CN114166863A - High-precision sheet detection system based on machine vision - Google Patents

High-precision sheet detection system based on machine vision Download PDF

Info

Publication number
CN114166863A
CN114166863A CN202111428771.7A CN202111428771A CN114166863A CN 114166863 A CN114166863 A CN 114166863A CN 202111428771 A CN202111428771 A CN 202111428771A CN 114166863 A CN114166863 A CN 114166863A
Authority
CN
China
Prior art keywords
sheet
roller
conveying
detection
image sensor
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202111428771.7A
Other languages
Chinese (zh)
Inventor
王平
张小攀
张涛
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Suzhou Watch Technology Co ltd
Original Assignee
Suzhou Watch Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Suzhou Watch Technology Co ltd filed Critical Suzhou Watch Technology Co ltd
Priority to CN202111428771.7A priority Critical patent/CN114166863A/en
Publication of CN114166863A publication Critical patent/CN114166863A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84Systems specially adapted for particular applications
    • G01N21/88Investigating the presence of flaws or contamination
    • G01N21/95Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
    • G01N21/956Inspecting patterns on the surface of objects

Abstract

The invention discloses a high-precision sheet detection system based on machine vision, which comprises a roller set, a conveying table and a detection assembly, wherein the detection assembly comprises an image sensor and a plurality of light sources arranged in different directions, the detection assembly is linked with the roller set, the plurality of light sources are sequentially started while the roller set pressurizes a sheet penetrating into a roller gap, the image sensor acquires a plurality of images of the surface of the sheet on a conveying surface at different illumination angles, and surface form parameters of the sheet are acquired according to the plurality of images; the pressing time of the roller group on the sheet is more than or equal to the detection time of the detection assembly. According to the high-precision sheet detection system, under the condition that the sheet is in a temporary static state relative to the roller set, the conveying surface and the light source, a plurality of images on the surface of the sheet are obtained, the definition of the plurality of images is greatly improved, the detection precision of the surface form of the sheet is improved, the detection efficiency is high, and the online continuous detection of the surface form parameters of the sheet is realized.

