JP2020034974A - Image generation device, image generation and display system, and image generation method - Google Patents

Abstract

To provide an image generation device, an image generation and display system, and an image generation method that can easily specify and display a place or a range where an abnormality occurs in a mechanical device including a plurality of components.SOLUTION: A plurality of abnormality sensors S01 to S05 are arranged on a mechanical device M. At the time of receiving an abnormality signal, on the basis of a matrix data that indicates the relationship between abnormal component(s) of one or more components causing an abnormal operation state that causes an abnormality signal and the abnormality signal generated by each of the plurality of abnormality sensors, an image generating device 2 connected to each of the plurality of abnormal sensors specifies a three-dimensional CAD data of the abnormal component related to the abnormality signal and generates a three-dimensional model image of the abnormal component based on the three-dimensional CAD data.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an image generation device, an image generation display system, and an image generation method for generating a three-dimensional model image, and more particularly, to an image generation device, an image generation system, and an image generation method capable of generating a three-dimensional model image of an abnormal part. About.

  Conventionally, when an abnormality is detected in a mechanical device, an image in which a portion corresponding to the component in which the abnormality has occurred is highlighted on a component layout of the mechanical device to generate an alarm screen indicating that the abnormality has occurred. There is an image generation device that can display the image (Patent Document 1).

  In the above-described conventional image generating apparatus, the component layout of the mechanical device is based on CAD data including information relating to the mounting position and orientation of the component and wiring between components created when designing the mechanical device. Since the alarm screen is created, the alarm screen can be easily displayed.

  Then, the conventional image generating apparatus highlights such an abnormal part on the component layout, so that the operator can easily grasp the position where the abnormality has occurred without referring to the drawing.

JP 2017-68324 A

  The conventional image generation device displays an alarm screen in which a location where an abnormality has occurred is highlighted on the component layout of the mechanical device.

  By the way, when the structure of a mechanical device is complicated and a large number of three-dimensional parts and members are combined to configure the mechanical device, information on the layout and wiring of the parts alone is not sufficient for the vertical position of the location where the abnormality has occurred. It is difficult to specify or display a three-dimensional position or range consisting of horizontal and depth.

  In addition, when such parts and members are combined in a multilayered manner, it is particularly difficult to identify and display a location where an abnormality has occurred from outside the combined parts. Alternatively, for example, when the part has a cylindrical shape and the abnormal part is located on the inner peripheral surface side, it is difficult to identify or display the abnormal part even if the parts are not combined with each other. It is.

  Further, since the conventional alarm screen is displayed by the display processing means included in the image generating device, when the image generating device is attached to the mechanical device, the operator can determine the location where the abnormality has occurred. Must be beside the machinery to know.

  The present invention has been made in view of such a problem, and it is possible to easily specify and display a place or a range where an abnormality occurs, and to view the alarm screen at a remote place farther than the mechanical device. It is an object of the present invention to provide an image generation apparatus, an image generation and display system, and an image generation method that can perform the above-described operations.

(1) The present invention includes a communication unit connected to a plurality of abnormality sensors provided in a mechanical device including a plurality of components, a processing unit connected to the communication unit, and a storage unit connected to the processing device. The storage means stores a first relationship, which is a relationship between an abnormal signal generated by each of the abnormal sensors and one or a plurality of abnormal components which are the components that cause an abnormal operating state that causes the abnormal signal. A network database that stores the matrix data and a three-dimensional CAD database that stores the three-dimensional CAD data of each of the parts are stored, and the processing unit stores the matrix data when the communication unit receives the abnormal signal. Based on the abnormal component CAD data, the abnormal component CAD data, which is three-dimensional CAD data of the abnormal component related to the abnormal signal, is specified. There is provided an image generating apparatus and generating a component three-dimensional model image.

  That is, the image generating apparatus of the present invention stores the three-dimensional CAD data of each of the parts, and specifies the three-dimensional CAD data of the abnormal part based on the matrix data. It is possible to easily specify a three-dimensional position or range including the width and the depth.

  In addition, the image generating apparatus of the present invention generates a three-dimensional model image based on the three-dimensional CAD data as an image to be displayed when an abnormal signal is received. The original model image can be displayed.

(2) In addition, the network database stores a relationship between the abnormal signal and an abnormal cause area which is one or a plurality of three-dimensional areas that cause an abnormal operation state of the abnormal component that causes the abnormal signal. A second relationship is stored as matrix data, and the processing unit is configured to display the abnormal component in which the abnormal cause area and the normal area that is a three-dimensional area that is not the abnormal cause area among the abnormal parts are displayed separately. A three-dimensional model image may be generated.

  That is, in order to store the relationship between the abnormal signal and the abnormal cause area of the three-dimensional area which is a three-dimensional area including the vertical, horizontal, and depth of the abnormal part, Position and range can be easily specified, and a three-dimensional model image can be displayed.

(3) In addition, based on the three-dimensional CAD data, display or non-display of one or a plurality of three-dimensional regions whose ranges are arbitrarily specified among the parts is selected to generate the abnormal part three-dimensional model image. May be.

  That is, even when the components are combined in a multilayered manner, one or more components other than the abnormal component or a three-dimensional region that is a three-dimensional region including vertical, horizontal, and depth is arbitrarily hidden. Thereby, it is possible to easily specify and display the location or range where the abnormality occurs.

  Further, by hiding a part of the three-dimensional area of the abnormal component, it is possible to easily specify and display the location or range where the abnormality has occurred. For example, even when the abnormal part has a cylindrical shape and the abnormality cause area is located on the inner peripheral surface side, a part of the abnormal part is not displayed so as to form a slit in the central axis direction of the cylindrical shape. By doing so, it is possible to easily identify and display the abnormal cause area that is hidden and cannot be seen.

(4) The present invention provides a plurality of abnormality sensors provided in a mechanical device including a plurality of parts, communication means connected to the plurality of abnormality sensors, processing means connected to the communication means, and storage connected to the processing device. An image generation and display system comprising: an image generation server device having a unit; and an external terminal device connected to the communication unit via a communication line, and having a terminal display processing unit. A network database that stores, by matrix data, a first relationship that is a relationship between an abnormal signal generated by the abnormal sensor and one or more abnormal components that are the components that cause the abnormal operating state that causes the abnormal signal; And a three-dimensional CAD database storing three-dimensional CAD data of each of the parts, wherein the processing unit receives the abnormal signal by the communication unit. Identifying abnormal component CAD data, which is three-dimensional CAD data of the abnormal component related to the abnormal signal, based on the matrix data, generating an abnormal component three-dimensional model image based on the abnormal component CAD data, The display processing means provides an image generation and display system, wherein the external terminal device displays the abnormal component three-dimensional model image received from the image generation server device.

  That is, the image generation and display system of the present invention stores the three-dimensional CAD data of each of the parts and specifies the three-dimensional CAD data of the abnormal part based on the matrix data. , And a three-dimensional position or range consisting of width and depth can be easily specified. In addition, when the abnormal signal is received, a three-dimensional model image based on the three-dimensional CAD data is generated, so that a three-dimensional model image including the vertical, horizontal, and depth of the part where the abnormality occurs can be displayed.

  Further, since the abnormal component three-dimensional model image is displayed on the external terminal device connected to the image generation server device via a communication line, the operator can display such an abnormal component three-dimensional model image. There is no need to view beside the mechanical device, and the external terminal device allows viewing at a remote place far from the mechanical device.

  For example, even when the operator is located in a central control room or an office building of a factory where the mechanical device is installed, outside the factory, or the like, the abnormal terminal 3D model image is obtained by the external terminal device at hand. You can easily see it.

(5) Further, the network database stores the relationship between the abnormal signal and an abnormal cause area which is one or a plurality of three-dimensional areas that cause an abnormal operation state of the abnormal part that causes the abnormal signal. A second relationship is stored as matrix data, and the processing unit is configured to display the abnormal component in which the abnormal cause area and the normal area that is a three-dimensional area that is not the abnormal cause area among the abnormal parts are displayed separately. A three-dimensional model image may be generated.

  That is, in order to store the relationship between the abnormal signal and the abnormal cause area of the three-dimensional area which is a three-dimensional area including the vertical, horizontal, and depth of the abnormal part, Position and range can be easily specified, and a three-dimensional model image can be displayed at a remote place.

(6) In addition, based on the three-dimensional CAD data, display or non-display of one or a plurality of three-dimensional areas whose ranges are arbitrarily specified among the respective parts is selected to generate the abnormal part three-dimensional model image. May be.

  That is, even when the components are combined in a multilayered manner, one or more components other than the abnormal component or a three-dimensional region that is a three-dimensional region including vertical, horizontal, and depth is arbitrarily hidden. Thereby, it is possible to easily specify and display the location or range where the abnormality occurs.

  Furthermore, by hiding a part of the three-dimensional area of the abnormal part, it is possible to easily specify and display the location or range where the abnormality occurs.

(7) According to the present invention, the storage means provided in the image generating apparatus may cause an abnormal signal generated by a plurality of abnormal sensors provided in a mechanical device including a plurality of components and an abnormal operating state causing the abnormal signal. Alternatively, a database that stores a network database that stores a first relationship, which is a relationship with a plurality of abnormal components as the components, using matrix data, and a three-dimensional CAD database that stores three-dimensional CAD data of each of the components. A storing step, a communication unit included in the image generating apparatus, an abnormal signal receiving step of receiving the abnormal signal from the abnormal sensor, and a processing unit connected to the storage unit and the communication unit, based on the matrix data, Specifying abnormal component CAD data, which is three-dimensional CAD data of the abnormal component related to the abnormal signal, There is provided an image generation method characterized by including the abnormal component three-dimensional model image generating step of generating an abnormal component three-dimensional model image based on the AD data.

  That is, according to the image generation method of the present invention, the three-dimensional CAD data of each component is stored, and the three-dimensional CAD data of the abnormal component is specified based on the matrix data. It is possible to easily specify a three-dimensional position or range including the width and the depth. In addition, when the abnormal signal is received, a three-dimensional model image based on the three-dimensional CAD data is generated, so that a three-dimensional model image composed of the vertical, horizontal, and depth of the part where the abnormality occurs can be displayed.

