110 of the image forming apparatus 10 functions as an acquisition unit 111, an output unit 114, and a reception unit 115. Since the functions of the acquisition unit 111, the output unit 114, and the reception unit 115 are the same as those of the image forming apparatus 10 of the 3-1 and 3-2 embodiments, detailed description thereof will be omitted.

The processes executed by each configuration will be described below.

(Paper setting process in the image forming device)
The paper setting process executed by the image forming apparatus 10 of the 3rd-3rd embodiment is the same as the paper setting process of the image forming apparatus 10 of the 3-2nd embodiment described with reference to FIG. 45.

(Registration of change information on the server and addition to teacher data)
FIG. 49 is a flowchart showing a change information registration process executed on the server according to the third to third embodiment. Hereinafter, description will be made with reference to FIG. 49.

(Step S391)
The control unit 81 of the server 80 determines whether or not the registration instruction of the change information transmitted from the image forming apparatus 10 is received in the process of step S363 of FIG. 45.

If not received (step S391: NO), the control unit 81 proceeds to the process of step S394.

When receiving (step S391: YES), the control unit 81 proceeds to the process of step S392.

(Steps S392 and S393)
The control unit 81 acquires change information including information such as the changed paper type, registration profile, and control parameters from the image forming apparatus 10, and registers the acquired change information in the storage unit 83.

(Step S394)
The control unit 81 determines whether or not an instruction regarding addition to the teacher data has been received from the image forming apparatus 10.

If not received (step S394: NO), the control unit 81 ends the process.

When receiving (step S394: YES), the control unit 81 proceeds to the process of step S395.

(Steps S395, S396)
The control unit 81 acquires and associates the measured value information corresponding to the changed paper type from the image forming apparatus 10, and additionally registers the associated information in the teacher database of the storage unit 83. The additional processing to the teacher database is the same as the additional processing to the teacher database in the server 80 of the 3-1 embodiment described with reference to FIG. 41.

(Generation of paper type discrimination model and paper type discrimination algorithm on the server)
FIG. 50 is a flowchart showing the generation and update processing of the paper type discrimination model and the paper type discrimination algorithm executed in the server according to the third to third embodiments. Hereinafter, description will be made with reference to FIG. 50.

(Steps S3101 to S3105)
Since the processing of steps S3101 to S3105 is the same as the processing of steps S321 to S325 in the server 80 of the 3-1 embodiment described with reference to FIG. 42, detailed description thereof will be omitted.

(Step S3106)
The control unit 81 of the server 80 writes the executable paper type determination algorithm generated in the process of step S3105 to the designated segment of the flash memory of the CPU of the control unit 81, and ends the process.

According to the third to third embodiment, since the generation and update processing of the paper type discrimination model, which takes a long time, is executed on the server 80, the printing process of the image forming apparatus 10 accompanying the generation and update processing of the paper type discrimination model Etc. are minimized. Further, by generating and executing the updated latest paper type discrimination algorithm by the server 80, a plurality of image forming devices 10 connected to the server 80 can share the latest paper type discrimination algorithm. Further, by creating a teacher database for each image forming apparatus 10 on the server 80, it is possible to generate and execute a paper type discrimination algorithm according to the usage status of each image forming apparatus 10. For example, the paper type determination algorithm may be provided for each individual in the same model of the image forming apparatus 10. In this case, a paper type discrimination algorithm is provided for each of the image forming apparatus 10a, 10b, 10c, etc., which is an image forming apparatus 10 which is a different machine of one model. Further, the paper type discrimination algorithm may be provided for each model of the image forming apparatus 10. In this case, a paper type discrimination algorithm is provided for each of the different models of the image forming apparatus 10, such as the image forming apparatus a, the image forming apparatus a, and the image forming apparatus c. Alternatively, the paper type determination algorithm may be provided for each model and individual of the image forming apparatus 10. In this case, different models of the image forming apparatus 10, such as the image forming apparatus a, the image forming apparatus a, the image forming apparatus c, and the like, the image forming apparatus a-10a, the image forming apparatus a-10b, and the image forming apparatus 10b. Device A-10c, etc., Image forming device A-10a', Image forming device A-10b', Image forming device A-10c', etc., Image forming device U-10a ", Image forming device U-10b", Image forming device A paper type discrimination algorithm is provided for each of W-10c "and the like.

(Modification example using neural network as trained model)
In the above embodiment, an example of generating a paper type discrimination model which is a trained model by using a random forest model has been described, but the paper type discrimination model is generated by using another machine learning model such as a neural network. May be good.

FIG. 51 is a diagram showing an example of discriminating a paper type using a trained model of a neural network machine-learned using teacher data.