Description

High-precision sheet detection system based on machine vision
Technical Field
The invention relates to a sheet detection system, in particular to a high-precision sheet detection system based on machine vision.
Background
Currently, for the purpose of giving the thin sheet with functions of bulk, softness, scalability, etc., and giving the thin sheet with aesthetic appearance, etc., it is common practice to subject the sheet to surface treatment to change the surface structure of the sheet, such as subjecting the sheet to treatment such as creping or embossing, etc., to form various surface morphologies such as wrinkles or embossments on the surface of the sheet. The sheet materials with different specifications/quality grades have different requirements on the surface forms, and each link of the production process has different influences on the surface forms of the sheet materials. In actual production, systematic evaluation of the quality and the production process of the sheet material needs to quantitatively detect various surface morphology parameters of the sheet material.
The commonly used quantitative detection equipment for the surface morphology parameters of the sheet materials comprises: mechanical probe type surface profilers based on point-by-point scanning modes, laser scanning surface roughness meters, measuring devices based on two-dimensional image analysis and the like.
The equipment based on the point-by-point scanning mode has the defects of small measurement area, long measurement period, low spatial resolution and the like, the equipment based on two-dimensional image analysis cannot comprehensively evaluate different quantitative parameters of the surface form of the sheet, the equipment based on three-dimensional image reconstruction can obtain high-quality images and accurately detect all the parameters, but is only suitable for detecting the static sheet under the line, and the sheet in the production process is in a moving state, so that the definition of the obtained images is low, and accurate on-line detection cannot be realized.
Disclosure of Invention
In view of the defects in the prior art, the invention provides a high-precision sheet detection system based on machine vision, which can realize online detection of sheet surface form parameters and has high detection precision.
The technical scheme adopted by the invention is as follows: provided is a high-precision sheet detection system based on machine vision, comprising:
a roller set: the roller group pressurizes the sheet passing through the roller gap to cut the sheet or perform surface treatment on the sheet;
a conveying table: the conveying surface is arranged at the downstream of the discharge port, and the sheet is conveyed to the conveying surface through the discharge port;
a detection component: the light source is arranged above the conveying surface and comprises an image sensor and a plurality of light sources arranged in different directions;
the detection assembly is linked with the roller set, the plurality of light sources are sequentially started while the roller set pressurizes the sheet penetrating into the roller gap, the image sensor collects a plurality of images of the surface of the sheet on the conveying surface at different illumination angles, and surface form parameters of the sheet are obtained according to the plurality of images;
the pressing time of the roller group on the sheet is more than or equal to the detection time of the detection assembly.
As an improvement to the above, the sheet comprises at least one ply of creped sheet, and the surface morphology parameters of the sheet include crepe width, crepe frequency and crepe depth of the sheet.
As an improvement of the above, the roller group presses the sheet passed through the nip to perform surface treatment on the sheet includes embossing treatment, edge pressing treatment, calendering treatment, or laminating treatment on the sheet.
In an improvement of the above, the conveying table includes a conveying frame, a first roller, a second roller, a driving roller and a conveying belt wound around the first roller, the second roller and the driving roller, and the sheet is conveyed while being attached to an upper surface of the conveying belt.
As the improvement to above-mentioned scheme, the conveying surface is the downward slope in the horizontal plane, and sets up to 15 ~ 35 with the contained angle between the horizontal plane.
As an improvement to the above solution, the detection speed of the detection assembly is not more than 100mS, the resolution of the image sensor is 2448 × 2048, and the central wavelength of the light source is 595 nm.
As an improvement to the above solution, the detection assembly includes four light sources respectively disposed at a front side, a rear side, a left side, and a right side of the image sensor;
when the roller group pressurizes the sheet penetrating into the roller gap, the four light sources are sequentially started according to the sequence of front, back, left and right, and the image sensor correspondingly acquires four images of the surface of the sheet on the conveying surface under four illumination angles.
As an improvement to the above scheme, the image sensor is perpendicular to the conveying surface, the four light sources are all obliquely arranged relative to the conveying surface, and the inclination angle is set to be 25-65 degrees.
As an improvement to the above scheme, the detection assembly further includes a light shield covering the image sensor and the plurality of light sources, a positive pressure air flow is introduced into the light shield, a first opening and a second opening are respectively formed in the front side and the rear side of the light shield, and the first opening is smaller than the second opening.