(8) The database storing step may include a relationship between the abnormal signal and an abnormal cause area that is one or a plurality of three-dimensional areas that cause an abnormal operation state of the abnormal part that causes the abnormal signal. Storing a network database that stores the second relationship by matrix data, wherein the abnormal part three-dimensional model image generating step includes a step of generating a three-dimensional image of the abnormal part that is not the abnormal cause area and the abnormal cause area. The method may further include a step of generating the abnormal part three-dimensional model image in which the normal region, which is the region, is displayed separately.

  That is, in order to store the relationship between the abnormal signal and the abnormal cause area of the three-dimensional area which is a three-dimensional area including the vertical, horizontal, and depth of the abnormal part, Position and range can be easily specified, and a three-dimensional model image can be displayed.

(9) A range designating step of arbitrarily designating a range of one or a plurality of three-dimensional regions among the parts, and a display / non-display selecting step of selecting display / non-display of the designated range. May be.

  That is, even when the components are combined in a multilayered manner, one or more components other than the abnormal component or a three-dimensional region that is a three-dimensional region including vertical, horizontal, and depth is arbitrarily hidden. Thereby, it is possible to easily specify and display the location or range where the abnormality occurs.

  Furthermore, by hiding a part of the three-dimensional area of the abnormal part, it is possible to easily specify and display the location or range where the abnormality occurs.

(10) The present invention has a mechanical device including a plurality of components, a plurality of monitoring sensors provided in the mechanical device, a communication unit connected to the monitoring sensor, and an artificial intelligence, and is connected to the communication unit. An image generation device connected to the processing device and a storage device for storing a log database that stores operation information of the mechanical device along with time as log data while being connected to the processing device, wherein each of the monitoring sensors includes the mechanical device. An abnormal signal is issued when detecting an abnormal operating state of the mechanical device, and the operating information is identification information of an operator who operates the mechanical device for each operation of operating the mechanical device, and an identification of the mechanical device issued by each of the monitoring sensors. Operating state information indicating an operating state, including abnormal operating state information including the abnormal signal, the processing means, learning the artificial intelligence Further, based on a learning model obtained by the learning, the remaining time until the occurrence of the abnormal signal is estimated, and the abnormal component which is a three-dimensional model image of the abnormal component related to the abnormal signal whose occurrence is estimated. An object of the present invention is to provide an image generation and display system characterized by generating a three-dimensional model image.

  That is, since the remaining time until the occurrence of the abnormal signal is estimated by the image generation and display system of the present invention, the company that owns the mechanical device, the image generating device, or the mechanical device and the image generating device In addition, the organization or the like can take precautionary measures such as preparing replacement parts in preparation for an upcoming abnormality. Artificial intelligence is defined as the ability of functional units that perform functions such as reasoning and learning, which are generally considered in connection with human intelligence, according to "JIS X 0028 Information processing term-Artificial intelligence-Basic concept and expert system". Is done.

  In addition, since an abnormal part 3D model image, which is a 3D model image of the abnormal part related to the abnormal signal, is generated, it is possible to easily identify and display the location or range where the abnormality occurs. it can.

(11) The present invention provides a mechanical device including a plurality of components, a plurality of monitoring sensors provided in the mechanical device, communication means connected to the monitoring sensor, and a neural network learning unit for learning a multilayer neural network. An image having processing means connected to the communication means, and a log database connected to the processing device for storing operation information of the mechanical device with time and log data, and a storage means for storing the neural network A monitoring device, wherein each of the monitoring sensors issues an abnormal signal when detecting an abnormal operation state of the mechanical device, and the operation information is an operator who operates the mechanical device for each operation of operating the mechanical device. Identification information, operating state information indicating the operating state of the mechanical device emitted by each monitoring sensor, Abnormal processing information including a normal signal, the processing means estimates the remaining time until the occurrence of the abnormal signal based on the neural network, and relates to the abnormal signal whose occurrence is estimated. It is an object of the present invention to provide an image generation and display system that generates an abnormal part three-dimensional model image that is a three-dimensional model image of an abnormal part.

  That is, since the remaining time until the occurrence of the abnormal signal is estimated by the image generation and display system of the present invention, the company that owns the mechanical device, the image generating device, or the mechanical device and the image generating device In addition, the organization or the like can take precautionary measures such as preparing replacement parts in preparation for an upcoming abnormality. A neural network or a neural network is a network in which primitive processing elements are connected by an adjustable weighted link according to "JIS X 0028 Information processing term-Artificial intelligence-Basic concept and expert system", and each element is , Applying a non-linear function to input values from multiple links to generate a value and send it to other elements or provide it as output.

  In addition, since an abnormal part 3D model image, which is a 3D model image of the abnormal part related to the abnormal signal, is generated, it is possible to easily identify and display the location or range where the abnormality occurs. it can.

(12) In addition, the storage unit may form a matrix with a first relationship, which is a relationship between the abnormal signal and one or a plurality of abnormal components that cause the abnormal operation state that causes the abnormal signal. A network database storing data based on data; and a three-dimensional CAD database storing three-dimensional CAD data of each of the parts, wherein the processing means includes an abnormality related to an abnormality signal whose occurrence is estimated based on the matrix data. The abnormal component CAD data that is the three-dimensional CAD data of the component may be specified, and the abnormal component three-dimensional model image may be based on the abnormal component CAD data.

  That is, since the three-dimensional CAD data of each part is stored and the three-dimensional CAD data of the abnormal part is specified based on the matrix data, the three-dimensional CAD data including the length, width, and depth of the location where the abnormality occurs is specified. Position and range can be easily specified.

  Moreover, since a three-dimensional model image based on the three-dimensional CAD data is generated as an image to be displayed when an abnormal signal is received, a three-dimensional model image including the vertical, horizontal, and depth of a component in which an abnormality occurs is displayed. be able to.

(13) Further, the network database stores the relationship between the abnormal signal and an abnormal cause area which is one or a plurality of three-dimensional areas that cause an abnormal operating state of the abnormal part that causes the abnormal signal. A second relationship is stored as matrix data, and the processing unit is configured to display the abnormal component in which the abnormal cause area and the normal area that is a three-dimensional area that is not the abnormal cause area among the abnormal parts are displayed separately. A three-dimensional model image may be generated.

  That is, in order to store the relationship between the abnormal signal and the abnormal cause area of the three-dimensional area which is a three-dimensional area including the vertical, horizontal, and depth of the abnormal part, Position and range can be easily specified, and a three-dimensional model image can be displayed.

  As described above, the image generation device, the image generation and display system, or the image generation method of the present invention can easily specify and display a location or a range where an abnormality occurs.

FIG. 2 is a functional configuration diagram according to the first embodiment of the present invention. It is a network database NDB1 in the first embodiment of the present invention. 4 is a flowchart according to the first embodiment of the present invention. It is a network database NDB2 in the second embodiment of the present invention. It is a network database NDB3 in the third embodiment of the present invention. It is an image showing abnormal parts P01 in a third embodiment of the present invention. It is an image showing a normal part and an abnormal part P02 in the third embodiment of the present invention. It is an image showing abnormal parts P02 in a third embodiment of the present invention. It is a flowchart in the 3rd Embodiment of this invention (1/2). It is a flowchart in the 3rd Embodiment of this invention (1/2). It is a network database NDB4 in the fourth embodiment of the present invention. It is a network database NDB5 in the fifth embodiment of the present invention. It is a functional lineblock diagram in a 6th embodiment of the present invention. It is a functional lineblock diagram in a 7th embodiment of the present invention. (A) is a functional configuration diagram in a case where each of the mechanical devices Ma to Mc is located near the image generation device 22, and (b) is a case where each of the mechanical devices Ma to Mc and the image generation device 22 are located apart from each other. FIG. 2 is a functional configuration diagram. It is a network database NDB6 in the seventh embodiment of the present invention. It is a log database LDB in the seventh embodiment of the present invention. It is the first neural net NN1 in the seventh embodiment of the present invention. It is an image showing abnormal parts P11 in a 7th embodiment of the present invention.

  1 to 3 illustrate a first embodiment of the present invention. Reference numeral 1 in FIG. 1 denotes an image generation and display system.

  The image generation and display system 1 has an image generation device 2 as shown in the functional configuration diagram of FIG.

  The image generating device 2 includes a communication unit 3 connected to a plurality of abnormality sensors S provided in a mechanical device M including a plurality of components, a processing unit 4 connected to the communication unit 3, and a storage connected to the processing unit 4. Means 5 and display processing means 6.

  Here, the mechanical device M may be various types of mechanical devices. For example, according to the major categories used by the Cabinet Office in the statistical survey on machinery orders, prime movers, heavy electric machines, electronic and communication machines, industrial machines, machine tools, railway machines Includes vehicles, road vehicles, aircraft and ships. Hereinafter, a case of an industrial machine such as a synthetic resin processing machine will be described as an example.

  Further, each part may be various kinds of parts, and if it is a part constituting the machine M, it is not limited to a mechanical part or an electronic part, but a member which is a part of the structure, a plate which forms an outer surface of the structure. And the outer plate.

  Further, each abnormality sensor S may be various types of sensors, and includes elements for detecting physical quantities such as temperature, pressure, flow rate, light, magnetism, sound, vibration, speed, acceleration, current, voltage, and the like, and their changes. . A signal generated when a predetermined physical quantity such as a threshold value, an elapsed time until the threshold value is reached, the number of times the threshold value is reached, a change amount, time, the number of times, and the like are detected by the abnormal sensor S is referred to as an abnormal signal. . At this time, one abnormal sensor may detect two or more types of physical quantity, change amount, time, number of times, and the like, and may generate two or more types of abnormal signals accordingly.

  The communication means 3 is connected to each abnormal sensor S and receives these abnormal signals. At this time, a signal such as a physical quantity and a change amount may be always received from each abnormal sensor S, or only an abnormal signal generated from each abnormal sensor S may be received. Further, in the mechanical device M, an abnormal sensor S in which the communication unit 3 always receives a signal such as a physical quantity and a change amount, and an abnormal sensor S that receives only an abnormal signal may be provided.

  When an abnormal sensor S that always receives a signal such as a physical quantity or a change amount is provided, the communication unit 3 includes an abnormal signal determination unit 3a. The abnormal signal determination unit 3a determines a signal corresponding to the above-described abnormal signal from all signals such as a physical quantity and a change amount received from the abnormal sensor S.