As shown in FIG. 51, a deep neural network (DNN), which is a neural network having an input layer, an output layer, and a plurality of hidden layers (intermediate layers), is configured, and deep learning (deep learning) using teacher data is performed. Will be executed. In the example of DNN shown in FIG. 51, the input layer is provided with data obtained by averaging the amount of specular reflected light and the amount of diffuse reflected light measured by the surface sensor 60, and the basis weight sensor 50 and the paper thickness sensor 40. Data obtained by averaging each of the measured values related to the basis weight and the paper thickness are input. Further, data obtained by applying a predetermined preprocessing to the surface image of the paper taken by the camera described later is also input to the input layer. From the output layer, data on the discriminating paper type such as gloss coated paper, matte coated paper, high quality paper, and plain paper is output. A paper type discrimination model is generated by machine learning the DNN shown in FIG. 51 using the teacher data shown in FIG. 30. Since the neural network using the teacher data, the machine learning process of DNN, and the discrimination process using the trained model are known, detailed description thereof will be omitted.

FIG. 52 is a diagram illustrating an imaging mechanism for acquiring a surface image. FIG. 53 is a diagram illustrating surface images of gloss-coated paper, matte-coated paper, wood-free paper, and plain paper acquired by the photographing mechanism, and their respective characteristics.

As shown in FIG. 52, the photographing mechanism 1500 includes a camera 1501, an LED 1502, and a reflector 1503. The photographing mechanism 1500 is provided, for example, in the transport path of the paper S in the image forming apparatus 10. The camera 1501 is, for example, a CMS color camera module provided with a proximity macro lens and has a pixel size of 2 μm to 10 μm. The paper S to be conveyed is arranged at a predetermined paper position by the paper holding mechanism. The light output from the LED 1502 is reflected by the reflector 1503 and irradiates the surface of the paper S arranged at a predetermined paper position. The LED 1502 uses a white light emitting LED. The irradiation angle with respect to the paper S can be set in the range of 95 ° to 80 °, and the paper surface image difference can be detected. The closer it is to 95 °, the more oblique light is applied, so it is easier to detect the difference in unevenness on the surface of the paper S, but as a result of verification, 90 ° is desirable. The distance and depth of the subject can be set by the focal length and brightness of the lens, but in order to read the image of the paper surface condition with high accuracy, the paper S is stopped and the paper is pushed up with a push-up plate in the same way as the surface sensor 60. It is fixed and read. The camera 1501 photographs the surface of the paper S in the portion irradiated with the light output from the LED 1502, and acquires a surface image of each type of paper S as shown in FIG. 53. As shown in FIG. 53, the smoothness of the paper surface is low, the surface is rough, and the image density is high in the order of gloss-coated paper, matte-coated paper, wood-free paper, and plain paper. In the above, the LED 1502 is a white light emitting LED in order to read the paper surface color as well, but in order to extract the characteristics of the image on the paper surface, an LED having a light emitting color other than white or an infrared color may be adopted. Good. Alternatively, a white light emitting LED may be used, and a cut filter that allows only a specific light wavelength to pass may be attached in front of the lens of the camera.

The data indicating the surface image acquired by the photographing mechanism 1500 is stored in the teacher database stored in the image forming apparatus 10 or the server 80 after being subjected to predetermined preprocessing by, for example, the control unit 11 (overall control unit 110). Will be added. As a predetermined pretreatment, for example, in order to acquire the feature amount of the unevenness of the paper surface, an integral value processing of a predetermined frequency band when the surface image is frequency-analyzed may be executed. Alternatively, as a predetermined preprocessing, a process of outputting the average gradation (the amount of scattered light as a whole) and the standard deviation (shading variation) of one image line may be executed. Further, as a predetermined pretreatment, a binarization process using a threshold value at which the characteristic of unevenness on the paper surface becomes apparent may be executed.

By generating the paper type discrimination model using the neural network (deep neural network) in this way, it becomes easy to introduce the surface image as an input factor for machine learning. As a result, the characteristics and state of the unevenness of the paper surface, which is expressed as the amount of density variation in the surface image, can be used as a parameter for determining the paper type, so that the paper type can be determined accurately. It takes time to tune (adjust) the weights of each layer of the neural network when performing machine learning. Therefore, as in each of the above embodiments, the influence on the normal use of the image forming apparatus 10 is suppressed by controlling the execution presence / absence, the execution timing, the configuration to be executed, and the like of the process of generating or updating the trained model. The effect of the treatment is more remarkable.

(About 1st tsubo and 2nd tsubo)
Hereinafter, a method for obtaining the first and second tsubo and an example of using the difference in tsubo (first tsubo-2 tsubo) for determining the paper type will be described.

First, the configuration of the basis weight sensor 50 will be described in detail.