As an improvement to the above, a guide roller for guiding the sheet to a downstream process is provided downstream of the conveying table; or, another roller set is arranged at the downstream of the conveying table and used for carrying out secondary pressurization on the sheet.
Has the advantages that: different from the prior art, the high-precision sheet detection system based on machine vision provided by the invention has the advantages that the detection assembly is linked with the roller set, the plurality of light sources are sequentially started while the roller set pressurizes a sheet penetrating into the roller gap, the image sensor acquires a plurality of images of the surface of the sheet positioned on a conveying surface under different illumination angles, namely, the plurality of images of the surface of the sheet are acquired under the condition that the sheet is temporarily static relative to the roller set, the conveying surface and the light sources, so that the definition of the plurality of images is greatly improved, the image sensor acquires surface form parameters of the sheet according to the plurality of images, the detection accuracy of the surface form of the sheet is improved, the detection efficiency is high, and the online continuous detection of the surface form parameters of the sheet is realized.
Drawings
FIG. 1 is a schematic diagram of a high precision machine vision based sheet inspection system according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of the detection assembly of FIG. 1;
FIG. 3 is a schematic diagram of a high precision machine vision based sheet inspection system according to another embodiment of the present invention;
FIG. 4 is a raster assembly moving in synchronization with the roll stack.
Detailed Description
The present invention will be described in further detail with reference to examples. It is to be noted that the following examples are only illustrative of the present invention, and do not limit the scope of the present invention. Similarly, the following examples are only some but not all examples of the present invention, and all other examples obtained by those skilled in the art without any inventive work are within the scope of the present invention.
In the description of the present invention, it is to be understood that the terms "upper", "lower", "front", "rear", "left", "right", "inner", "outer", "vertical", "horizontal", and the like, indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are only for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first," "second," etc. may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless otherwise specified.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; they may be connected directly or indirectly through intervening media, or they may be connected internally or indirectly to each other. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art through specific situations.
The invention provides a high-precision sheet detection system based on machine vision, which is used for carrying out online continuous quantitative detection on the surface morphology of a thin sheet so as to conveniently carry out efficient systematic evaluation on the sheet quality and the production process in actual production.
The sheet refers to a thin sheet with a specific surface morphology, and the sheet includes but is not limited to creped household paper, creped non-woven fabric, embossed/edge pressed household paper, embossed/edge pressed non-woven fabric or film material.
Referring to fig. 1, fig. 1 illustrates a structure of a high-precision sheet detection system based on machine vision according to an embodiment of the present invention, where the high-precision sheet detection system includes a roller group 10, a conveying table 20, and a detection assembly.
Wherein the roller group 10 includes a nip which is a gap defined between an upper press roll and a lower press roll, and a discharge port which is located downstream of the nip, and pressurizes the sheet passing through the nip to slit the sheet or to surface-treat the sheet; the conveying platform 20 is arranged at the downstream of the discharge port and comprises a conveying surface 21, and the sheet is conveyed to the conveying surface 21 through the discharge port and conveyed to the downstream through the conveying surface 21; the detection assembly is mounted above the conveying surface 21 and includes an image sensor 31 and a plurality of light sources 32 disposed in different orientations.
The detection assembly is linked with the roller set 10, the plurality of light sources 32 are sequentially turned on while the roller set 10 pressurizes the sheet passing through the nip, the image sensor 31 collects a plurality of images of the surface of the sheet 100 on the conveying surface 21 at different illumination angles, and the surface form parameters of the sheet 100 are acquired according to the plurality of images.
The pressing time of the roller group 10 to the sheet is equal to or longer than the detection time of the detection assembly.
According to the high-precision sheet detection system based on machine vision, provided by the invention, under the condition that the sheet 100 is temporarily static relative to the roller set 10, the conveying surface 21 and the light source 30, a plurality of images of the surface of the sheet 100 under different illumination angles are obtained, so that the definition of the plurality of images is greatly improved, secondary optimization processing is not required, an image sensor obtains surface form parameters of the sheet 100 according to the plurality of images, the detection precision of the surface form of the sheet is improved, the detection efficiency is high, the surface form parameter information of the sheet can be timely fed back, and the quality and the production process of the sheet in actual production are systematically evaluated.