  When the communication unit 3 includes the abnormal signal determination unit 3a, the communication unit 3 determines a threshold value of the abnormal signal written in the network database NDB, an elapsed time until the threshold value is reached, a value of the number of times the threshold value is reached, and the like. It is received from the processing means 4 described below. Then, the abnormal signal determination unit 3a determines a signal corresponding to the abnormal signal by comparing the signal received from the abnormal sensor S with the value written in the network database NDB.

  The processing means 4 has a three-dimensional CAD data specifying part 4a and a three-dimensional model image generating part 4b.

  When the communication unit 3 receives the abnormal signal, the three-dimensional CAD data specifying unit 4a uses the abnormal signal and the network database NDB read from the storage unit 5 described below to cause the abnormal operation state that causes the abnormal signal. An abnormal part P, which is one or more parts, is identified.

  The three-dimensional model image generation unit 4b generates the abnormal part three-dimensional model image Ip based on the abnormal part CAD data Dp that is the three-dimensional CAD data for representing the abnormal part P specified as described above. Further, a normal part three-dimensional model image Ir based on the normal part CAD data Dr that is three-dimensional CAD data for representing a normal part, and an entire part based on the whole CAD data Dm that is three-dimensional CAD data for representing the entire mechanical device M. A three-dimensional model image Im can be generated. Further, a composite three-dimensional model image Ii in which two or more three-dimensional model images are superimposed is generated.

  Here, the three-dimensional CAD data refers to CAD data composed of three-dimensional coordinate information including vertical, horizontal, and depth.

  The three-dimensional model is a shape model expressing a three-dimensional shape. According to Japanese Industrial Standards JIS B3401-1993 "CAD terms", three-dimensional models can be classified into solid models based on volume information, surface models based on surface information, and wireframe models based on line information. The three-dimensional model image is an image in which such a three-dimensional model is displayed on a certain display surface.

  The storage unit 5 has a network database storage unit 5a and a three-dimensional CAD database storage unit 5b.

  The network database storage unit 5a determines the first relationship between the abnormal signal generated by each abnormal sensor S and one or a plurality of abnormal components P that cause an abnormal operation state that causes the abnormal signal in FIG. The network database NDB1 stored by the matrix data shown in FIG.

  The network database NDB1 of FIG. 2 stores the four abnormal sensors S01 to S04 indicated by the leftmost column, the abnormal signals generated by the abnormal sensors S01 to S04 indicated by the middle column, and these abnormal signals indicated by the rightmost column. This is a database that stores, using matrix data, a first relationship, which is a relationship with the abnormal components P01 and P02 that cause the abnormal operating state to occur.

  The abnormality sensors S01 and S02 are sensors including an element for detecting a temperature. The abnormality sensors S03 and S04 are sensors including elements for detecting pressure. Then, each abnormal signal is represented by a threshold value when each is detected.

  For example, when the abnormality sensor S01 detects a temperature equal to or higher than the threshold value of 1000 ° C., the network database NDB1 indicates a relationship that a component that causes an abnormal operation state that causes an abnormal signal is the abnormal component P01. The first relationship is stored. Similarly, when the abnormality sensors S02 to S04 detect the respective threshold values, the relationship between the abnormal components P01, the abnormal components P01, and the abnormal components P02 that cause the abnormal operation state that causes each abnormal signal is respectively detected. The first relationship is stored.

  With these first relationships, the image generation device 2 can specify the abnormal components P01 and P02 for each abnormal operation state.

  The three-dimensional CAD database storage unit 5b stores a three-dimensional CAD database TDB1 that stores three-dimensional CAD data of the entire mechanical device M and three-dimensional CAD data of each component.

  In the three-dimensional CAD data of each part stored in the three-dimensional CAD database TDB1, the vertical, horizontal, and depth coordinate axes, which are the reference of the coordinate information, match the same coordinate axes of the entire CAD data Dm, and , And its coordinate information matches the coordinate information in a state where the mechanical device M is assembled.

  Therefore, the relationship between the coordinate information of one three-dimensional CAD data and the coordinate information of another three-dimensional CAD data is based on the relationship between the actual part and the mechanical device M with respect to the respective coordinate axes in the vertical, horizontal, and depth directions, or Shows the relative positional relationship between real parts. For example, the relationship between the coordinate information of the abnormal parts CAD data Dp01 and Dp02, which are three-dimensional CAD data for representing the abnormal parts P01 and P02, and the coordinate information of the entire CAD data Dm is the same as that of the actual abnormal parts P01 and P02 with respect to the coordinate axes. 3 shows a positional relationship with a mechanical device M.

  Accordingly, the 3D model image generation unit 4b superimposes the abnormal component 3D model images Ip01 and Ip02 on the normal component 3D model image Ir, another abnormal component 3D model image Ip, or the entire 3D model image Im. These positional relationships can be matched with the positional relationship between the actual abnormal parts P01 and P02 and the normal part, another abnormal part P or the mechanical device M. As a result, the three-dimensional model image generation unit 4b generates the composite three-dimensional model image Ii that is represented as if the abnormal parts P01 and P02 are mounted at the mounting position of the actual abnormal parts P01 and P02. can do.

  Note that the entire CAD data Dm does not necessarily need to be stored in the three-dimensional CAD database TDB, and in that case, it is only necessary that the coordinate axes serving as references for the coordinate information of the three-dimensional CAD data of each part match. .

  Hereinafter, the normal part three-dimensional model image Ir, the abnormal part three-dimensional model image Ip, the whole three-dimensional model image Im, and the composite three-dimensional model image Ii are collectively referred to as three-dimensional model images Ii, Im, Ip, and Ir.

  Further, the three-dimensional model image generation unit 4b selects display or non-display of any one or a plurality of parts included in the mechanical device M based on each of the three-dimensional CAD data, and selects the three-dimensional model images Ii, Im, Ip. , Ir.

  As these three-dimensional CAD data, CAD data created at the time of manufacturing and assembling or manufacturing and assembling the mechanical device M and each part can be used.

  In this way, the image generation device 2 can easily specify the three-dimensional position and range including the length, width, and depth of the location where the abnormality has occurred. Further, in order to generate a three-dimensional model image based on the three-dimensional CAD data Dm, Dp, and Dr as an image to be displayed when an abnormal signal is received, a three-dimensional model image including a vertical, a horizontal, and a depth including an abnormal part is generated. Ii, Im, Ip, and Ir can be displayed.

  In addition, the image generation device 2 can easily specify a three-dimensional position or range, which is a part of the entire mechanical device M, including the vertical, horizontal, and depth positions of the location where the abnormality has occurred. Further, in order to generate a three-dimensional model image based on the three-dimensional CAD data Dm, Dp, and Dr as an image to be displayed when an abnormal signal is received, as a part of the entire mechanical device M, a vertical image including an abnormal part, It is possible to display three-dimensional model images Ii, Im, Ip, Ir composed of horizontal and depth.

  The display processing means 6 has a display surface 6a and an alarm unit 6b. The display processing means 6 is incorporated in an operation panel (not shown) so that the display surface 6a is exposed. The operation panel is arranged at the level of the line of sight of the operator and is configured integrally with the mechanical device M.

  When the communication means 3 receives the abnormal signal, the display processing means 6 displays the three-dimensional model images Ii, Im, Ip, Ir generated by the processing means 4 on the display surface 6a. In addition, the alarm unit 6b sounds an alarm sound to call attention of the operator.

  Further, the display processing means 6 has an operation unit 6c. The operator operates the mechanical device M and processes the three-dimensional model images Ii, Im, Ip, Ir using the operation unit 6c.

  The operation unit 6c may be a keyboard, a mouse, or a trackball on an operation panel, or a touch panel on the display surface 6a, as long as the operator can operate with fingers.

  At this time, when, for example, the abnormal component three-dimensional model image Ip01 is hidden behind a normal component and is difficult to see in the composite three-dimensional model image Ii, the operator adds the normal component three-dimensional CAD data Dr for representing the normal component. An operation of arbitrarily specifying the range of the normal part three-dimensional model image Ir based on the selected part is performed, and a selection is made to hide the normal part from display and non-display.

  With these, the operator can easily observe the abnormal component three-dimensional model image Ip01 on the display surface 6a, and can easily grasp the position and range of the abnormal component P01 in the entire mechanical device M. .

  Note that the image generating device 2 may not only be configured integrally with the mechanical device M but also be configured separately. Further, the storage unit 5, the display processing unit 6, the storage unit 5 and the display processing unit 6, or a part of them may be arranged separately from other parts of the image generating apparatus 2.

  Here, a schematic flow from the start of the operation of the mechanical device M by the operator to the occurrence of the abnormal operation state and the start of the treatment for eliminating the abnormal operation state will be described with reference to the flowchart shown in FIG. explain.

  The flowchart illustrated in FIG. 3 illustrates the image generation method S100 of the present embodiment, and includes a database storage step S110, an abnormal signal reception step S120, a three-dimensional model image generation step S130, and a three-dimensional model image display step S140. Here, the three-dimensional model image generation step S130 may be called an abnormal part three-dimensional model image generation step.

  The operator starts operation of the mechanical device M, and the network database NDB1 and the three-dimensional CAD database TDB1 are stored in the storage unit 5 in a database storage step S110. At this time, the network database NDB1 stores the first relationship using matrix data. That is, the database storage step S110 includes a storage step S111 of the network database NDB1 that stores the first relationship.

  After the database storage step S110, the operation of the mechanical device M is started. Thereafter, an abnormal operation state of the mechanical device M occurs.

  The abnormal sensors S01 to S04 generate an abnormal signal with the occurrence of the abnormal operation state, and the communication unit 3 receives the abnormal signal in the abnormal signal receiving step S120.

  After the reception of the abnormal signal by the communication unit 3, in the three-dimensional model image generation step S130, the processing unit 4 generates three-dimensional model images Ii, Im, Ip, and Ir including the abnormal part three-dimensional model image Ip.

  After the three-dimensional model image generation step S130, the three-dimensional model images Ii, Im, Ip, Ir are displayed by the display processing means 6 in the three-dimensional model image display step S140. At this time, an alarm is sounded in the alarm step S141 to draw the operator's attention. That is, the three-dimensional model image display step S140 includes an alarm step S141.

  At this time, in the range specifying step S142, an operation of arbitrarily specifying the range of the three-dimensional model image of some parts can be performed. That is, the three-dimensional model image display step S140 includes a range designation step S142.