(Configuration of basis weight sensor 50)
FIG. 54 is a schematic view showing the configuration of the basis weight sensor 50. As described above, the basis weight sensor 50 is a transmission type optical sensor that detects the basis weight of the paper, includes a light emitting portion and a light receiving portion, and measures by the amount of attenuation of the light transmitted through the paper S.

As shown in FIG. 54, the basis weight sensor 50 includes a plurality of light emitting units 51 and a single light receiving unit 52. The light emitting unit 51 includes a first light emitting unit 51a, a second light emitting unit 51b, and a third light emitting unit 51c. From the first, second, and third light emitting units, the first, second, and third irradiation lights are irradiated to the irradiation region, respectively. This irradiation region (second irradiation region) is an inner region of the opening a12 when viewed from the Z'direction. The opening a12 is provided in the upper guide 1431. Further, the lower guide 1432 is also provided with an opening a22 at a position facing the opening a12. The openings a22 and a12 have the same shape, and are, for example, rectangular. A transparent sheet made of PET or the like and transmitting the wavelength of each irradiation light in order to prevent foreign matter such as paper dust from the paper S passing through the transport path 143 from adhering to the openings a22 and a12. 54a and 54b are attached.

The first light emitting unit 51a irradiates the first irradiation light having the first wavelength. The first wavelength is, for example, a wavelength of near infrared rays that is longer than the wavelength of visible light. More specifically, the first wavelength includes, for example, wavelengths between 750 nm and 900 nm. The second light emitting unit 51b irradiates the second irradiation light having the second wavelength. The second wavelength is, for example, the wavelength of a blue ray included in visible light. More specifically, the second wavelength includes, for example, wavelengths between 400 nm and 470 nm. Both the first light emitting unit 51a and the second light emitting unit 51b are arranged on the opposite side of the transport path 143 from the light receiving unit 52, and the third light emitting unit 51c is on the same side as the light receiving unit 52. Therefore, it is provided in the vicinity of the light receiving unit 52. The third light emitting unit 51c irradiates the third irradiation light having a third wavelength toward the irradiation region (aperture a12). The third wavelength is, for example, the wavelength of the green ray of the visible light. More specifically, the third wavelength includes, for example, wavelengths between 495 nm and 570 nm. The third wavelength is different from the first wavelength (eg, wavelength between 750 nm and 900 nm) and the second wavelength (eg, 400 nm to 470 nm).

The third irradiation light is emitted toward the transport path 143 in the vertical guides 1431 and 1432. A reflection unit 53 is provided inside the lower guide 1432 provided in the vicinity of the first light emitting unit 51a and the second light emitting unit 51b. The reflecting portion 53 is, for example, painted in green, which is the same color as the third irradiation light, and reflects the third irradiation light. The reflecting unit 53 does not reflect the first irradiation light (near infrared rays) and the second irradiation light (blue rays) that are not the same color.

In the present embodiment, the control unit 11 controls the first light emitting unit 51a and the second light emitting unit 51b at the time of measurement, and irradiates the first irradiation light and the second irradiation light at different timings, respectively. The light receiving unit 52 receives the first irradiation light and the second irradiation light, detects the light amount of each irradiation light, and transmits the detected light amount of the first irradiation light and the light amount of the second irradiation light to the control unit 11. Output. Further, the paper S transported to the position of the opening a12 is similarly irradiated with the first irradiation light and the second irradiation light. The light receiving unit 52 receives the transmitted light (first transmitted light, second transmitted light) of the first irradiation light and the second irradiation light, detects the amount of each irradiation light, and detects the first transmitted light. The amount of light and the amount of light of the second transmitted light are output to the control unit 11. That is, the light receiving unit 52 detects the first irradiation light and the second irradiation light when there is no paper S, and the first transmitted light and the second transmitted light when the paper S is in the opening a12.

Similarly, regarding the third light emitting unit 51c, the light receiving unit 52 reflects the first reflected light reflected by the reflecting unit 53 when there is no paper S, and is reflected by the surface of the paper S when the paper S is in the opening a12. The second reflected light is detected.

The control unit 11 calculates the first transmittance by dividing the amount of light of the first transmitted light by the amount of light of the first irradiation light. Similarly, the second transmittance is calculated by dividing the amount of the second transmitted light by the amount of the second irradiation light. Then, the type of paper S is determined from these first and second transmittances and the determination criteria stored in the storage unit 12.

Further, the control unit 11 calculates the reflectance by dividing the amount of light of the third reflected light by the amount of light of the first reflected light in addition to the first and second transmittances, and takes this reflectance into consideration. , The type of paper S may be determined. In this embodiment, the third light emitting unit 51c and the reflecting unit 53 are provided, but these may be omitted.

Next, the function of the basis weight sensor 50 will be described.

(Function of basis weight sensor 50)
FIG. 55 is a block diagram showing a functional configuration of a basis weight sensor and a control unit in which the third light emitting unit 51c and the reflecting unit 53 are omitted.