Further, the detection speed of the detection assembly is not more than 100mS, the resolution of the image sensor 31 is 2448 × 2048, and the central wavelength of the light source 32 is 595 nm.
Further, the sheet material comprises at least one layer of wrinkled sheet material, such as wrinkled household paper, wrinkled non-woven fabric and the like, and the surface morphological parameters of the sheet material comprise the wrinkle width, the wrinkle frequency and the wrinkle depth of the sheet material.
In one embodiment of the invention, the sheet material is wrinkled household paper, in the drying link of the household paper, the paper adhered to the surface of the drying cylinder is peeled off from the surface of the drying cylinder by a scraper, the longitudinal direction of the paper is compressed and folded in the peeling process, so that corrugated wrinkles are generated, the quality of the wrinkles has important influence on the softness, hand feeling, absorptivity and strength of the finished paper, if the quality of the finished paper and the production process are controlled, the quality of the wrinkles needs to be quantitatively detected, and then the influence of the process parameters of each production link on the product quality can be quantitatively and systematically evaluated.
In this embodiment, the sheet is a single-layer or multi-layer creped household paper, the roller group 10 is a cutter roller group, the roller group 10 presses the sheet inserted into the nip to slit the sheet into a predetermined size, and the slit sheet into the predetermined size is conveyed onto the conveying surface 21 through the discharge port and conveyed downstream by the conveying table 20.
Referring to fig. 2, fig. 2 shows a structure of the detecting assembly, and further, the detecting assembly includes four light sources 321, 322, 323, and 324, the four light sources 321, 322, 323, and 324 are respectively disposed on a front side, a rear side, a left side, and a right side of the image sensor 31, the light sources 321 and 322 are disposed oppositely, and the light sources 323 and 324 are disposed oppositely.
The four light sources 321, 322, 323 and 324 are located on the same horizontal plane and are all disposed below the image sensor 31, the four light sources 321, 322, 323 and 324 surround and define an image capturing opening, the image sensor 31 is correspondingly disposed right above the image capturing opening, and an image of a sheet on the conveying surface 21 is captured through the image capturing opening.
The front-back direction in the present invention means a direction from upstream to downstream in the conveyance direction of the crumpled household paper, and the left and right means both sides perpendicular to the conveyance direction of the crumpled household paper.
Specifically, the cutting roller group 10 applies pressure to the wrinkled household paper, and then the front light source 321 is started, the image sensor 31 captures a first image of crumpled household paper 100 on the conveying surface 21 at a first illumination angle, turns off the front side light source 321 and turns on the back side light source 322, the image sensor 31 captures a second image of crumpled household paper 100 on the transport surface 21 at a second illumination angle, turns off the back side light source 322 and turns on the left side light source 323, the image sensor 31 captures a third image of crumpled household paper 100 on the conveying surface 21 at a third illumination angle, and finally, the left light source 323 is turned off and the right light source 324 is turned on, image sensor 31 captures a fourth image of crumpled household paper 100 on conveying surface 21 at a fourth illumination angle, the image sensor 31 acquires the surface morphology parameters of the wrinkled household paper 100 according to the first image, the second image, the third image and the fourth image.
The pressing time of the roller group 10 on the wrinkled household paper is set to be more than or equal to the detection time of the detection component, namely, more than or equal to the total time of acquiring four images and acquiring the surface form parameters of the wrinkled household paper 100 by the image sensor 31.
It can be understood that, in the time period when the roller set 10 pressurizes the crumpled household paper, the crumpled household paper in conveying is in a temporary static state relatively, the detection assembly acquires four images of the crumpled household paper 100 in four different illumination angles when the crumpled household paper is in the temporary static state, the image definition is greatly improved, the image sensor 31 calculates the height corresponding to each part of the paper surface by analyzing the change rule of the reflection and the shadow of the four images based on the three-dimensional image fast reconstruction method to obtain the three-dimensional information of the paper, calculates the three-dimensional appearance of the paper surface by using the photometric stereo reconstruction method, extracts the macro-crumpled image after fast fourier transform, and acquires the surface form parameters of the crumpled household paper 100.
The detection method has short measurement and analysis time, can obtain a high-resolution plane image to measure the width and the frequency of the wrinkles, and can establish the real three-dimensional wrinkle appearance at the same time, thereby accurately measuring the depth of the wrinkles.