  Further, in the display / non-display selection step S143, it is possible to select whether to display or hide some of the components. That is, the three-dimensional model image display step S140 includes a display / non-display selection step S143.

  After the three-dimensional model image display step S140, the operator views the three-dimensional model images Ii, Im, Ip, and Ir, and starts a process for eliminating the corresponding abnormal operation state of the mechanical device M. For example, the operation of the mechanical device M is stopped, and the three-dimensional model images Ii, Im, Ip, Ir displayed on the display processing means 6 are observed, and the abnormal part three-dimensional model images Ip01, Ip02 displayed are displayed. The corresponding abnormal parts P01 and P02 are replaced.

  In the above-described three-dimensional model image generation step S130, it is possible to easily specify a three-dimensional position or range including the length, width, and depth of the location where the abnormality has occurred. In addition, in order to generate a three-dimensional model image based on the three-dimensional CAD data Dm, Dp, and Dr as an image to be displayed when an abnormal signal is received, a three-dimensional model including a vertical, a horizontal, and a depth including a component in which an abnormality has occurred is generated. The model images Ii, Im, Ip, Ir can be displayed.

  Further, in the three-dimensional model image generation step S130, it is possible to easily specify a three-dimensional position or range including the length, width, and depth of the location where the abnormality has occurred. Further, in order to generate a three-dimensional model image based on the three-dimensional CAD data Dm, Dp, and Dr as an image to be displayed when an abnormal signal is received, as a part of the entire mechanical device M, a vertical image including an abnormal part, It is possible to display three-dimensional model images Ii, Im, Ip, Ir composed of horizontal and depth.

  Thereby, for example, in order to replace parts, it is possible to easily grasp the three-dimensional abnormal operation state relating to the abnormal parts P01 and P02, and easily confirm the three-dimensional position and range of the abnormal parts P01 and P02. it can.

  Furthermore, in the partial non-displaying step S142, the abnormal component three-dimensional model images Ip01 and Ip02 of the abnormal components P01 and P02 which are hidden behind other components and are difficult to see are easily observed. Therefore, the three-dimensional position and range of the abnormal components P01 and P02 can be confirmed more reliably.

  FIG. 4 illustrates a second embodiment of the present invention.

  A first relationship, which is a relationship between an abnormal signal generated by each abnormal sensor S and one or a plurality of abnormal components P causing an abnormal operation state causing the abnormal signal, is stored by matrix data shown in FIG. The network database NDB2 is stored in the network database storage unit 5a.

  The network database NDB2 illustrated in FIG. 4 includes a first abnormality sensor S01 indicated by a leftmost column, a first abnormality signal generated by the first abnormality sensor S01 indicated by a rightmost column, and a first abnormality signal indicated by a middle column. The second abnormal sensor S05, the second abnormal signal generated by the second abnormal sensor S05 indicated by the right column thereof, and the first abnormal signal and the second abnormal signal indicated by the rightmost column are simultaneously generated. This is a database that stores a first relationship, which is a relationship with the abnormal components P01 and P03 that cause the abnormal operation state to be caused, by matrix data.

  The abnormality sensor S05 is a sensor including an element for detecting pressure. Configurations other than those described above are common to the first embodiment.

  The network NDB2 generates those abnormal signals when the first abnormal sensor S01 detects a temperature equal to or higher than the threshold value of 1000 ° C. and the second abnormal sensor S05 detects a pressure equal to or higher than the threshold value of 1 MPa. The first relationship, which is the relationship between the abnormal component P01 and the abnormal component P03 that cause the abnormal operating state to be executed, is stored.

  As described above, since the abnormal operation state is grasped by simultaneously generating two or more abnormal signals such as the abnormal signal generated by the first abnormal sensor and the abnormal signal generated by the second abnormal sensor, more accurate and detailed information can be obtained. The abnormal component P causing the abnormal operation state can be specified.

  Although not shown in FIG. 4, when the first abnormal signal and the second abnormal signal are emitted at intervals of, for example, less than a certain number of seconds or at least a certain number of seconds, The first relationship may be defined such that the abnormal operating state of the device is grasped. In this way, by adding the passage of time to the requirement, the abnormal component P causing the abnormal operation state can be specified more accurately and in detail.

  5 to 10 illustrate a third embodiment of the present invention.

  In the present embodiment, when the communication unit 3 receives an abnormal signal, the three-dimensional CAD data specifying unit 4a uses the abnormal signal and a network database NDB read out from the storage unit 5 described below to generate the abnormal signal. An abnormal component P that is one or more components that cause an operating state, and an abnormal cause area A that is one or a plurality of three-dimensional areas that cause the abnormal operating state that causes the abnormal signal among the abnormal components P And

  Based on the abnormal component CAD data Dp that is the three-dimensional CAD data for representing the abnormal component P, the three-dimensional model image generation unit 4b includes, among the abnormal components P, the abnormality cause area A specified as described above, The three-dimensional model images Ii, Im, Ip, and Ir that are displayed so as to be distinguished from the normal region R, which is a three-dimensional region that is not the abnormal cause region A, are generated.

  Further, the three-dimensional model image generation unit 4b, based on each of the three-dimensional CAD data Dp, Dr, and Dm, regardless of whether the abnormal cause area A or the normal area R is used, includes the entire mechanical device M, the abnormal part P, or the normal part. , One or a plurality of three-dimensional regions can be arbitrarily specified, and display / non-display of the three-dimensional region can be selected to generate three-dimensional model images Ii, Im, Ip, Ir.

  The network database storage unit 5a stores a first relationship, which is a relationship between an abnormal signal generated by each abnormal sensor S and one or a plurality of abnormal components P that cause an abnormal operating state that causes the abnormal signal, and The second relationship, which is the relationship between the abnormal signal among the abnormal components P and one or a plurality of abnormality cause areas A that cause the abnormal operation state causing the abnormal signal, is represented by matrix data shown in FIG. The network database NDB3 to be stored is stored.

  The network database NDB3 in FIG. 5 is a first relationship which is a relationship between the abnormal signals generated by the respective abnormal sensors S01 to S04 and the abnormal components P01 and P02 which cause the abnormal operation state causing these abnormal signals. Is stored in the form of matrix data, the abnormal signals similarly generated by the abnormal sensors S01 to S04, and the causes of the abnormal operating states that cause these abnormal signals among the abnormal components P01 and P02 indicated by the second column from the right end. This is a database that stores a second relationship, which is a relationship with the abnormal cause regions A011, A012, A013, A021, and A022, using matrix data.

  For example, when the abnormality sensor S01 detects a temperature equal to or higher than the threshold value of 1000 ° C., the network database NDB3 indicates a relationship that a component causing an abnormal operation state that causes an abnormal signal is the abnormal component P01. The first relationship is stored. Similarly, when the abnormality sensors S02 to S04 detect the respective threshold values, the relationship between the abnormal components P01, the abnormal components P01, and the abnormal components P02 that cause the abnormal operation state that causes each abnormal signal is respectively detected. The first relationship is stored.

  Further, when the abnormality sensor S02 detects a temperature equal to or higher than 100 ° C. which is the first threshold, the network database NDB3 determines that the three-dimensional area that causes the abnormal operation state that causes the abnormal signal is included in the abnormal part P01. A second relationship, which is a relationship of being the abnormality cause area A013, and a three-dimensional which causes an abnormal operation state that generates an abnormal signal when detecting a temperature equal to or higher than 300 ° C., which is a second threshold value. The second relationship, which is the relationship between the regions that are the abnormal cause region A012 and the abnormal cause region A013 of the abnormal component P01, is stored.

  Similarly, when the abnormality sensors S01, S03, and S04 detect the respective thresholds, the three-dimensional area that causes the abnormal operation state that causes each abnormal signal is caused by the abnormal cause of the abnormal component P01 or the abnormal component P02. A second relationship, which is a relationship between the area A011, the abnormal cause area A013, the abnormal cause area A021, and the abnormal cause area A022, is stored.

  As an example, it is assumed that an abnormal sensor S01 and an abnormal sensor S02 as shown in the image example in FIG. 6 are arranged on a cylindrical abnormal component P01 included in the mechanical device M. Further, the abnormal part P01 includes abnormality cause areas A011, A012, and A013 as shown in a vertical section including the arrangement positions of these abnormality sensors S01 and S02.

  At this time, for example, when the abnormality sensor S02 detects a temperature equal to or higher than 100 ° C., which is the first threshold, and the temperature is lower than 300 ° C., the network database NDB3 indicates a three-dimensional area that causes an abnormal operation state. Is only the abnormality cause area A013. On the other hand, for example, when the abnormality sensor S02 detects a temperature equal to or higher than the second threshold value of 300 ° C., the three-dimensional area that causes the abnormal operation state is only the abnormality cause area A013. But the second relationship that extends to the abnormal cause area A012.

  With such a second relationship, the image generation device 2 can specify the abnormality cause areas A011, A012, A013, A021, and A022 for each abnormal operation state.

  Then, the three-dimensional model image generation unit 4b generates a three-dimensional model in which, among the abnormal parts P01 and P02, the abnormality cause areas A011, A012, A013, A021, and A022 and the normal area R are divided for each area. Images Ii, Im, Ip, and Ir can be generated. Alternatively, it can be expressed as if the abnormal components P01 and P02 are mounted at the mounting position of the actual abnormal components P01 and P02 in the mechanical device M. Configurations other than those described above are common to the first embodiment.

  Further, as an example different from the above image example, as shown in an image example shown in FIG. 7A, an abnormal part 3D model image Ip02 of the abnormal part P02 based on the abnormal part CAD data Dp and an abnormal part P02 When a composite three-dimensional model image I01 is generated in which a normal part three-dimensional model image Ir based on normal part CAD data Dr, which is three-dimensional CAD data for representing a normal cylindrical part to be fitted, is generated, the center line is generated. It is possible to generate a cut three-dimensional model image I02, which is a composite three-dimensional model image of the cut image, by making a selection to display the left side of the image and to hide the right side of the image at a cross section orthogonal to C. it can. The cut three-dimensional model image I02 is shown in the image example of FIG.

  At this time, as shown in the network database NDB3 in FIG. 5, the abnormality sensor S04 detects a pressure equal to or higher than the first threshold value of 500 kPa, and is a three-dimensional area that causes an abnormal operation state that generates an abnormality signal. Even if it is known that the abnormal cause area A021 exists in the abnormal part P02, the position or range occupied by the abnormal cause area A021 cannot be grasped from the cut three-dimensional model image I02.