Hereinafter, with reference to FIG. 55, the function of controlling the light emitting unit 51 will be described first, and the functions executed thereafter will be described in order. The control unit 11 functions as an irradiation control unit 1100 that controls the timing at which the light emitting unit 51 irradiates the irradiation light. The irradiation control unit 1100 outputs an instruction signal instructing the irradiation of the irradiation light to the first light emitting unit 51a and the second light emitting unit 51b. The first light emitting unit 51a and the second light emitting unit 51b irradiate the first irradiation light and the second irradiation light at different timings.

The light receiving unit 52 receives the first irradiation light and the second irradiation light, detects the amount of each irradiation light, and controls the detected light amount of the first irradiation light and the light amount of the second irradiation light. Output to. When the paper S is conveyed, the light receiving unit 52 receives the first transmitted light that the first irradiation light transmitted through the paper S and the second transmitted light that the second irradiation light transmitted through the paper S. The detected light amount of the first transmitted light and the light amount of the second transmitted light are output to the control unit 11.

The control unit 11 calculates the transmittance based on the light amount of the irradiation light and the light amount of the transmitted light as the transmittance calculation unit 1120. The transmittance calculation unit 1120 calculates the first transmittance by dividing the amount of light of the first transmitted light by the amount of light of the first irradiation light. The transmittance calculation unit 1120 calculates the second transmittance by dividing the amount of the second transmitted light by the amount of the second irradiation light.

The control unit 11, as the type determination unit 1140, determines the basis weight derivation paper type, which is the type of the paper S for selecting the formula for converting the basis weight based on the calculated first transmittance and the second transmittance. judge. More specifically, the type determination unit 1140 includes a first transmittance and a second transmittance, a predetermined determination standard among a plurality of determination criteria 124 stored in the storage unit 12, and a basis weight threshold value 126. Is used to determine the basis weight derivation paper type of the paper S. Alternatively, the basis weight derivation paper type used by the basis weight derivation unit 1160 of the paper S may be determined from the reflected light amount value detected by the surface sensor 60.

The control unit 11 derives the first grammage and the second grammage as the grammage deriving unit 1160 as the grammage according to the determination criteria based on the determined grammage deriving paper type of the paper S. The details of the process of acquiring the first basis weight and the second basis weight will be described later.

The judgment criteria will be described below.

(Criteria)
The determination criteria will be described with reference to FIGS. 56 to 58. FIG. 56 is a diagram showing a determination criterion showing the relationship between the first transmittance and the nominal basis weight. More specifically, FIG. 56 shows the respective transmittances and the nominal basis weight obtained when the plain paper, the coated paper and the recycled paper are irradiated with the first irradiation light (near infrared rays) having the first wavelength. The relationship with is shown. The transmittance is a value obtained by an experiment. The nominal basis weight is the nominal basis weight of the paper S announced by a manufacturer or the like that manufactures the paper S.

In FIG. 56, the index showing the relationship between the transmittance of plain paper and the nominal basis weight is a diamond, the index showing the relationship between the transmittance of coated paper and the nominal basis weight is a quadrangle, and the transmittance of recycled paper and the nominal basis weight are used. The index showing the relationship between the two is shown by a triangle. For example, index 601 indicates that for a piece of plain paper, the transmittance calculated by the experiment is about 25%, and the nominal basis weight of the plain paper used in the experiment is about 100 g / m ² . As another example, the index 602 indicates that for a coated paper, the experimentally calculated transmittance is about 30% and the nominal basis weight of the coated paper used in the experiment is about 100 g / m ^2. .. In addition, the transmittance of recycled paper is also calculated by experiments, and the nominal basis weight of recycled paper used in the experiments is indicated by an index.

In the experiment, a plurality of indexes on plain paper, a plurality of indexes on coated paper, and a plurality of indexes on recycled paper are calculated. Based on these indexes, for example, an approximation line using the least squares method is derived by a control unit (not shown) provided in a PC (Personal Computer) used in the experiment. More specifically, the determination standard 611 (dashed line) for plain paper, the determination standard 612 (solid line) for coated paper, and the determination standard 613 (broken line) for recycled paper are derived. A plurality of determination criteria 124 including the determination criteria 611 to 613 are stored in the storage unit 12.

FIG. 57 is a diagram showing a determination criterion showing the relationship between the second transmittance and the nominal basis weight. More specifically, in FIG. 57, the transmittances obtained when the plain paper, the coated paper and the recycled paper are irradiated with the second irradiation light (blue light rays contained in the visible light) having the second wavelength. The relationship between the rate and the nominal basis weight is shown. In FIG. 57, the index showing the relationship between the transmittance of plain paper and the nominal basis weight is a diamond, the index showing the relationship between the transmittance of coated paper and the nominal basis weight is a quadrangle, and the transmittance of recycled paper and the nominal basis weight are used. The index showing the relationship between the two is shown by a triangle.