In addition, regarding the detection component and the roller set 10 to be linked, please refer to fig. 4 together, fig. 4 shows a grating component moving synchronously with the roller set, which includes a grating frame 11 and a photoelectric sensor 12, the grating frame 11 and one roller of the roller set 10 are coaxially linked to be set, so that the grating frame 11 and one roller of the roller set 10 move synchronously, the grating frame 11 includes a cylindrical wall, on which a number of light holes 110 corresponding to the number of the pressing components in the roller set are opened, it can be understood that when the roller set 10 is a cutter roller set, the pressing components are cutters, when the roller set 10 is an embossing roller, the pressing components are embossing protrusions, the width of the light holes 110 is equal to the width of the pressing components, the photoelectric sensor 12 is set corresponding to the position of the light holes 110, and includes an emitting end 121 and a receiving end 122, when the pressing components move to apply pressure to the corrugated household paper 100, the light beam emitted by the emitting end 121 can be received by the receiving end 122, so as to start the detection assembly, and the detection time of the detection assembly on the sheet material should be less than or equal to the time when the light beam can be received and blocked, so that the detection assembly can be linked with the roller group 10.
In one application scenario, the pressing time of the roller group 10 for pressing the wrinkled household paper is set to be equal to the time required by the image sensor 31 for acquiring the four images of the wrinkled household paper 100 on the conveying surface 21, and the total time for starting each light source of the four light sources 321, 322, 323 and 324 and acquiring one image by the image sensor 31 is set to be one fourth of the pressing time.
It is understood that the four images acquired by the image sensor 31 are images of the surface of the creped household paper 100 in the same area.
Further, the image sensor 31 is arranged perpendicular to the conveying surface 21, and acquires a sheet surface image of a portion of the creped household paper 100 directly below the sheet surface image; the four light sources are all obliquely arranged relative to the conveying surface 21, and compared with the arrangement that the light sources are parallel to the conveying surface 21, the illumination intensity of the wrinkled household paper 100 from the periphery is improved, and the definition of the obtained image is further improved.
Furthermore, the inclination angles of the four light sources relative to the conveying surface 21 are set to be 25-65 °, such as 25 °, 35 °, 40 °, 55 °, 60 °, 65 °, and the like, and preferably set to be 30-60 °, such as 30 °, 35 °, 40 °, 45 °, 50 °, 55 °, 60 °, and the like.
In one embodiment of this embodiment, a guide roller 40 is provided downstream of the transport table 20 for guiding the crumpled tissue to a downstream station.
Further, the conveying table 20 includes a conveying frame 22, a first roller 23, a second roller 24, a driving roller 25 and a conveying belt 26 wound around the first roller 23, the second roller 24 and the driving roller 25, the conveying belt 26 is driven by the driving roller 25 to rotate around the first roller 23 and the second roller 24, the driving roller 25 is a driving roller, and the first roller 23 and the second roller 24 are driven rollers.
The creped household paper is conveyed downstream by being attached to the upper surface of the conveyor belt 26, and as can be appreciated, the conveyor surface 21 is the upper surface of the conveyor belt 26.
Further, the conveying surface 21 is inclined to the horizontal plane, and an included angle between the conveying surface and the horizontal plane is set to be 15-35 degrees, and preferably set to be 30 degrees. Specifically, the conveying surface 21 is inclined downward with respect to a horizontal plane, and one end of the conveying surface 21 near the discharge port is higher than one end near the guide roller 40.
The crumpled household paper 100 on the inclined conveying surface 21 inclines downwards relative to a horizontal plane along the conveying direction of the crumpled household paper, so that the crumpling phenomenon generated in the conveying process of the crumpled household paper can be spread, the crumpled household paper 100 on the conveying surface 21 is kept flat, the image sensor 31 can conveniently acquire high-quality images, and the detection efficiency of the detection assembly is improved.
It will be understood that the detection assembly is arranged in correspondence with the conveying surface 21, which is arranged inclined downwards with respect to the horizontal.
Further, the detection assembly further includes a light shield 33 covering the image sensor 31 and the four light sources 321, 322, 323, and 324, wherein the light shield 33 is disposed corresponding to the conveying surface 21 and is inclined downward with respect to a horizontal plane.
The arrangement of the light shield 33 can effectively shield the influence of ambient light on the image sensor 31 to acquire the image on the surface of the wrinkled household paper 100, and further improve the definition of the image acquired by the image sensor 31; in addition, the light shield 33 can prevent dust generated in the conveying process of the wrinkled household paper from accumulating on the image sensor 31 and the four light sources 321, 322, 323 and 324 and influencing the detection efficiency of the detection assembly.
It is understood that the image sensor 31 obtains the image of the surface of the wrinkled household paper 100 in the light shield 33, and further, a positive pressure air flow is introduced into the light shield 33, preferably from the top of the light shield 33, to ensure that the surface of the wrinkled household paper 100 in the light shield 33 is kept flat.