  Therefore, the operator can select to display the abnormal part P02 and hide the normal part, and generate an abnormal part cut three-dimensional model image I03 which is a cut image of only the abnormal part P02. The abnormal part cut three-dimensional model image I03 is shown in the image example of FIG.

  However, even from such an abnormal part cut three-dimensional model image I03, the position and range occupied by the abnormality cause area A021 cannot be grasped. Specifying a three-dimensional area, hiding this slit-shaped three-dimensional area, and selecting to display a three-dimensional area in a range other than the slit-shaped area to partially hide the three-dimensional area The non-display three-dimensional model image I04 can be generated. The partially hidden three-dimensional model image I04 is shown in the image example of FIG.

  As a result, it is possible to easily observe the abnormal cause area A021, which has been hidden and cannot be seen so far, and to easily grasp the position and range occupied by the entire mechanical device M and the abnormal part P02.

  The flowcharts shown in FIGS. 9 and 10 show an example of the image generation method S200 of the present embodiment, and include a database storage step S210, an abnormal signal reception step S220, a three-dimensional model image generation step S230, and a three-dimensional model image display step S240. including. Here, the three-dimensional model image generation step S230 may be called an abnormal part three-dimensional model image generation step.

  In the database storage step S210, the network database NDB3 and the three-dimensional CAD database TDB1 are stored in the storage unit 5. At this time, the network database NDB3 stores the first relationship and the second relationship using matrix data. That is, the database storage step S210 includes a storage step S211 of the network database NDB3 that stores the first relationship and the second relationship.

  After the abnormal operation state of the mechanical device M occurs, the process proceeds to the three-dimensional model image generation step S230 through the abnormal signal receiving step S220. Here, it is possible to generate three-dimensional model images Ii, Im, Ip, and Ir in which the normal region R and the abnormal cause region A are displayed separately. That is, the three-dimensional model image generating step S230 includes a generating step S231 of the three-dimensional model images Ii, Im, Ip, and Ir in which the normal region and the abnormal cause region are displayed separately.

  After the three-dimensional model image generation step S230, the process proceeds to a three-dimensional model image display step S240. In the range specifying step S242 included in the three-dimensional model image display step S240, not only can the operation of arbitrarily specifying the range of the three-dimensional model image of some parts be performed, but also some of the parts The operation of arbitrarily designating the three-dimensional region can be performed.

  Further, in the display / non-display selection step S243 included in the three-dimensional model image display step S240, not only the selection to display or non-display the whole part can be performed, but also a part of Can be selected to display or hide the three-dimensional area of the image.

  After the composite three-dimensional model image display step S240, the operator views the three-dimensional model images Ii, Im, Ip, and Ir and starts a process for eliminating the corresponding abnormal operation state of the mechanical device M. For example, while the operation of the mechanical device M is stopped, the three-dimensional model images Ii, Im, Ip, and Ir displayed on the display processing unit 6 are observed, and the abnormality cause area A011, which is displayed separately from the normal area R, is displayed. Repair or replace the abnormal parts P01 and P02 including A012, A013, A021, and A022.

  In the above-described three-dimensional model image generation step S230, it is possible to easily specify a three-dimensional position or range including the length, width, and depth of the location where the abnormality has occurred. Further, in order to generate a three-dimensional model image based on the three-dimensional CAD data Dm, Dp, and Dr as an image to be displayed when receiving the abnormal signal, the three-dimensional model image Ii including the vertical, horizontal, and depth including the abnormal cause area A is generated. , Im, Ip, and Ir.

  Further, in the three-dimensional model image generation step S230, it is possible to easily specify a three-dimensional position or range, which constitutes a part of the entire mechanical device M, including the vertical, horizontal, and depth of the location where the abnormality has occurred. it can. Further, in order to generate a three-dimensional model image based on the three-dimensional CAD data Dm, Dp, and Dr as an image to be displayed when the abnormal signal is received, the three-dimensional model image Ii including the vertical, horizontal, and depth including the abnormal cause area A is generated. , Im, Ip, and Ir.

  Thereby, for example, in order to eliminate the abnormal operation state of the abnormal component P01, as shown in FIG. 6, the three-dimensional abnormal operation state relating to the abnormality cause areas A011, A012, and A013 is easily grasped, and The three-dimensional position and range of the areas A011, A012, and A013 can be easily confirmed.

  Further, in the partial non-displaying step S242, as in the case of FIGS. 7 and 8, for example, it is difficult to see behind a normal part and hidden behind another three-dimensional area of the abnormal part P02. Since the difficult abnormality cause area A021 is easily observed, the three-dimensional position and range of the abnormality cause area A021 can be more reliably confirmed for repair or replacement of the abnormal part P02.

  FIG. 11 illustrates a fourth embodiment of the present invention.

  The network database storage unit 5a includes a first relationship, which is a relationship between an abnormal signal generated by each abnormal sensor S and one or a plurality of abnormal components P that cause an abnormal operation state that causes the abnormal signal, and An abnormal signal and a second relationship, which is a relationship between one or a plurality of abnormal cause areas A which cause the abnormal operation state which causes the abnormal signal among the abnormal components P, are represented by matrix data shown in FIG. The network database NDB4 to be stored is stored.

  The network database NDB4 in FIG. 11 stores, using matrix data, a first relationship that is a relationship between an abnormal signal generated by the abnormal sensor S01 and an abnormal component P01 that causes an abnormal operation state that causes the abnormal signal. In addition, the second relationship, which is the relationship between the abnormal signal generated by the abnormal sensor S01 and the abnormal cause areas A011 and A014 of the abnormal component P01 that cause the abnormal operation state that causes the abnormal signal, is represented by matrix data. Is a database stored by. Configurations other than those described above are common to the third embodiment.

  For example, when the abnormal sensor S01, which is a temperature sensor, detects a temperature of 800 ° C. or higher within 60 minutes after the start of operation, the relationship with the abnormal component P01 that causes an abnormal operating state that causes an abnormal signal is generated. 1 is stored.

  Further, when the abnormality sensor S01 detects a temperature of 800 ° C. or more within 60 minutes after the start of operation, a three-dimensional area that causes an abnormal operation state that causes an abnormal signal is generated in the abnormal cause area A011 of the abnormal part P01. And a second relationship, which is a relationship between being the abnormality cause area A014.

  As described above, the abnormal signal includes the lapse of time such as the elapsed time after the start of operation as a factor, so that the abnormal component P and the abnormal cause area A that cause the abnormal operation state can be specified more accurately and in detail. Can be.

  FIG. 12 illustrates a fifth embodiment of the present invention.

  The network database storage unit 5a includes a first relationship, which is a relationship between an abnormal signal generated by each abnormal sensor S and one or a plurality of abnormal components P that cause an abnormal operation state that causes the abnormal signal, and The matrix data shown in FIG. 12 shows the abnormal signal and the second relationship which is the relationship between the abnormal component P and one or a plurality of abnormal cause areas A which cause the abnormal operating state causing the abnormal signal. The network database NDB5 to be stored is stored.

  The network database NDB5 in FIG. 12 stores, using matrix data, a first relationship that is a relationship between an abnormal signal generated by the abnormal sensor S01 and an abnormal component P01 that causes the abnormal operation state that causes the abnormal signal. At the same time, the second relationship, which is the relationship between the abnormal signal generated by the abnormal sensor S01 and the abnormal cause area A011 of the abnormal component P01 which causes the abnormal operation state that causes the abnormal signal, is stored by matrix data. Database. Configurations other than those described above are common to the third embodiment.

  For example, when the abnormality sensor S01 detects a temperature of 500 ° C. or more and the detection state does not continue for 60 seconds or more. When such a case occurs three or more times, an abnormal operation state that causes an abnormality signal is generated. A first relationship that is a relationship with the abnormal component P01 that causes the abnormal condition and a second relationship that is a relationship with the abnormal cause area A011 that causes the abnormal operating state that causes the abnormal signal. Stored.

  Further, when the abnormality sensor S01 detects a temperature of 500 ° C. or more and the detection state continues for 60 seconds or more, the relationship with the abnormal component P01 which causes an abnormal operation state that causes the abnormal signal is generated. A first relationship and a second relationship, which is a relationship between an abnormal cause area A011 that causes an abnormal operation state that causes the abnormal signal, are stored.

  As described above, the abnormal signal P includes the lapse of time such as one continuous time or the number of times the abnormal signal occurs, so that the abnormal component P and the abnormal cause area A that cause the abnormal operation state can be specified more accurately and in detail. can do.

  According to the above-described embodiment, it is possible to leave such an abnormal signal, an abnormal cause area A that causes the abnormal operating state that causes the abnormal signal, and an abnormal history that is also the history of the abnormal component P. By accumulating the abnormality history, an abnormal operation state that is likely to occur in the machine M and an abnormal operation state that is likely to occur when a specific operator operates the machine M are analyzed to improve the machine M. It can be used for training of operators.

  In addition, it is possible to review the arrangement, number, type, etc. of the abnormal sensors S, factors of abnormal signals such as elapsed time, duration, number of times, etc., and to optimize for more accurate and detailed understanding of abnormal operating conditions. It is.

  FIG. 13 illustrates a sixth embodiment of the present invention. Reference numeral 11 in FIG. 13 denotes an image generation and display system.

  The image generation and display system 11 includes an image generation server device 12 and an external terminal device 17 that is connected to the image generation server device 12 via a communication line such as the Internet, wireless, or a telephone line. The external terminal device 17 is an information processing terminal device such as a dedicated terminal, a PC (Personal Computer), a tablet terminal, a smartphone, a mobile phone, a PDA (Personal Digital Assistant), and the like.

  The image generation server device 12 is connected to a communication unit 13 connected to a plurality of abnormality sensors S provided in a mechanical device M including a plurality of components, a processing unit 14 connected to the communication unit 13, and connected to the processing unit 14. A storage unit 15 and a display processing unit 6 are provided.

  The communication unit 13 has a receiving unit 13r and a transmitting unit 13d.