For plain paper, coated paper, and recycled paper, multiple indexes are calculated for each. Based on these indexes, for example, an approximation line using the least squares method is derived by a control unit provided in the PC used in the experiment. More specifically, the determination standard 711 (dashed line) for plain paper, the determination standard 712 (solid line) for coated paper, and the determination standard 713 (broken line) for recycled paper are derived. The storage unit 12 can store a plurality of determination criteria 124 including the determination criteria 711 to 713.

The storage unit 12 may store the determination criteria of the approximate line as a table, or may store the mathematical formula corresponding to the approximate line. For example, in the judgment criteria 611 to 613, the mathematical formula when the basis weight is y1 is the following formula (1).

y1 = exp (b1 x Log (x1) + b2) ... (1)
x1 represents the first transmittance, and b1 and b2 represent constants. The first transmittance used in the formula (1) is a value obtained by dividing the transmittance by 100 (for example, in the case of a transmittance of 25%, 25/100 = 0.25). The control device 101 reads out the equation (1) stored in the storage unit 12 and substitutes the transmittance into the equation (1) to derive the basis weight. By changing at least one of the constants of b1 and b2, a mathematical formula corresponding to any of the determination criteria 611, the determination criteria 612, and the determination criteria 613 is generated.

For example, in the judgment criteria 711 to 713, the mathematical formula when the basis weight is y2 is the following formula (2).

y2 = exp (a1 x Log (x2) ² + a2 x Log (x2) + a3) ... (2)
x2 represents the second transmittance, and a1, a2, and a3 represent constants. The second transmittance used in the formula (2) is a value obtained by dividing the transmittance by 100 (for example, in the case of a transmittance of 30%, 30/100 = 0.3). The control device 101 reads out the equation (2) stored in the storage unit 12 and substitutes the transmittance into the equation (2) to derive the basis weight. By changing at least one of the constants of a1, a2, and a3, a mathematical formula corresponding to any of the determination criteria 711, the determination criteria 712, and the determination criteria 713 is generated.

The reason why the first wavelength and the second wavelength are used when calculating the transmittance is that these wavelengths have less variation in the indexes constituting the approximation line in the judgment criteria than the other wavelengths. .. More specifically, the index showing the relationship between the transmittance and the nominal basis weight at the first wavelength and the second wavelength is on an approximate line than the index showing the relationship between the transmittance and the nominal basis weight at other wavelengths. There are many in or near the approximate line. The first wavelength and the second wavelength are wavelengths in which the correlation between the transmittance and the basis weight is higher than that of the other wavelengths. Therefore, the first irradiation light having the first wavelength and the second irradiation light having the second wavelength are used for calculating the transmittance for deriving the basis weight.

FIG. 58 is a diagram showing the correlation between the transmittance at the wavelength and the nominal basis weight. With reference to FIG. 58, it corresponds to the first wavelength corresponding to the wavelength of near infrared rays (750 nm to 900 nm) having a relatively long wavelength (nm), and the wavelength of the blue light of visible light (400 nm to 470 nm). The second wavelength indicates a value whose determination coefficient is closer to "1" as compared with other wavelengths (for example, 500 nm to 700 nm). When the coefficient of determination at a certain wavelength is close to "1", the irradiation light having the wavelength has a high correlation between the transmittance and the nominal basis weight. When the correlation between the transmittance and the nominal basis weight is high, the variation of the plurality of indexes with respect to the approximate line is smaller than when the correlation is low. Referring to FIG. 58, since the coefficient of determination at the first wavelength and the second wavelength is close to “1”, the irradiation light having these wavelengths has a high correlation between the transmittance and the nominal basis weight. Become. The values showing the correlation between the transmittance and the basis weight at the wavelength of FIG. 58 were obtained by the experiments described in FIGS. 56 and 57. Further, although FIG. 58 shows the correlation in plain paper, other types of paper S (for example, coated paper and the like) also have the same correlation.

The reason why the correlation differs depending on the wavelength is that even if the type of paper S is the same, the components constituting the paper S are different. When the types of the paper S are the same, the nominal basis weight is almost the same basis weight, but when the components are different, the transmittance detected when the paper S is irradiated with the irradiation light may be different. Paper S contains, for example, at least one component of calcium carbonate, kaolin, talc, satin white and the like. When these components are contained in the paper S, the index based on the first irradiation light having the first wavelength and the index based on the second irradiation light having the second wavelength have little variation with respect to the approximate line. The index based on the irradiation light of other wavelengths has a large variation with respect to the approximate line.