In a preferred embodiment, a first opening and a second opening (not shown in the drawings) are respectively formed on the front side and the rear side of the light shield 33, and the opening area of the first opening is smaller than that of the second opening, so that the positive pressure air flow in the light shield 33 has a tendency of flowing from the upstream to the downstream of the conveying of the crumpled household paper, the possible crumples on the crumpled household paper 100 are further unfolded, the paper surface of the crumpled household paper 100 in the light shield 33 is ensured to be in a flat state, the definition of the image acquired by the image sensor 31 is improved, and the accuracy of the detection result is ensured.
In another embodiment of the present invention, the sheet material passing through the nip is single-layered or multi-layered creped tissue paper, and unlike the previous embodiment, the roller set 10 is an embossing roller set, and the roller set 10 presses the creped tissue paper passing through the nip to form an embossed pattern on the surface of the creped tissue paper, wherein the embossing may be a contact or various patterns, and the embossing is used to increase the surface area of the tissue paper, thereby increasing the bulk, achieving good appearance, and further improving the water absorption capacity and wiping performance.
The creped household paper subjected to embossing is conveyed onto the conveying surface 21 through the discharge port and is conveyed downstream by the conveying table 20.
It is understood that, in the present embodiment, the sheet material on the conveying surface 21 is embossed household paper, and the surface morphology parameters of the sheet material include the embossing width and the embossing depth of the sheet material.
At the same time when the embossing roller set starts to apply pressure on the wrinkled household paper, the four light sources 321, 322, 323 and 324 are sequentially started, the image sensor 31 collects four images of the embossed household paper 100 on the conveying surface 21 under four different illumination angles, and surface form parameters of the embossed household paper 100 are acquired according to the four images. The pressing time of the roller group 10 to the wrinkled living paper is set to be greater than or equal to the detection time of the detection component.
It can be understood that, in the time period when the roller set 10 pressurizes the wrinkled household paper, the embossed household paper in conveying is relatively in a temporary static state, the detection assembly acquires four images under four different illumination angles when the embossed household paper 100 is in the temporary static state, the image sensor 31 calculates the height corresponding to each part of the paper surface by analyzing the change rule of the reflection and the shadow of the four images based on the method for quickly reconstructing the three-dimensional images, so as to acquire the three-dimensional information of the paper, calculates the three-dimensional shape of the paper surface by using the photometric stereo reconstruction method, and extracts the macroscopic surface image after the fast fourier transform, so as to acquire the surface shape parameters of the embossed household paper 100.
The detection method has short measurement and analysis time, can obtain a high-resolution plane image to measure the embossing width, and can establish a real three-dimensional embossing shape at the same time, thereby accurately measuring the embossing depth.
Referring to fig. 3, fig. 3 shows the structure of the high-precision sheet detection system in the present embodiment, different from the previous embodiment, in the present embodiment, another roller set 50 is disposed downstream of the conveying table 20, the roller set 50 is a cutter roller set, and the roller set 50 is used for performing secondary pressurization on the embossed household paper conveyed downstream by the conveying table 20 to cut the embossed household paper into a predetermined size.
In this embodiment, the conveying surface 21 is inclined downward with respect to the horizontal plane, and the discharge port of the embossing roller set 10 is set higher than the feed port of the cutter roller set 50. The embossed household paper 100 on the inclined conveying surface 21 is inclined downwards relative to a horizontal plane along the conveying direction of the embossed household paper, so that the wrinkle phenomenon generated in the conveying process of the embossed household paper can be spread, the embossed household paper 100 on the conveying surface 21 is kept flat, the image sensor 31 can conveniently acquire high-quality images, and the detection efficiency of the detection assembly is improved.
The technical features of this embodiment that are the same as those of the previous embodiment are not described herein again.
In other embodiments of the invention, the roll stack 10/roll stack 50 may also be provided as a calender roll stack, a binder roll stack or a laminating roll stack for pressing the sheet passing through the nip to calender, binder or laminate the sheet.
According to the high-precision sheet detection system based on machine vision, the detection assembly is linked with the roller set, and the image sensor acquires the plurality of images on the surface of the sheet when the sheet is in a temporary static state relative to the roller set, the conveying surface and the light source, so that the definition of the plurality of images is greatly improved, and the detection precision of the surface morphology of the sheet is improved. The high-precision sheet detection system realizes the online continuous detection of the surface form parameters of the sheet, has high detection efficiency, and can feed back the surface form parameter information of the sheet in time so as to systematically evaluate the quality and the production process of the sheet in actual production.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes performed by the present specification and drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.