  The external terminal device 17 includes a terminal receiving unit 17r and a terminal transmitting unit 17d that transmit and receive data to and from the receiving unit 13r and the transmitting unit 13d via a communication line, and a terminal connected to the terminal receiving unit 17r and the terminal transmitting unit 17d. It has a processing means 18 and a terminal display processing means 19 connected to the terminal processing means 18.

  The terminal display processing means 19 has a terminal display surface 19a and a terminal alarm unit 19b.

  The terminal display processing means 19 receives the three-dimensional model images Ii, Im, Ip, Ir generated by the processing means 14 via the communication means 13 when the communication means 13 receives the abnormal signal from the abnormal sensor S, and displays the terminal display. It is displayed on the surface 19a. Further, the terminal alarm unit 19b sounds an alarm sound to call attention of the operator.

  At this time, the three-dimensional model images Ii, Im, Ip, Ir are displayed not only on both the display surface 16a of the image generation server device 12 and the terminal display surface 19a of the external terminal device 17, but also on the terminal display surface 19a. May be displayed. Further, the alarm sound may be sounded only by the terminal alarm unit 19b.

  Further, the terminal display processing means 19 has a terminal operation unit 19c. The operator operates the mechanical device M and processes the three-dimensional model images Ii, Im, Ip, Ir using the terminal operation unit 19c.

  At this time, the operation of the mechanical device M and the processing of the three-dimensional model images Ii, Im, Ip, Ir can be performed from both the operation unit 16c of the image generation server device 12 and the terminal operation unit 19c of the external terminal device. Not only that, it may be possible to perform only from the terminal operation unit 19c.

  The terminal operation unit 19c is configured by a touch panel. Alternatively, a keyboard, a mouse, or a trackball may be used as long as the operator can operate with fingers. Configurations other than those described above are common to the third embodiment, the fourth embodiment, and the fifth embodiment.

  At this time, the operator sets the abnormal cause area A021 behind the three-dimensional area of the normal part or the abnormal part P02 in the three-dimensional model images Ii, Im, Ip, and Ir, for example, as in the cases of FIGS. When hidden and difficult to see, a selection is made to hide the normal part three-dimensional model image Ir based on the normal part three-dimensional CAD data Dr so as to make the abnormal cause area A021 easily visible. The user can specify a three-dimensional area in the range of, and select to hide the three-dimensional area.

  With these, the operator can easily observe the abnormal cause area A021 on the terminal display surface 19a, and easily grasp the position and range of the abnormal cause area A021 in the abnormal part P02 or the entire machine M. be able to.

  As described above, since the three-dimensional model images Ii, Im, Ip, and Ir are displayed on the external terminal device 17 connected to the image generation server device 12 via the communication line, the operator can input the three-dimensional model images Ii, There is no need to see Im, Ip, and Ir beside the mechanical device M, and it is possible to see Im, Ip, and Ir at a remote place far from the mechanical device M by the external terminal device 17.

  For example, even when the operator is located in the central control room or office building of a factory where the machine M is installed, outside the factory, or the like, the three-dimensional model images Ii, Im, Ip and Ir can be easily seen. For such a purpose, the external terminal device 17 may be a portable terminal such as a tablet terminal or a notebook PC connected to the Internet, or a desktop PC connected to the Internet and placed in an office building. A fixed terminal such as

  Further, the operator does not need to perform operations such as designation of parts and three-dimensional regions in the three-dimensional model images Ii, Im, Ip, and Ir, selection of display or non-display, beside the mechanical device M, and the external terminal device 17 does not need to be operated. Thus, it can be performed in a remote place far from the mechanical device M. Then, after grasping the position and range of the abnormal component P and the abnormal cause area A in such a remote place, rush below the mechanical device M to perform an abnormal operation state of the mechanical device M such as repair or replacement of the abnormal component P. Can be taken.

  Further, depending on the type of the abnormal operation state of the machine M, even if it is difficult to immediately access the machine M due to high temperature, high pressure, smoke, steam emission, radioactive contamination, etc. Through the external terminal device 17, observation and operation can be performed in a remote place away from the mechanical device M.

  14 to 18 illustrate a seventh embodiment of the present invention. In FIG. 14A, reference numeral 21 denotes an image generation and display system.

  The image generation and display system 21 includes three mechanical devices Ma to Mc including a plurality of components and an image generation device 22. Each of the mechanical devices Ma to Mc is located near the image generating device 22, for example, in the same factory.

  Each of the mechanical devices Ma to Mc includes a first monitoring sensor S21, S31, S41, a second monitoring sensor S22, S32, S42, a sixth monitoring sensor S26, S36, S46, and a seventh monitoring sensor S27, S37. , S47 and an eighth monitoring sensor S28, S38, S48. Note that the first monitoring sensor and the second monitoring sensor may be referred to as a first abnormality sensor and a second abnormality sensor, respectively.

  Further, each monitoring sensor S may be various types of sensors, and includes elements for detecting physical quantities such as temperature, pressure, flow rate, light, magnetism, sound, vibration, speed, acceleration, current, voltage, and the like, and their changes. . A signal generated when such a monitoring sensor S detects a predetermined physical quantity such as a threshold value, an elapsed time until the threshold value is reached, and the number of times the threshold value is reached, a change amount, time, number of times, and the like is detected as an operating state signal. Or called an abnormal signal. At this time, one monitoring sensor may detect two or more types of physical quantity, change amount, time, number of times, and the like, and may generate two or more types of operating state signals or abnormal signals accordingly.

  The image generating device 22 includes a communication unit 23 connected to each of the monitoring sensors S21 to S48, a three-dimensional CAD data specifying unit 24a, a three-dimensional model image generating unit 24b, and a neural network learning unit 24c for learning a multilayer neural network NN. And a processing unit 24 connected to the communication unit 23.

  At this time, each of the mechanical devices Ma to Mc and the image generating device 22 may be located apart from each other, and as shown in FIG. 14B, the communication unit 23 has a receiving unit 23r, and each of the monitoring sensors S21 to S48. And the receiving unit 23r may be connected via a communication line such as the Internet, wireless, or a telephone line.

  The image generation device 22 is connected to the processing unit 24 and stores a neural network NN and a log database LDB that stores the operation information H, Sr, and Si of each of the mechanical devices Ma to Mc as time and log data. Means 25 are provided. The storage unit 25 has a network database storage unit 25a, a three-dimensional CAD database storage unit 25b, a log data storage unit 25c, and a learning model storage unit 25d. The log data storage unit 25c stores the log database LDB, and the learning model The storage unit 25d stores the neural network NN.

  By the way, according to the prior art disclosed in Japanese Patent Application Laid-Open No. 2017-68324, a company, an institution, or the like that owns the mechanical device M can display an alarm screen indicating that an abnormality has occurred after an abnormality has occurred. It is not possible to pre-estimate the occurrence of such anomalies and take precautionary measures such as preparing replacement parts in preparation for the upcoming anomalies.

  In addition, the structure of the mechanical device M becomes complicated, and when the mechanical device is configured by combining a large number of three-dimensional parts and members, abnormalities are not obtained simply by the information indicating the layout and wiring of the components by the above-described prior art. It is difficult to identify or display a three-dimensional position or range consisting of the vertical, horizontal, and depth of the location where the error occurred.

  Further, when such parts and members are combined in a multilayered manner, it is particularly difficult to identify and display a place where an abnormality has occurred from outside the combined parts. Alternatively, for example, when the part has a cylindrical shape and the abnormal part is located on the inner peripheral surface side, it is difficult to identify or display the abnormal part even if the parts are not combined with each other. It is.

  In view of such a problem, the present embodiment estimates the remaining time until an abnormal signal is generated, and generates an abnormal part 3D model image that is a 3D model image of an abnormal part related to the abnormal signal. Accordingly, it is an object of the present invention to provide an image generation system capable of easily specifying and displaying a location or a range in which an abnormality occurs.

  The network database NDB6 in FIG. 15 includes two abnormal sensors (monitoring sensors) S21 and S22 indicated by the leftmost column, abnormal signals generated by the abnormal sensors S21 and S22 indicated by the middle column, and an abnormal signal indicated by the rightmost column. Is a database that stores a first relationship, which is a relationship with an abnormal component P11 that causes an abnormal operation state that causes an abnormal signal, by matrix data.

  A log database LDB1, which is an example of the log database LDB illustrated in FIG. 16, indicates a machine device name, operation times, operator identification information H, date and time, operation state information Sr, and abnormal operation state information Si in order from the leftmost column to the rightmost column. . FIG. 16 shows a log database LDB for the mechanical device Ma.

  In the column of the moving state information Sr, the respective monitoring sensors S26 to S28 and the operating state signals generated by the respective monitoring sensors S26 to S28 are shown to indicate the operating state of the mechanical device Ma at each date and time. In the column of the abnormal operation state information Si, a first abnormality sensor (monitoring sensor) S21 that detects the abnormal operation state and a first abnormality sensor S21 for indicating the abnormal operation state of the mechanical device Ma are also shown. And an abnormal signal generated by the.

  For example, in the first operation, the first operator H01 turns on the main switch (not shown) of the mechanical device Ma at 9:05 on July 20, 2018, and the sixth monitoring sensor S26 detects this. , An operation state signal “ON” was issued. Next, at 9:08:30, the first driving device (not shown) was turned on and driven at a speed of 10 m / h, so that the seventh monitoring sensor S27 detected them, and the operation state signal “ON” 10m / h ". Further, at 9:09, the second drive device (not shown) was turned on and driven at a speed of 10 m / h, so that the eighth monitoring sensor S28 detected them, and the operation state signal "ON 10 m / h" Issued.

  Thereafter, at 9:14, the first abnormality sensor S21 detected a temperature of 1000 ° C. or higher, and thus issued an abnormal signal “1000 ° C. or higher”.

  Then, at 9:15, since the switch of the first drive device and the switch of the second drive device were turned off, the seventh and eighth monitoring sensors S27 and S28 detect them, and both of them have the operation state signal “ OFF ". Further, since the main switch was turned off at 9:15:30, the sixth monitoring sensor S26 detected this, and issued the operating state signal “OFF”.

  After 11:30, each monitoring sensor S26 to S28 emits a respective operating state signal by the operation of the mechanical device Ma by the second operator H02.

  The neural network learning unit 24c makes the neural network NN learn. Then, the neural network NN is stored in the learning model storage unit 25d.