The image forming apparatus 10 calculates the transmittance using irradiation light having a wavelength having a higher correlation between the transmittance and the nominal basis weight than other wavelengths, and derives the basis weight corresponding to the transmittance. , Accurate basis weight can be derived. Even when the basis weight is derived by the irradiation light having a wavelength having a high correlation, the difference between the derived basis weight and the nominal basis weight may become extremely large depending on the components of the paper S. Therefore, using a plurality of irradiation lights having highly correlated wavelengths (for example, a first irradiation light having a first wavelength and a second irradiation light having a second wavelength), based on their respective basis weights, Derivation of the basis weight with a small difference from the nominal basis weight. The details of the process for deriving the basis weight having a small difference from the nominal basis weight will be described later.

(Basis weight difference (1st basis weight-2nd basis weight) and basis weight threshold)
FIG. 59 is a diagram showing an index showing the correspondence between the transmittance and the basis weight difference and the basis weight threshold value 126. More specifically, the index represents the correspondence between the transmittance and the basis weight difference in plain paper and the correspondence relationship between the transmittance and the basis weight difference in coated paper. The transmittance and the basis weight difference are the values obtained by the experiment. The transmittance is, for example, a first transmittance calculated using first irradiation light (near infrared rays) having a first wavelength. As described above, the basis weight difference is the difference between the first basis weight and the second basis weight. The first basis weight is the basis weight corresponding to the transmittance derived using the determination standard 611 of plain paper at the first wavelength shown in FIG. 56. The second basis weight is the basis weight corresponding to the transmittance derived using the determination standard 711 of plain paper at the second wavelength shown in FIG. 57.

In FIG. 59, an index showing the relationship between the transmittance of plain paper and the difference in basis weight is represented by a diamond. The index of plain paper is plotted at a position where the basis weight difference corresponding to the transmittance is about -10 g / m ^{2 or more.} An index showing the relationship between the transmittance of coated paper and the difference in basis weight is represented by a quadrangle. The index of coated paper is plotted at a position where the basis weight difference corresponding to the transmittance is about -15 g / m ^{2 or less.} A threshold value for determining the type of plain paper and coated paper is set based on the difference in basis weight between plain paper and coated paper. For example, a basis weight threshold value 126 having a basis weight difference of −12 g / m ² is set and stored in the storage unit 12.

The reason why the index of coated paper has a large difference in basis weight compared to the index of plain paper is that the basis weight corresponding to the first transmittance and the basis weight corresponding to the second transmittance are determined by predetermined criteria (for example). , This is because it is derived using the criteria for plain paper).

More specifically, the index of coated paper has a larger difference in basis weight than the index of plain paper for the following reasons. First, it is assumed that when the paper S is plain paper, substantially the same basis weight is derived regardless of which of the determination criteria 611 and the determination criteria 711, which are the criteria for plain paper, is used. Further, it is assumed that when the paper S is coated paper, substantially the same basis weight is derived regardless of which of the determination criteria 612 and the determination criteria 712, which are the determination criteria of the coated paper, is used.

Next, when the basis weight corresponding to the transmittance of the paper S was derived using the judgment standard 711 of plain paper, the basis weight corresponding to the same transmittance was derived using the determination criterion 712 of coated paper. The difference in basis weight is relatively small compared to the case. An example in which the difference in basis weight is relatively small is the difference between the nominal basis weight of the determination standard 711 at a certain transmittance and the nominal basis weight of the determination standard 712 at the same transmittance. Since the difference in basis weight is relatively small, the difference in basis weight corresponding to a certain transmittance is small regardless of whether the type of paper S is coated paper or plain paper. On the other hand, when the basis weight corresponding to the transmittance of the paper S is derived using the judgment standard 611 of plain paper, the basis weight corresponding to the same transmittance is obtained by using the judgment criterion 612 of coated paper. The difference in basis weight between plain paper and coated paper is relatively large compared to the case of out-licensing. An example in which the difference in basis weight is relatively large is the difference between the nominal basis weight of the determination standard 611 at a certain transmittance and the nominal basis weight of the determination standard 612 at the same transmittance. The basis weight of coated paper corresponding to the same transmittance is larger than the basis weight of plain paper. This is because the transmittance of coated paper tends to be higher than that of plain paper as the wavelength becomes longer.

Then, according to the above assumption, when the basis weight is derived using the determination criteria 611 and the determination criterion 711 of plain paper, when the paper S is plain paper, the basis weight derived by each determination criterion is almost the same. Become a value. On the other hand, when the paper S is coated paper, the basis weight derived by the judgment standard 611 of plain paper is based on the actual basis weight of the paper S (the basis weight derived using the judgment standard 612 of coated paper). Also becomes smaller. The basis weight derived by the judgment standard 711 of plain paper is substantially the same as the actual basis weight (the basis weight derived by using the determination standard 712 of coated paper). Therefore, when the paper S is coated paper, the value obtained by subtracting the basis weight derived by the judgment standard 711 from the basis weight derived by the judgment standard 611 is derived by the judgment standard 611 when the paper is plain paper. It is smaller than the value obtained by subtracting the second basis weight derived from the criterion 711 from the calculated basis weight.

The control unit 11 derives the first basis weight and the second basis weight based on the first transmission rate and the second transmission rate and the determination criteria 611 and 711 of plain paper, and the first basis weight to the second basis weight. When the value obtained by subtracting is equal to or greater than the value of the basis weight threshold 126, it is determined that the type of paper S is plain paper. Further, when the value obtained by subtracting the second basis weight from the first basis weight is less than the value of the basis weight threshold value 126, the control unit 11 determines that the type of paper S is coated paper. That is, it was confirmed that the value of 1st basis weight − 2nd basis weight can be treated as one index related to paper type discrimination and functions advantageously as a discrimination factor. Therefore, as described above, the paper type discrimination model I decided to use it as an input factor for.

(Registration profile candidate judgment processing)
FIG. 60 is a diagram showing an example of paper profile information.

As shown in FIG. 60, as the paper profile information, a profile name indicating the name of the registered profile, a control parameter including setting of various adjustment values of the image forming apparatus 10 such as a paper size and front and back adjustment values, and a paper physical property value and the like. Are stored in the storage unit 12 of the image forming apparatus 10 or the storage unit 83 of the server 80 in association with each other. Each item included in the paper physical characteristic value corresponds to each item of the measured value measured by the media sensor 15.

In the process of determining the candidate registration profile from the measured value and the paper profile, the paper property value of each registered profile registered in the paper profile is compared with the measured value acquired by the measurement of the paper S by the media sensor 15. Is executed by. That is, the registered profile having the paper physical characteristic value closest to the measured value is determined as a candidate. Hereinafter, an example of a specific determination method will be described.

The measured value used for the determination and the paper property value of each registered profile are normalized in advance. The distance between the value of each item of the measured value and the value of each item of the paper physical characteristic value of each registration profile is calculated. Here, a weighting coefficient may be set in advance for each item, and the distance may be calculated by multiplying each item by the weighting coefficient. Then, the registration profile having the smallest calculated distance value is determined as a candidate. In addition, in the same type (brand) of paper, there may be some variations in basis weight such as basis weight 90, 100, 160, 200, 250, 300. Even if it is not possible to discriminate variations in the basis weight of the same type of paper by discrimination using the paper type discrimination model, by including the basis weight value in the calculation of the registration profile judgment as described above, the paper type can be determined. An appropriate registration profile can be selected according to the basis weight.

The configurations of the image forming apparatus 10 or the server 80 and the like described above are not limited to the above configurations but are various within the scope of the claims, as the main configurations have been described in explaining the features of the above-described embodiments. It can be modified. Further, it does not exclude the configuration provided in a general image forming apparatus or server. For example, the example in which the surface sensor 60 is arranged on the transport path 143 of the image forming apparatus 10 is shown, but the present invention is not limited to this, and the apparatus may be independent of the image forming apparatus 10. In this case, the user can measure the paper characteristics by arranging the paper in the irradiation area of the surface sensor 60. Further, instead of the paper thickness sensor 40, a density sensor capable of measuring the density of the paper may be provided. In this case, as the measured value, the density of the paper is acquired instead of the value related to the paper thickness of the paper.

Further, in FIG. 1 and the like, the image forming apparatus 10 shows a configuration in which the image forming apparatus 10 is connected to the optional paper feeding apparatus 20 and the post-processing apparatus 30, but the image forming apparatus 10 may be a single image forming apparatus 10 without these options. Further, in each of the above embodiments, each process described as being executed by the image forming apparatus 10 may be executed by a controller, a PC, or the like connected to the image forming apparatus 10.

Further, in the present embodiment, as a result of determining the paper type, as shown in FIG. 22, an example in which the priority (“recommendation”) is displayed in descending order of priority (score) is shown. The display may be omitted. Also, if there is only one candidate (or if there is a dissociation of the difference from the second and subsequent values by a predetermined value or more), it is automatically applied to the selected paper feed tray in order to improve operability. Then, the operation screen on which the operation of the test printing (step S20) can be executed immediately (with one touch) may be displayed.

1 Image formation system 10 Image formation device 11 Control unit 110 Overall control unit 14 Transport unit 141, 142 Paper feed tray 143, 144 Transport path 1431 Upper guide a1 Opening 1432 Lower guide 15 Media sensor 40 Paper thickness sensor 50 Basis weight sensor 60 Surface Sex sensor 61 Housing a2, a3 Opening 61a Inclined surface b1, b2, b3 Board 62 Light emitting part 63 Collimating lens 64, 641, 642 Light receiving part 70 Paper pressing part 18 Operation panel 20 Paper feed device 30 Post-processing device 80 Server 81 Control Unit 82 Storage unit 83 Communication unit

Claims (14)

A positively reflected light amount value relating to the amount of positively reflected light that is positively reflected on the surface of the recording medium by irradiating the recording medium from a light source via an optical system at a predetermined incident angle, and at least one reflection angle on the surface of the recording medium. Acquiring unit for acquiring a diffusely reflected light amount value relating to the amount of diffuse reflected light, a value relating to the basis weight of the recording medium, and a value relating to the thickness or density of the recording medium.
A discriminant unit that discriminates the type of the recording medium by inputting each value acquired by the acquisition unit into a machine-learned trained model for discriminating the paper type.
Discriminating device having. The discriminating device according to claim 1, wherein the trained model is composed of a random forest. The discriminating device according to claim 1, wherein the trained model is composed of a neural network. The discriminating device according to any one of claims 1 to 3 and
The positive reflected light amount value, the diffused reflected light amount value, the value related to the thickness and basis weight of the recording medium, or the value related to the density of the recording medium are used as input factors of the teacher data, and the type of the recording medium is the teacher. A learning unit that generates the trained model by performing machine learning as a data output factor,
Discrimination system with. The discrimination system according to claim 4, further comprising an image forming apparatus for forming an image on the recording medium. The image forming apparatus
Light source and
An optical system that irradiates the surface of a recording medium in the irradiation region with light from the light source at a predetermined angle of incidence.
A first light receiving unit that detects the amount of specularly reflected light that is specularly reflected on the surface of the recording medium in the irradiation region, and
With at least one second light receiving portion that detects the amount of diffusely reflected light diffusely reflected at at least one reflection angle on the surface of the recording medium in the irradiation region.
A detection unit that detects a value related to the basis weight of the recording medium and a value related to the thickness or density of the recording medium.
The determination system according to claim 5. The discrimination system according to claim 5 or 6, wherein the learning unit executes machine learning at a timing when the image forming process is not executed in the image forming apparatus. The discrimination system according to any one of claims 5 to 7, wherein the control unit of the image forming apparatus does not receive an instruction for executing the image forming process while the machine learning is being executed in the learning unit. The discrimination system according to any one of claims 5 to 8, wherein the learning unit executes machine learning at a preset timing. An output unit that outputs the discrimination result by the discrimination unit and
A reception unit that receives instructions from the user to change the determination result, and
Further having a storage unit for storing the teacher data for executing the machine learning,
The learning unit further machine-learns the trained model by using the changed information including the changed discriminant result and the information input to the trained model to obtain the discriminant result as the teacher data. The discrimination system according to any one of claims 5 to 9. The storage unit and the learning unit are provided in a server connected to the image forming apparatus via a network.
The acquisition unit, the determination unit, the output unit, and the reception unit are provided in the image forming apparatus.
The image forming apparatus transmits the change information received at the reception unit to the server, and the image forming apparatus transmits the change information to the server.
The server stores the change information transmitted from the image forming apparatus as the teacher data in the storage unit, and causes the learning unit to further machine learn the trained model using the stored teacher data. , The machine-learned trained model is transmitted to the image forming apparatus,
The discrimination system according to claim 10, wherein the discrimination unit of the image forming apparatus discriminates the type of the recording medium by using the learned model transmitted from the server. The storage unit, the learning unit, and the discriminating unit are provided in a server connected to the image forming apparatus via a network.
The acquisition unit, the output unit, and the reception unit are provided in the image forming apparatus.
The image forming apparatus transmits each value acquired by the acquisition unit to the server.
The discrimination system according to claim 10, wherein the discrimination unit of the server discriminates the type of the recording medium by using the respective values transmitted from the image forming apparatus and the trained model. The change information transmitted from the image forming apparatus is stored in the storage unit as the teacher data, and the learned model is stored in the learning unit using the stored teacher data based on preset execution conditions. The discrimination system according to claim 11 or 12, wherein the machine learning is further performed. A positively reflected light amount value relating to the amount of positively reflected light that is positively reflected on the surface of the recording medium by irradiating the recording medium from a light source via an optical system at a predetermined incident angle, and at least one reflection angle on the surface of the recording medium. In step (a), a step (a) of acquiring a diffusely reflected light amount value relating to the amount of diffusely reflected light, a value relating to the basis weight of the recording medium, and a value relating to the thickness or density of the recording medium.
In the step (b), each value acquired in the step (a) is input to a machine-learned trained model for determining the paper type to determine the type of the recording medium.
Discrimination method having.

Images