Claims (10)

1. A high-precision sheet inspection system based on machine vision, comprising:
a roller set: the roller group pressurizes the sheet passing through the roller gap to cut the sheet or perform surface treatment on the sheet;
a conveying table: the conveying surface is arranged at the downstream of the discharge port, and the sheet is conveyed to the conveying surface through the discharge port;
a detection component: the light source is arranged above the conveying surface and comprises an image sensor and a plurality of light sources arranged in different directions;
the detection assembly is linked with the roller set, the plurality of light sources are sequentially started while the roller set pressurizes the sheet penetrating into the roller gap, the image sensor collects a plurality of images of the surface of the sheet on the conveying surface at different illumination angles, and surface form parameters of the sheet are obtained according to the plurality of images;
the pressing time of the roller group on the sheet is more than or equal to the detection time of the detection assembly.
2. The high accuracy sheet inspection system of claim 1, wherein said sheet comprises at least one layer of creped sheet, and wherein said sheet surface topography parameters comprise sheet crepe width, crepe frequency, and crepe depth.
3. A high accuracy sheet inspection system as set forth in claim 1 wherein said roller set pressurizing the sheet passing into said nip to surface treat the sheet comprises embossing, edge pressing, calendering, or laminating the sheet.
4. The high-precision sheet detection system according to claim 1, wherein the conveying table comprises a conveying frame, a first roller, a second roller, a driving roller and a conveying belt, wherein the first roller, the second roller and the driving roller are arranged on the conveying frame, and the sheet is conveyed by being attached to the upper surface of the conveying belt.
5. The high-precision sheet detection system according to claim 1, wherein the conveying surface is inclined downward to a horizontal plane, and an included angle between the conveying surface and the horizontal plane is set to be 15-35 degrees.
6. The high precision sheet inspection system of claim 1, wherein the inspection assembly has an inspection speed of no more than 100mS, the image sensor has a resolution of 2448 x 2048, and the light source has a center wavelength of 595 nm.
7. The high precision sheet inspection system of claim 1, wherein the inspection assembly comprises four light sources disposed on a front side, a back side, a left side, and a right side of the image sensor, respectively;
when the roller group pressurizes the sheet penetrating into the roller gap, the four light sources are sequentially started according to the sequence of front, back, left and right, and the image sensor correspondingly acquires four images of the surface of the sheet on the conveying surface under four illumination angles.
8. The high-precision sheet detection system according to claim 7, wherein the image sensor is disposed perpendicular to the conveying surface, and the four light sources are each disposed obliquely with respect to the conveying surface at an angle of 25 to 65 °.
9. The system of claim 1, wherein the inspection assembly further comprises a light shield covering the image sensor and the plurality of light sources, wherein a positive pressure air flow is introduced into the light shield, a first opening and a second opening are respectively formed in the front side and the rear side of the light shield, and the first opening is smaller than the second opening.
10. A high precision sheet material inspection system according to claim 1, wherein a guide roller is provided downstream of the transport table for guiding the sheet material to a downstream process; or, another roller set is arranged at the downstream of the conveying table and used for carrying out secondary pressurization on the sheet.
CN202111428771.7A 2021-11-29 2021-11-29 High-precision sheet detection system based on machine vision Pending CN114166863A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111428771.7A CN114166863A (en) 2021-11-29 2021-11-29 High-precision sheet detection system based on machine vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111428771.7A CN114166863A (en) 2021-11-29 2021-11-29 High-precision sheet detection system based on machine vision