  FIG. 17 shows an example of the neural network NN. The neural network learning unit 24c inputs the log data whose operator identification information H is the first operator H01 from the log database LDB1 of FIG. 16 to the first neural network NN1 shown in FIG. 17 for the machine Ma, for example.

  The first neural network NN1 is a network having a hierarchical structure, and is divided into three layers, an input layer, an intermediate layer, and an output layer, from the left side in FIG.

  The intermediate layer is composed of n layers, and the first neural network NN1 is a multilayer neural network composed of n + 2 layers obtained by adding an input layer and an output layer to the intermediate layer.

  To the input layer, for example, in order from the top in FIG. 17, the first time is a time in seconds from when the sixth monitoring sensor S26 emits “ON” to when the seventh monitoring sensor S27 emits “ON”. The input value x1, the second input value x2, which is the speed in m / h units generated by the seventh monitoring sensor S27, and the eighth monitoring sensor S28 after the sixth monitoring sensor S26 has turned ON. A third input value x3, which is a time in seconds until “ON” is issued, and a fourth input value x4, which is a speed in m / h that is emitted by the eighth monitoring sensor S28, are input.

  In the hidden layer, in response to the example of these four input values, the hidden layer neuron 01a, which is the hidden layer neuron located at the upper left of FIG. 17, receives the first to fourth input values x1 to x4 respectively. Corresponding four coupling coefficients w1 to w4 are set. The intermediate layer neuron 01a outputs an output value ya. The output value ya may be a continuous value, or may be 0 or 1.

  Similarly to the intermediate layer neuron 01a, the intermediate layer neuron 01b, which is an intermediate layer neuron located one step below the intermediate layer neuron 01a, has four coupling coefficients corresponding to the first to fourth input values x1 to x4, respectively. w is set, and the output value yb is output. Below that is a similar hidden neuron.

  In an intermediate layer neuron 02m in the second column, which is an intermediate layer neuron located one row ahead of each intermediate layer neuron 01m in the first column, each output value output from each intermediate layer neuron 01m in the first column A coupling coefficient w corresponding to each of ym is set. Further, similar intermediate layer neurons are arranged up to the n-th row in front of the same.

  Thus, an intermediate layer is formed by each of the intermediate layer neurons arranged vertically and horizontally.

  From the output layer, for example, the first time, which is the time in seconds from when the sixth monitoring sensor S26 emits “ON” to when the first abnormality sensor S21 detects a temperature of 1000 ° C. or more and issues an abnormality signal, Is output.

  The learning of the first neural network NN1 is performed by the neural network learning unit 24c repeating, for example, forward calculation and backward calculation. The neural network learning unit 24c converts the first to fourth input values x1 to x4 and the first output value z1 when the operator H01 operates from the log database LDB1 in the case of the mechanical device Ma into the first neural network NN1. input. For example, for the first operation time, 210 is used as the first input value x1, 10 is used as the second input value x2, 240 is used as the third input value x3, and 10 is used as the fourth input value x4. 540 is input as the first output value z1. After the first operation, the input values and output values x1 to x4, z1 when the first operator H01 operates are also input.

  Further, when the other mechanical devices Mb and Mc are of the same model as Ma, the input values and the output values x1 to x4 and z1 when the first operator H01 operates in the case of the mechanical devices Mb and Mc are all changed. Input to the first neural network NN1.

  At this time, as described above, the first output value z1 540 of the first operation of the mechanical device Ma by the first operator H01 is 540, which is the input value x1 to x4 of the first operation of the mechanical device Ma. Is the teacher output corresponding to. Then, each coupling coefficient w is determined such that the first output value z1 becomes 540. An output value is obtained from an input value by a forward operation using the coupling coefficient w determined in this way.

  Also, the coupling coefficient is corrected by the backward operation so that the error between the output value obtained by the forward operation and the teacher output is reduced. For example, each coupling coefficient w is repeatedly corrected so that the square (square error E) of the difference between the output value obtained by the forward calculation and the teacher output after the first operation is reduced.

  The first neural net NN1 thus learned is stored in the learning model storage unit 25d.

  Further, the operator identification information H inputs the log data of the second operator H02 to a second neural network NN2 (not shown), and the neural network learning unit 24c outputs the second neural network NN2 in the same manner as the first neural network NN1. To learn. After learning the second neural net NN2 in this way, it is stored in the learning model storage unit 25d.

  For example, after the first operator H01 turns on the main switch of the mechanical device Ma, the three-dimensional CAD data specifying unit 24a stores the input layer of the first neural network NN1 stored in the learning model storage unit 25d of the storage unit 25. , The first to fourth input values x1 to x4 based on the operation state signals generated by the monitoring sensors S26, S27, and S28 are input.

  In addition, the three-dimensional CAD data specifying unit 24a, in accordance with the first output value z1 output using the first neural network NN1, for example, outputs the first abnormality after the sixth monitoring sensor S26 emits “ON”. The time in seconds until the sensor S21 detects a temperature of 1000 ° C. or more and issues an abnormal signal is estimated. Then, the time in seconds that has elapsed since the sixth monitoring sensor S26 emits “ON” is subtracted, and the remaining seconds in units from the estimation time until the first abnormality sensor S21 issues an abnormality signal are subtracted. Calculate and estimate time.

  For example, it is estimated that the time from when the sixth monitoring sensor S26 emits “ON” to when the first abnormal sensor S21 issues an abnormal signal is 540 seconds, and it is already 300 seconds after the “ON” is also emitted. Has elapsed, the remaining time is estimated to be 240 seconds.

  Further, when it is estimated that the first abnormality sensor S21 emits an abnormal signal, the three-dimensional CAD data specifying unit 24a estimates the occurrence based on the abnormal signal and the network database NDB6 shown in FIG. An abnormal component P11 that causes an abnormal operation state that causes an abnormal signal is specified. Configurations other than those described above are common to the third embodiment.

  The three-dimensional model image generation unit 24b generates the abnormal part three-dimensional model image Ip based on the abnormal part CAD data Dp that is the three-dimensional CAD data for representing the abnormal part P specified in this way. Further, a normal part three-dimensional model image Ir based on the normal part CAD data Dr that is three-dimensional CAD data for representing a normal part, and an entire part based on the whole CAD data Dm that is three-dimensional CAD data for representing the entire mechanical device M. A three-dimensional model image Im can be generated. Further, it is possible to generate a composite three-dimensional model image Ii in which two or more three-dimensional model images are superimposed.

  FIG. 18 shows an abnormal part three-dimensional based on abnormal part CAD data Dp11, which is three-dimensional CAD data generated by the three-dimensional model image generation unit 24b and representing the abnormal part P11 related to the abnormal signal whose occurrence is estimated. 4 shows an image example of a model image Ip11. At this time, not only the abnormal part three-dimensional model image Ip11 is displayed as shown in FIG. 18 but also the normal part three-dimensional model image Ir, another abnormal part three-dimensional model image Ip, or the entire three-dimensional model image Im. A composite three-dimensional model image Ii may be represented.

  In the image example of FIG. 18, the abnormal component three-dimensional model image Ip11 is “240 seconds from now” on the remaining time until the first abnormal sensor S21 estimated by the three-dimensional CAD data specifying unit 24a issues an abnormal signal. An abnormal signal will occur later. "

  Further, the operator designates a three-dimensional area in a range corresponding to the slit in the direction of the center line C in the abnormal part P11, hides this slit-shaped three-dimensional area, and sets a tertiary area in a range other than the slit shape. By selecting to display the original region, a partially hidden three-dimensional model image that partially hides the three-dimensional region can be generated. Thereby, it is possible to easily observe the abnormal cause area which is not visible in the image example of FIG. 18, and to easily grasp the position and range occupied by the entire mechanical device Ma and the abnormal component P11.

  In this way, the remaining time until the occurrence of the abnormal signal is estimated and displayed together with the abnormal part three-dimensional model image Ip11 as shown in the image example of FIG. 18, so that the mechanical device Ma, the image generating device 22, or A company, an institution, or the like having the mechanical device Ma and the image generating device 22 can take a precautionary measure such as preparing a replacement part for the abnormal part P11.

  Further, the abnormal component three-dimensional model image Ip11 in which the occurrence of the abnormal signal is estimated is displayed so as to be superimposed on the normal component three-dimensional model image Ir, another abnormal component three-dimensional model image Ip, or the entire three-dimensional model image Im. That is, the three-dimensional position or range that needs to be repaired or replaced later can be grasped at an early stage.

  Further, the remaining time until the occurrence of the abnormal signal is estimated and displayed, so that the operator H lowers the driving speed of the driving device, interrupts the operation and turns off the main switch of the mechanical device M, and the like. In some cases, the occurrence can be avoided. Moreover, the operator H adjusts the operating state so that no abnormal signal is generated, investigates the cause of the abnormal signal from the history of the operating state information Sr and the abnormal operating state information Si, and prepares spare parts with a margin. Measures such as can be taken.

  Since the neural network NN is learned and stored for each operator H, the remaining time until the occurrence of an abnormal signal for a specific operator H can be more accurately determined without being affected by log data of different operators H. Can be estimated.

  When a company, an institution, or the like has a plurality of mechanical devices M of the same type, input values and output values x1 to x4, z1 of the mechanical devices Ma, Mb, Mc are also input to one neural network NN for learning. Therefore, more opportunities to correct the coupling coefficient w can be obtained.

  When each of the mechanical devices Ma to Mb and the image generating device 22 are located apart from each other as illustrated in FIG. 14B, each of the mechanical devices Ma to Mc is a company different from a company or an institution that owns the image generating device 22. It may be owned by an institution or the like.

  The radix of the mechanical device M included in the image generation / display system 21 is not limited to three, which is the radix shown in the example of the functional configuration diagram in FIG. 14, but may be one or two, and may be four or more. .

  Further, the number of operators H is not limited to two, which is the number shown in the example of the log database LDB in FIG. 16, and may be more or less than this. In the example of the log database LDB of FIG. 16, only the log data of the mechanical device Ma is input, but log data of the mechanical device M other than the mechanical device Ma may be input.

  Further, the three-dimensional CAD data specifying unit 24a estimates the remaining time to be 240 seconds according to the first output value z1, but does not limit the estimated time to one, and calculates the probabilities for a plurality of estimated values. May be shown. In this case, the three-dimensional model image generation unit 24b may generate an image including a display such as, for example, "the probability of occurrence of an abnormal signal after 240 seconds is 70%."

  Along with these displays, the alarm unit 26b may sound an alarm sound to draw the operator's attention.

  The image generation and display system 21 may have an external terminal device as shown in FIG. 13, and the operations, displays, alarms and the like described above may be performed by the terminal display processing means of the external terminal device.

  Although the embodiments of the present invention have been described above, the present invention is not limited to these embodiments, and various modifications can be made without departing from the spirit of the present invention.

  For example, the mechanical device M does not need to be a single mechanical device such as an industrial machine or a machine tool. If the mechanical device M includes a plurality of parts, it constitutes a building or a structure, or a building or a structure. May be a mechanical device attached to.

  Further, the abnormal sensor S does not need to be a sensor including an element for detecting a physical quantity such as temperature and pressure and an amount of change thereof, and if it generates an abnormal signal depending on an abnormal operation state, for example, a part or a part of the part may be used. A sensor for detecting loss may be used.

  The number of abnormal sensors S provided is not limited to the number exemplified in each embodiment, and may be larger or smaller than these. The same applies to the number of monitoring sensors S in the seventh embodiment.

  Further, it is not necessary for the alarm sections 6b, 16b, 26b or the terminal alarm section 19b to emit an alarm sound. For example, three-dimensional model images Ii, Im, Ip shown on the display surfaces 6a, 16a, 26a or the terminal display surface 19a. , Ir blinking, a color change, etc., to alert the operator. Also, a combination of these and an alarm sound may be used.

  INDUSTRIAL APPLICATION This invention can be used for the image generation apparatus which produces | generates a three-dimensional model image of an abnormal part.

1, 11, 21 Image generation and display system 2 Image generation device, 12 Image generation server device, 22 Image generation devices 3, 13, 23 Communication means 4, 14, 24 Processing means 5, 15, 25 Storage means 6, 16, 26 Display processing means 17 External terminal device 18 Terminal processing means 19 Terminal display processing means M, Ma to Mc Mechanical devices S, S01 to S15 Abnormal sensors S21, S22, S31, S32, S41, S42 Monitoring sensor (abnormal sensor)
S26 to S28, S36 to S38, S46 to S48 Monitoring sensors P, P01, P02, P11 Abnormal parts A, A011 to A022 Abnormal cause areas LDB, LDB1 Log database NDB, NDB1 to NDB6 Network database NN, NN1 Neural net Dp, Dp01 , Dp02 Abnormal part CAD data (3D CAD data)
Dr Normal part CAD data (3D CAD data)
Dm Whole CAD data (3D CAD data)
Ii Composite 3D model image (3D model image)
Ip, Ip01, Ip02, Ip11 Abnormal part 3D model image (3D model image)
Ir normal part 3D model image (3D model image)
Im Overall 3D model image (3D model image)
S100, S200 Image generation method S110, S210 Database storage step S120, S220 Abnormal signal receiving step S130, S230 Three-dimensional model image generation step (abnormal part three-dimensional model image generation step)
S140, S240 Three-dimensional model image display process

Claims (13)

A communication unit connected to a plurality of abnormality sensors disposed in a mechanical device including a plurality of components, a processing unit connected to the communication unit, and a storage unit connected to the processing device;
The storage means is configured to matrix a first relationship, which is a relationship between an abnormal signal generated by each of the abnormal sensors and one or a plurality of abnormal components that cause the abnormal operation state that causes the abnormal signal. A network database for storing the data, and a three-dimensional CAD database for storing the three-dimensional CAD data of each component,
When the communication unit receives the abnormal signal, the processing unit specifies abnormal component CAD data that is three-dimensional CAD data of the abnormal component related to the abnormal signal based on the matrix data, and An image generating apparatus for generating a three-dimensional model image of an abnormal part based on CAD data. The network database is a second relationship that is a relationship between the abnormal signal and an abnormal cause area that is one or a plurality of three-dimensional areas that cause an abnormal operation state of the abnormal component that causes the abnormal signal. Is stored by matrix data,
The processing unit generates the abnormal component three-dimensional model image in which the abnormal cause area and the normal area that is a three-dimensional area that is not the abnormal cause area among the abnormal parts are displayed in a distinguished manner. Item 2. The image generation device according to Item 1. Generating an abnormal part three-dimensional model image by selecting display or non-display of one or a plurality of three-dimensional regions whose ranges are arbitrarily specified among the respective parts based on the three-dimensional CAD data. The image generation device according to claim 1 or 2, wherein An image generation server comprising: a plurality of abnormality sensors provided in a mechanical device including a plurality of components; a communication unit connected to the plurality of abnormality sensors; a processing unit connected to the communication unit; and a storage unit connected to the processing device. An image generation and display system including a device and an external terminal device connected to the communication unit via a communication line, and including a terminal display processing unit,
The storage means is configured to matrix a first relationship, which is a relationship between an abnormal signal generated by each of the abnormal sensors and one or a plurality of abnormal components that cause the abnormal operation state that causes the abnormal signal. A network database for storing the data, and a three-dimensional CAD database for storing the three-dimensional CAD data of each component,
When the communication unit receives the abnormal signal, the processing unit specifies abnormal component CAD data that is three-dimensional CAD data of the abnormal component related to the abnormal signal based on the matrix data, and Generate an abnormal part 3D model image based on CAD data,
The image generation display system, wherein the terminal display processing means displays the abnormal component three-dimensional model image received by the external terminal device from the image generation server device. The network database is a second relationship that is a relationship between the abnormal signal and an abnormal cause area that is one or a plurality of three-dimensional areas that cause an abnormal operation state of the abnormal component that causes the abnormal signal. Is stored by matrix data,
The processing unit generates the abnormal component three-dimensional model image in which the abnormal cause area and the normal area that is a three-dimensional area that is not the abnormal cause area among the abnormal parts are displayed in a distinguished manner. Item 5. The image generation device according to Item 4. Generating an abnormal part three-dimensional model image by selecting display or non-display of one or a plurality of three-dimensional regions whose ranges are arbitrarily specified among the respective parts based on the three-dimensional CAD data. The image generation and display system according to claim 4 or 5, wherein The storage means included in the image generating device is configured to store an abnormal signal generated by a plurality of abnormal sensors provided in a mechanical device including a plurality of components and one or a plurality of the components that cause an abnormal operation state that causes the abnormal signal. A database storage step of storing a network database that stores a first relationship that is a relationship with a certain abnormal component by matrix data, and a three-dimensional CAD database that stores three-dimensional CAD data of each of the components;
A communication unit included in the image generation device, an abnormal signal receiving step of receiving the abnormal signal from the abnormal sensor,
A processing unit connected to the storage unit and the communication unit specifies abnormal component CAD data, which is three-dimensional CAD data of the abnormal component related to the abnormal signal, based on the matrix data. An abnormal part three-dimensional model image generating step of generating an abnormal part three-dimensional model image based on the abnormal part three-dimensional model image. The database storing step is a second relationship between the abnormal signal and an abnormal cause area that is one or a plurality of three-dimensional areas that cause an abnormal operation state that causes the abnormal signal among the abnormal parts. Storing a network database storing the relationships by matrix data,
The abnormal part three-dimensional model image generation step generates the abnormal part three-dimensional model image in which the abnormal cause area and the normal area that is a three-dimensional area other than the abnormal cause area among the abnormal parts are displayed in a distinguished manner. The method according to claim 7, comprising a step. A range specifying step of arbitrarily specifying a range of one or a plurality of three-dimensional regions among the parts; and a display / non-display selecting step of selecting display / non-display of the specified range. The image generation method according to claim 7. A mechanical device including a plurality of parts;
A plurality of monitoring sensors disposed on the mechanical device;
A communication unit connected to the monitoring sensor, a processing unit connected to the communication unit having artificial intelligence and a log database connected to the processing device and storing operation information of the machine device as log data along with time. An image generation device having a storage unit that performs
Each of the monitoring sensors emits an abnormal signal when detecting an abnormal operation state of the mechanical device,
The operation information is identification information of an operator who operates the mechanical device for each operation of operating the mechanical device, operating state information indicating the operating state of the mechanical device issued by each of the monitoring sensors, and the abnormal signal. Including abnormal operation status information,
The processing means learns the artificial intelligence, and estimates a remaining time until the occurrence of the abnormal signal based on a learning model obtained by the learning. An image generation and display system, which generates a three-dimensional model image of an abnormal part, which is a three-dimensional model image of the abnormal part that is generated. A mechanical device including a plurality of parts;
A plurality of monitoring sensors disposed on the mechanical device;
A communication unit connected to the monitoring sensor, a processing unit having a neural network learning unit that learns a multilayer neural network and connected to the communication unit, and a connection to the processing device, and operating information of the mechanical device. A log database that stores the log data together with the time, and an image generating apparatus having a storage unit that stores the neural network,
Each of the monitoring sensors emits an abnormal signal when detecting an abnormal operation state of the mechanical device,
The operation information is identification information of an operator who operates the mechanical device for each operation of operating the mechanical device, operating state information indicating the operating state of the mechanical device issued by each of the monitoring sensors, and the abnormal signal. Including abnormal operation status information,
The processing means estimates a remaining time until the occurrence of the abnormal signal based on the neural network, and outputs a three-dimensional model image of the abnormal part related to the abnormal signal whose occurrence is estimated. An image generation and display system for generating an original model image. A network configured to store, using matrix data, a first relationship that is a relationship between the abnormal signal and one or a plurality of abnormal components that cause the abnormal operation state that causes the abnormal signal; A database and a three-dimensional CAD database for storing three-dimensional CAD data of each of the parts,
The processing means specifies abnormal component CAD data that is three-dimensional CAD data of an abnormal component related to the abnormal signal whose occurrence is estimated based on the matrix data,
The image generation and display system according to claim 11, wherein the abnormal part three-dimensional model image is based on the abnormal part CAD data. The network database is a second relationship that is a relationship between the abnormal signal and an abnormal cause area that is one or a plurality of three-dimensional areas that cause an abnormal operation state of the abnormal component that causes the abnormal signal. Is stored by matrix data,
The processing unit generates the abnormal component three-dimensional model image in which the abnormal cause area and the normal area that is a three-dimensional area that is not the abnormal cause area among the abnormal parts are displayed in a distinguished manner. Item 13. The image generation and display system according to Item 12.

Images