Publications (1)

Publication Number Publication Date
CN114166863A true CN114166863A (en) 2022-03-11

Family

ID=80481266

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111428771.7A Pending CN114166863A (en) 2021-11-29 2021-11-29 High-precision sheet detection system based on machine vision

Country Status (1)

Country Link
CN (1) CN114166863A (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4885601A (en) * 1987-10-27 1989-12-05 Sony Corporation Apparatus for developing imaging sheets employing photosensitive microcapsules
CN202141437U (en) * 2011-07-08 2012-02-08 陕西科技大学 Scanning head box with paper web anti-shaking device
CN205853624U (en) * 2016-06-03 2017-01-04 江苏昌昇集团股份有限公司 The servo-actuated pressing roll mechanism that a kind of cam controls
CN206609396U (en) * 2017-04-10 2017-11-03 深圳汉华工业数码设备有限公司 Calliper detects structure
JP2018009927A (en) * 2016-07-15 2018-01-18 キヤノン株式会社 Image processing device, image processing method and program
JP2018008826A (en) * 2017-10-18 2018-01-18 キヤノンファインテックニスカ株式会社 Post-processing device and image formation system using the same
JP2019074354A (en) * 2017-10-13 2019-05-16 王子ホールディングス株式会社 Sanitary paper manufacturing method and defect inspection device
JP2021038988A (en) * 2019-09-03 2021-03-11 王子ホールディングス株式会社 Defect inspection device and production method of sheet-like article
CN212722666U (en) * 2020-07-31 2021-03-16 广西真龙彩印包装有限公司 Online detection device for printed matter of printing machine
US20220011093A1 (en) * 2019-01-11 2022-01-13 Hewlett-Packard Development Company, L.P. Optical media sensor with blower

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4885601A (en) * 1987-10-27 1989-12-05 Sony Corporation Apparatus for developing imaging sheets employing photosensitive microcapsules
CN202141437U (en) * 2011-07-08 2012-02-08 陕西科技大学 Scanning head box with paper web anti-shaking device
CN205853624U (en) * 2016-06-03 2017-01-04 江苏昌昇集团股份有限公司 The servo-actuated pressing roll mechanism that a kind of cam controls
JP2018009927A (en) * 2016-07-15 2018-01-18 キヤノン株式会社 Image processing device, image processing method and program
CN206609396U (en) * 2017-04-10 2017-11-03 深圳汉华工业数码设备有限公司 Calliper detects structure
JP2019074354A (en) * 2017-10-13 2019-05-16 王子ホールディングス株式会社 Sanitary paper manufacturing method and defect inspection device
JP2018008826A (en) * 2017-10-18 2018-01-18 キヤノンファインテックニスカ株式会社 Post-processing device and image formation system using the same
US20220011093A1 (en) * 2019-01-11 2022-01-13 Hewlett-Packard Development Company, L.P. Optical media sensor with blower
JP2021038988A (en) * 2019-09-03 2021-03-11 王子ホールディングス株式会社 Defect inspection device and production method of sheet-like article
CN212722666U (en) * 2020-07-31 2021-03-16 广西真龙彩印包装有限公司 Online detection device for printed matter of printing machine

Similar Documents

Publication Publication Date Title
KR102442684B1 (en) Soft, absorbent sheets having high absorbency and high caliper, and methods of making soft, absorbent sheets
US10643323B2 (en) Measurement of tissue paper
CN103874919B (en) The method and apparatus of web features during for creping is monitored and controlled
KR100245350B1 (en) Cellulosic fibrous structures having at least three regions distinguished by intensive properties
EP2310195B1 (en) Embossed fibrous structures and methods for making same
AU685340B2 (en) Method for increasing the internal bulk of wet-pressed tissue
US20120244241A1 (en) Extended nip embossing apparatus
US20200354896A1 (en) Creped fibrous structures
US20080013818A1 (en) Method and apparatus for measuring the crepe of a moving sheet
JP2012518777A (en) Optical inspection system using shortwave infrared sensing
US9816977B2 (en) Method and arrangement for detecting free fibre ends in paper
CN114166863A (en) High-precision sheet detection system based on machine vision
JP2023089140A (en) Device for inspecting sheet-like material for defects and method for manufacturing the same
JP5357496B2 (en) Method for inspecting deposit hardening
JP7030914B1 (en) Manufacturing method of sheet-shaped member
JP2021045255A (en) Absorbent article manufacturing method
JP2018086112A (en) Method and apparatus for inspection of opening sheet, method for manufacturing opening sheet and method for manufacturing absorbent article

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination