Abnormality prediction device, abnormality prediction system, abnormality prediction method, and abnormality prediction program

Abstract

An abnormality prediction device (100) is provided with a deterioration prediction unit (120). When an object component provided to the object device is deteriorated at an object time point, and the object component at the object time point is set as an object deteriorated component. There is a difference between the relative position of the drive unit corresponding to the target degraded member with respect to the other member and the relative position of the drive unit corresponding to the target member with respect to the other member when the target member is not degraded. When an abnormality has occurred in the target device, it is estimated that the distance between the drive unit corresponding to the target member and the other member reaches an abnormal distance due to the further deterioration of the target deterioration member. A degradation prediction unit (120) predicts the point in time at which an abnormality occurs in the target device on the basis of a remaining distance, which is the difference between the distance between the drive unit corresponding to the target degraded member and the other member, and the abnormal distance.

Description

Technical Field

[0001] The present disclosure relates to an abnormality prediction device, an abnormality prediction system, an abnormality prediction method, and an abnormality prediction program. Background Art

[0002] Conventionally, maintenance personnel perform inspections related to wear of manufacturing equipment based on the shape of components. Although failure conditions can be accurately grasped by using the shape of components, it is difficult to accurately predict the failure time by using the shape of components.

[0003] Patent Document 1 discloses a technology that estimates the degradation state of a component by generating a model for estimating the degradation state of a component from actual operation data acquired from sensors provided in the component provided in a manufacturing device in a normal state, thereby reducing the amount of data collected in advance and estimating the degradation state of the component.

[0004] Prior art literature

[0005] Patent Literature

[0006] Patent Document 1: Japanese Patent Application Publication No. 2022-021202 Summary of the invention

[0007] Problem that the invention aims to solve

[0008] According to Patent Document 1, the degradation state of a component alone is the target, so there is a problem that an abnormality of the device cannot be predicted based on the position of the drive unit corresponding to the target component relative to other components that changes with degradation of the target component.

[0009] An object of the present disclosure is to predict abnormality of a device based on a position that changes with degradation of a target component, the position being a relative position of a driving unit corresponding to the target component with respect to other components.

[0010] Means used to solve problems

[0011] The abnormality prediction device of the present disclosure includes a degradation prediction unit. When a target component provided by a target device is degraded at a target time point and the target component at the target time point is set as a target degraded component, there is a difference between the relative position of a drive unit corresponding to the target degraded component with respect to other components and the relative position of the drive unit corresponding to the target component with respect to the other components when the target component is not degraded, and it is estimated that the distance between the drive unit corresponding to the target component and the other components will reach an abnormal distance due to further deterioration of the target degraded component, thereby causing an abnormality to occur in the target device. The degradation prediction unit predicts a time point when the abnormality will occur in the target device based on a remaining distance that is a difference between the distance between the drive unit corresponding to the target degraded component and the other components and the abnormal distance.

[0012] Effects of the Invention

[0013] According to the present disclosure, when it is estimated that the distance between the driving unit corresponding to the object component and other components will reach the abnormal distance due to further degradation of the object deterioration component, thereby causing an abnormality in the object device, the degradation prediction unit predicts the time point when the abnormality will occur in the object device based on the difference between the distance between the driving unit corresponding to the object deterioration component and other components and the abnormal distance, that is, the remaining distance. Here, the position of the driving unit corresponding to the object component is equivalent to the position that changes with the degradation of the object component. Therefore, according to the present disclosure, it is possible to predict the abnormality of the device based on the position that changes with the degradation of the object component, which is the relative position of the driving unit corresponding to the object component relative to other components. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 This is a diagram showing a configuration example of an abnormality prediction system 90 according to the first embodiment.

[0015] Figure 2 This is a diagram for explaining the processing of the abnormal part prediction unit 110 according to the first embodiment.

[0016] Figure 3 This is a diagram for explaining the processing of the degradation prediction unit 120 according to the first embodiment.

[0017] Figure 4 This is a diagram showing a hardware configuration example of the abnormality prediction device 100 according to the first embodiment.

[0018] Figure 5 This is a flowchart showing the operation of the abnormality part prediction unit 110 according to the first embodiment.

[0019] Figure 6 This is a flowchart showing the operation of the degradation prediction unit 120 according to the first embodiment.

[0020] Figure 7 This is a diagram showing a hardware configuration example of an abnormality prediction device 100 according to a modified example of the first embodiment.

[0021] Figure 8 This is a diagram showing a configuration example of an abnormality prediction system 90 according to the second embodiment.

[0022] Fig. 9 This is a diagram for explaining the processing of the component degradation prediction unit 130 according to the second embodiment.

[0023] Fig.10 This is a flowchart showing the operation of the component degradation prediction unit 130 according to the second embodiment. DETAILED DESCRIPTION

[0024] In the description of the embodiments and the accompanying drawings, the same reference numerals are used for the same elements and corresponding elements. The description of the elements marked with the same reference numerals is appropriately omitted or simplified. The arrows in the figures mainly show the flow of data or the process. In addition, the word "unit" can also be appropriately rewritten as "circuit", "process", "procedure", "processing" or "circuit".

[0025] Implementation method 1.

[0026] Hereinafter, this embodiment will be described in detail with reference to the drawings.

[0027] ***Structure description***

[0028] Figure 1 FIG. 9 shows a configuration example of an abnormality prediction system 90 according to the present embodiment. Figure 1 As shown, the abnormality prediction system 90 includes an abnormality prediction device 100 and a 3D (three-dimensional) scanner.

[0029] like Figure 1 As shown, the abnormality prediction device 100 includes an abnormality portion prediction unit 110 and a degradation prediction unit 120 .

[0030] The 3D scanner is an example of a device that measures the degree of degradation of each component included in the abnormality prediction device 100. The device that measures the degree of degradation of each component may be a sensor included in each component.

[0031] The abnormal part prediction unit 110 calculates the configuration of each component of the target device using the data representing the target degraded component, and simulates the target behavior as the behavior of the target device based on the calculated configuration. At this time, as a specific example, the abnormal part prediction unit 110 uses a 3D simulator. Here, it is assumed that the target component of the target device has degraded at the target time point, and the target component at the target time point is set as the target degraded component.

[0032] The abnormal part prediction unit 110 calculates the arrangement of each component included in the target device using data indicating the non-degraded target component, and simulates the behavior of the target device, that is, the reference behavior, based on the calculated arrangement.

[0033] When there is a difference between the object behavior and the reference behavior, the abnormal part prediction unit 110 estimates whether the distance between the driving unit corresponding to the object component and other components reaches an abnormal distance due to further degradation of the object deteriorated component, thereby causing an abnormality in the object device. Here, the driving unit corresponding to the object component may be the object component itself or a component that is driven in conjunction with the object component. The driving unit corresponding to the object component may be a degraded component or a non-degraded component. In addition, the driving unit corresponding to the object component may also be composed of multiple components.

[0034] The abnormal part prediction unit 110 calculates the remaining distance corresponding to the driving unit and other components corresponding to the target deteriorated component when it is estimated that the distance between the driving unit and other components corresponding to the target deteriorated component will reach the abnormal distance due to further deterioration of the target deteriorated component, thereby causing an abnormality to occur in the target device. The remaining distance is the difference between the distance between the driving unit and other components corresponding to the target deteriorated component and the abnormal distance, and is the remaining distance until an abnormality occurs in the device, and is the distance corresponding to the margin until an abnormality occurs in the device.

[0035] Specifically, the abnormal part prediction unit 110 uses the data corresponding to each component that has degraded to calculate the configuration of each component of the device, and simulates the behavior of the device based on the calculated configuration. The device is also called an object device, and as a specific example, it is a manufacturing device. As a specific example, the component is a gear, a bearing, or a shaft. The degradation of a component refers to a change in the component from an initial state, and as a specific example, it is a change in the shape of the component or a change in the position of the component. As a specific example, the change in the shape of the component is the wear of the component or the deformation of the component. As a specific example, the data corresponding to each component that has degraded is 3D CAD (Computer Aided Design) data representing each component that has degraded. As a specific example, the 3D CAD data representing each component is obtained by sensing each component or 3D scanning each component.

[0036] The abnormal part prediction unit 110 calculates the configuration of each component of the device between multiple time points, simulates the behavior of the device based on the calculated configuration, extracts the difference in the behavior of the device caused by the degradation of each component based on the simulated behavior, and estimates whether the extracted differences are related to the abnormality of the device. In addition, the abnormal part prediction unit 110 can extract the difference in the behavior of the device based only on the degradation of each component, or estimate whether the extracted differences are related to the abnormality of the device based on the design information of the device or the function of the device. The design information of the device and the function of the device are specific examples of the properties of the device. In addition, the abnormal part prediction unit 110 determines the abnormal parts corresponding to the extracted differences, and extracts the difference in physical distance at the determined abnormal parts. At this time, the abnormal part prediction unit 110 determines the parts that are related to the difference in physical distance at the determined abnormal parts. As a specific example, the determined abnormal part is a driving unit that causes an abnormality related to each extracted difference, or a region containing the driving unit. As a specific example, the difference in physical distance at the determined abnormal part is the difference between the physical distance between the drive unit and other components at the abnormal part in the reference configuration model and the physical distance between the drive unit and other components at the abnormal part in the object configuration model. Here, the reference configuration model is a model that represents the configuration of each component when each component is not degraded. The object configuration model is a model that represents the configuration of each component when each component is degraded. As a specific example, the abnormal part prediction unit 110 extracts the difference in distance between components at the determined part or the difference in position of the drive unit at the determined abnormal part as the difference in physical distance at the determined abnormal part. As a specific example, the abnormality of the device means that the behavior of the device is abnormal, or the device detects an abnormality in the device itself.

[0037] The abnormal part prediction unit 110 measures the remaining distance at the abnormal part corresponding to the difference of each behavior related to the abnormality of the device. At this time, as a specific example, the abnormal part prediction unit 110 uses a model representing the device to measure the remaining distance. In addition, as a specific example, the abnormal part prediction unit 110 measures the difference between the distance between the components at a certain time point and the abnormal distance as the remaining distance. Here, the abnormal distance is the distance between the components corresponding to the abnormality occurring in the device. In the case where the distance between the components is the abnormal distance, as a specific example, when the device is driven, the components collide with each other and the behavior of the device is abnormal. In addition, the abnormal part prediction unit 110 can also measure the distance from the position of the driving unit corresponding to the target component at a certain time point to the position corresponding to the position abnormality related to the driving unit corresponding to the target component as the remaining distance corresponding to the target component. At this time, the position abnormality related to the driving unit corresponding to the target component occurs because the relative position of the driving unit corresponding to the target component with respect to other components changes. In addition, the remaining distance may not be the distance in the path through which the component passes with the deformation of the component, but the distance in the shortest path connecting two locations.

[0038] Figure 2 2 is a diagram for explaining the processing of the abnormal part prediction unit 110. Figure 2 As shown, the abnormal part prediction unit 110 compares the behavior of the device corresponding to the data representing each component that has not been degraded and the behavior of the device corresponding to each component that has been degraded by simulation. Figure 2 In FIG. 1 , the behavior of the portion corresponding to the arrow changes, and the change in behavior is related to the abnormality of the device. As a specific example, when the gear G is worn, the force transmission method changes, thereby changing the behavior of the drive unit D1 and the drive unit D2.

[0039] exist Figure 2 In FIG. 1 , the deterioration of each component related to the abnormal part is shown by a balloon. Each component that has deteriorated corresponds to the target deteriorated component. Figure 2 In the embodiment, due to at least any one of the wear of the gear G, the wear of the shaft S, the bending of the shaft S, and the movement of the driving part D1, the relative position of the driving part D1 with respect to other parts changes, and the distance between the driving part D2 and the part P changes. Here, the driving part D1 is equivalent to the abnormal part. The area including the space between the driving part D2 and the part P is equivalent to the abnormal part. The driving part D1 is equivalent to the driving part corresponding to the shaft S, the driving part corresponding to the gear G, and the driving part corresponding to the driving part D2. The driving part D2 is equivalent to the driving part corresponding to the shaft S, and the driving part corresponding to the gear G. The gear G and the like are equivalent to other parts with respect to the driving part D1. The part P is equivalent to other parts with respect to the driving part D2.

[0040] When there is a difference between the relative position of the driving unit corresponding to the target deteriorated component with respect to other components and the relative position of the driving unit corresponding to the target component with respect to other components when the target component is not deteriorated, and it is estimated that the distance between the driving unit corresponding to the target component and other components will reach the abnormal distance due to further deterioration of the target deteriorated component, thereby causing an abnormality in the target device, the degradation prediction unit 120 predicts the time point when the abnormality occurs in the target device based on the remaining distance. The degradation prediction unit 120 may also estimate the replacement period of the target component based on the predicted time point when the abnormality occurs in the target device. The degradation prediction unit 120 may also predict the time point when the abnormality occurs in the target device based on the remaining distance and the operating time of the target device at the target time point.

[0041] As a specific example, the degradation prediction unit 120 uses data representing the remaining distance at multiple time points and information representing the number of operating days of the device to predict the abnormality occurrence date. The abnormality occurrence date is a specific example of the time point at which the abnormality occurs in the target device. As a specific example, the abnormality occurrence date is the date when the distance between the components in the degradation curve reaches the abnormal distance. The degradation curve is equivalent to a model generated using data representing the degradation of the target deteriorated component obtained at the target time point and data representing the degradation of the target component obtained at a time point before the target time point, and the model shows the change in the distance between the drive unit corresponding to the target component and other components in a time series. The degradation prediction unit 120 can also predict the time point at which the abnormality occurs in the target device based on the model. As a specific example, the degradation curve is a curve derived based on the operating time of the device and the degradation model of the component, and is a curve showing the time transition of the remaining distance. The degradation model is a model that shows the degradation of each component in a time series. The degradation model can be a normal model.

[0042] The degradation prediction unit 120 may also use AI (Artificial Intelligence) to predict the abnormality occurrence date. In this case, as a specific example, the inference model used by the degradation prediction unit 120 is a model obtained by learning using data obtained from a device of the same type as the target device or a component of the same type as the target component. In addition, as a specific example, the input to the AI ​​is data indicating the remaining distance, and the output of the AI ​​is a degradation curve.

[0043] Furthermore, the degradation prediction unit 120 calculates the replacement time of the degraded component based on the predicted abnormality occurrence date and presents the calculated replacement time to the user. In this case, the degradation prediction unit 120 may calculate the replacement time in consideration of the error in the predicted abnormality occurrence date.

[0044] Figure 3 This is a diagram for explaining the processing of the degradation prediction unit 120 .

[0045] First, the degradation prediction unit 120 predicts a degradation curve based on the results obtained by measuring the degradation degree of each component at a plurality of time points. Figure 3 The degradation curve shown is a curve showing the relationship between the number of days the device has been in operation and the distance between components. The distance between components corresponds to the remaining distance. In addition, the initial data is data corresponding to each component that has not degraded. In addition, there is a case where the distance between components decreases over time.

[0046] Next, the degradation prediction unit 120 calculates the date when the distance between components reaches a threshold value in consideration of the number of days the device is in operation. Here, the threshold value corresponds to the abnormal distance.

[0047] Figure 4 The following is a hardware configuration example of the abnormality prediction device 100 according to the present embodiment. The abnormality prediction device 100 is configured by a computer. The abnormality prediction device 100 may be configured by a plurality of computers.

[0048] As shown in the figure, the abnormality prediction device 100 is a computer including hardware such as a processor 11, a memory 12, an auxiliary storage device 13, an input / output interface 14, and a communication device 15. These hardware are connected via a signal line 19 as appropriate.

[0049] The processor 11 is an IC (Integrated Circuit) that performs calculation processing and controls hardware included in the computer. As a specific example, the processor 11 is a CPU (Central Processing Unit), a DSP (Digital Signal Processor), or a GPU (Graphics Processing Unit).

[0050] The abnormality prediction device 100 may include a plurality of processors instead of the processor 11. The plurality of processors share the role of the processor 11.

[0051] The memory 12 is typically a volatile storage device, and a specific example is a RAM (Random Access Memory). The memory 12 is also called a main storage device or a main memory. The data stored in the memory 12 is stored in the auxiliary storage device 13 as needed.

[0052] The auxiliary storage device 13 is typically a nonvolatile storage device, and specific examples thereof include ROM (Read Only Memory), HDD (Hard Disk Drive), or flash memory. Data stored in the auxiliary storage device 13 is loaded into the memory 12 as needed.

[0053] The memory 12 and the auxiliary storage device 13 may be integrally configured.

[0054] The input / output interface 14 is a port connected to an input device and an output device. As a specific example, the input / output interface 14 is a USB (Universal Serial Bus) terminal. As a specific example, the input device is a keyboard and a mouse. As a specific example, the output device is a display.

[0055] The communication device 15 is a receiver and a transmitter. As a specific example, the communication device 15 is a communication chip or a NIC (Network Interface Card).

[0056] When communicating with other devices, the components of the abnormality prediction device 100 may use the input / output interface 14 and the communication device 15 as appropriate.

[0057] The auxiliary storage device 13 stores an abnormality prediction program. The abnormality prediction program is a program that causes a computer to implement the functions of each unit of the abnormality prediction device 100. The abnormality prediction program is loaded into the memory 12 and executed by the processor 11. The functions of each unit of the abnormality prediction device 100 are implemented by software.

[0058] The data used when executing the abnormality prediction program and the data obtained by executing the abnormality prediction program are appropriately stored in the storage device. Each part of the abnormality prediction device 100 appropriately uses the storage device. As a specific example, the storage device is composed of at least one of the memory 12, the auxiliary storage device 13, the register in the processor 11, and the cache memory in the processor 11. In addition, the term "data" and the term "information" sometimes have equivalent meanings. The storage device can also be a device independent of the computer.

[0059] The functions of the memory 12 and the auxiliary storage device 13 may also be implemented by other storage devices.

[0060] The abnormality prediction program may also be recorded in a computer-readable nonvolatile recording medium. As a specific example, the nonvolatile recording medium is an optical disk or a flash memory. The abnormality prediction program may also be provided as a program product.

[0061] ***Action description***

[0062] The operation process of the abnormality prediction device 100 corresponds to the abnormality prediction method. In addition, the program that realizes the operation of the abnormality prediction device 100 corresponds to the abnormality prediction program.

[0063] Figure 5 is a flowchart showing an example of the operation of the abnormal part prediction unit 110. Figure 5 The operation of the abnormal part prediction unit 110 will be described.

[0064] (Step S101)

[0065] The abnormal part prediction unit 110 receives 3D CAD data representing each component of the device as input. Here, it is assumed that each component represented by the 3D CAD data has deteriorated.

[0066] (Step S102)

[0067] The abnormal part prediction unit 110 uses the received 3D CAD data to calculate the configuration of each component of the device, and simulates the behavior of the device based on the calculated configuration. At this time, the abnormal part prediction unit 110 can also use the 3D CAD data prepared in advance to represent each component that is not shown in the received 3D CAD data.

[0068] (Step S103)

[0069] The abnormal part prediction unit 110 determines whether there is a difference between the behavior of the device in simulation based on the arrangement of the components of the device calculated using the device design data and the behavior of the device simulated in step S102. Here, the device design data is 3D CAD data representing the components that have not degraded.

[0070] When there is a difference in the behavior of the device, the abnormal part prediction unit 110 proceeds to step S104. In other cases, the abnormal part prediction unit 110 proceeds to step S101.

[0071] (Step S104)

[0072] When the behavior difference determined in step S103 is related to the failure of the device, the abnormal part prediction unit 110 identifies the abnormal part corresponding to the behavior difference and measures the remaining distance at each identified abnormal part.

[0073] Figure 6 is a flowchart showing an example of the operation of the degradation prediction unit 120. Figure 6 The operation of the degradation prediction unit 120 will be described.

[0074] (Step S121)

[0075] The degradation prediction unit 120 predicts degradation of a component corresponding to each remaining distance based on each remaining distance measured by the abnormality prediction unit 110 and the number of operating days of the device at the time when the 3D data corresponding to each remaining distance is acquired.

[0076] (Step S122)

[0077] The degradation prediction unit 120 calculates the number of operating days of the device until abnormality occurs in the device based on the result predicted in step S121, calculates the replacement time of the component based on the calculated operating days, and presents the calculated replacement time of the component to the user.

[0078] **Description of the effects of Embodiment 1**

[0079] As described above, according to the present embodiment, it is possible to identify replacement parts and derive replacement timings for parts for a failure related to physical distance caused by degradation of multiple parts of a device without acquiring data related to abnormal states of the device in advance.

[0080] **Other structures**

[0081] <Variation 1>

[0082] Figure 7 A hardware configuration example of the abnormality prediction device 100 according to this modification is shown.

[0083] The abnormality prediction device 100 includes a processing circuit 18 instead of the processor 11 , the processor 11 and the memory 12 , the processor 11 and the auxiliary storage device 13 , or the processor 11 , the memory 12 , and the auxiliary storage device 13 .

[0084] The processing circuit 18 is hardware that realizes at least a part of each unit included in the abnormality prediction device 100 .

[0085] The processing circuit 18 may be dedicated hardware, or may be a processor that executes a program stored in the memory 12 .

[0086] When the processing circuit 18 is dedicated hardware, as a specific example, the processing circuit 18 is a single circuit, a complex circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a combination thereof.

[0087] The abnormality prediction device 100 may include a plurality of processing circuits instead of the processing circuit 18. The plurality of processing circuits share the role of the processing circuit 18.

[0088] In the abnormality prediction device 100 , part of the functions may be implemented by dedicated hardware, and the remaining functions may be implemented by software or firmware.

[0089] As a specific example, the processing circuit 18 is implemented by hardware, software, firmware, or a combination thereof.

[0090] The processor 11, the memory 12, the auxiliary storage device 13, and the processing circuit 18 are collectively referred to as a “processing circuit.” That is, the functions of each functional component of the abnormality prediction device 100 are realized by the processing circuit.

[0091] The abnormality prediction device 100 according to other embodiments may have the same structure as that of this modification.

[0092] Implementation method 2.

[0093] Hereinafter, the differences from the above-described embodiment will be mainly described with reference to the drawings.

[0094] ***Structure description***

[0095] Figure 8 The following is a configuration example of the abnormality prediction device 100 according to the present embodiment. The abnormality prediction device 100 further includes a component degradation prediction unit 130 .

[0096] The component degradation prediction unit 130 calculates the degree of improvement of the remaining distances corresponding to the target component and other components by replacing the degraded target component with the non-degraded target component as the influence degree corresponding to the target component. As a specific example, the component degradation prediction unit 130 estimates the degradation amount of the target component at the time point when the degradation prediction unit 120 predicts that the target device will have an abnormality, calculates the first remaining distance and the second remaining distance respectively, and calculates the influence degree corresponding to the target component based on the calculated first remaining distance and the second remaining distance. Here, the first remaining distance is the remaining distance corresponding to the drive unit and other components corresponding to the target component when the degradation amount of the target component is the estimated degradation amount. The second remaining distance is the remaining distance corresponding to the drive unit and other components corresponding to the target component when the target degraded component is replaced with the non-degraded target component. In the case where there are multiple degraded components that affect the remaining distance, the component degradation prediction unit 130 calculates the influence degrees corresponding to the multiple degraded components respectively, and calculates the priority related to component replacement for each of the multiple degraded components based on the calculated influence degrees.

[0097] A specific example of the processing performed by the component degradation prediction unit 130 will be described below.

[0098] First, the component degradation prediction unit 130 predicts the degradation amount of each component on the abnormality occurrence date predicted by the degradation prediction unit 120 based on the data corresponding to each degraded component.

[0099] Next, the component degradation prediction unit 130 generates data corresponding to each component on the abnormality occurrence date based on the predicted degradation amount of each component.

[0100] Next, the component degradation prediction unit 130 uses the generated data and the data indicating each non-degraded component to calculate the arrangement of each component of the device in each combination of the degraded component and the non-degraded component. That is, the component degradation prediction unit 130 calculates the arrangement of each component of the device when some components are replaced on the abnormality occurrence date.

[0101] Next, the component degradation prediction unit 130 predicts the impact of each component on the abnormality corresponding to the abnormality occurrence date based on the calculated configuration of each component, and estimates the priority related to the replacement of each component and the time to replace each component based on the predicted impact. The impact corresponding to a certain component is the degree to which the configuration of each component of the device is restored by replacing the certain component. As a specific example, the impact corresponding to a certain component is the remaining distance that is increased or decreased by replacing the certain component with a new one.

[0102] Fig. 9 This is a diagram for explaining the processing of the component degradation prediction unit 130 .

[0103] First, the component degradation prediction unit 130 calculates the degradation amount of each component on the abnormality occurrence date X predicted by the degradation prediction unit 120. Fig. 9 As a specific example, the degradation amount of component A on day X is represented as dA.

[0104] Next, the component degradation prediction unit 130 assumes that the target component is replaced on day X, calculates the arrangement of each component on day X based on the calculated degradation amount, and calculates the remaining distance on day X based on the calculated result. At this time, the component degradation prediction unit 130 typically calculates the arrangement of each component on day X using one component as the target component.

[0105] Next, the component degradation prediction unit 130 compares the remaining distances when each component is replaced on the Xth day based on the calculated arrangement, thereby calculating the influence degree corresponding to each component.

[0106] ***Action description***

[0107] Fig.10 2 is a flowchart showing an example of the operation of the component degradation prediction unit 130. Fig.10 The operation of the component degradation prediction unit 130 will be described.

[0108] (Step S201)

[0109] The component degradation prediction unit 130 uses the 3D CAD data indicating each component that has degraded at the target time point to predict the degradation amount of each component from the target time point to the abnormality occurrence date predicted by the degradation prediction unit 120 .

[0110] (Step S202)

[0111] The component degradation prediction unit 130 generates 3D CAD data representing each component on the abnormality occurrence date based on the predicted degradation amount of each component.

[0112] (Step S203)

[0113] The component degradation prediction unit 130 uses the 3D CAD data generated in step S202 and the 3D CAD data representing each non-degraded component to calculate the arrangement of each component included in the device in each combination of degraded and non-degraded components and measures the remaining distance in each combination.

[0114] (Step S204)

[0115] The component degradation prediction unit 130 predicts the influence of each component on the abnormality corresponding to the remaining distance measured in step S203 , estimates the priority order and replacement timing of each component for replacement, and presents the estimated result to the user.

[0116] **Description of the effects of the second embodiment**

[0117] As described above, according to the present embodiment, it is possible to predict an appropriate replacement time for each component, thereby avoiding a failure of the device and extending the life of the components.

[0118] ***Other implementation methods***

[0119] The above-described embodiments may be freely combined or arbitrary components of the embodiments may be modified, or arbitrary components may be omitted in the embodiments.

[0120] In addition, the embodiments are not limited to the contents described in Embodiments 1 and 2, and various changes can be made as needed. The process described using the flowcharts and the like can also be changed as appropriate.

[0121] Description of Reference Numerals

[0122] 11 processor, 12 memory, 13 auxiliary storage device, 14 input / output interface, 15 communication device, 18 processing circuit, 19 signal line, 90 abnormality prediction system, 100 abnormality prediction device, 110 abnormal part prediction unit, 120 degradation prediction unit, 130 component degradation prediction unit.

Claims

1. An abnormality prediction device, wherein: The abnormality prediction device includes a degradation prediction unit, When it is assumed that a target component included in the target device has deteriorated at a target time point, and the target component at the target time point is set as a target deteriorated component, When there is a difference between the relative position of the driving unit corresponding to the target degraded component with respect to other components and the relative position of the driving unit corresponding to the target component with respect to the other components when the target component is not degraded, and it is estimated that the distance between the driving unit corresponding to the target component and the other components will reach an abnormal distance due to further deterioration of the target degraded component, thereby causing an abnormality to occur in the target device, the degradation prediction unit predicts a time point when the abnormality will occur in the target device based on a remaining distance that is a difference between the distance between the driving unit corresponding to the target degraded component and the other components and the abnormal distance.

2. The abnormality prediction device according to claim 1, wherein: The degradation prediction unit predicts a time point at which an abnormality occurs in the target device based on a model that is generated using data indicating degradation of the target deteriorated component acquired at the target time point and data indicating degradation of the target component acquired at a time point before the target time point, and that shows changes in the distance between a drive unit corresponding to the target component and the other components in a time series.

3. The abnormality prediction device according to claim 1 or 2, wherein: The degradation prediction unit estimates a replacement timing of the target component based on a predicted time point of occurrence of an abnormality in the target device.

4. The abnormality prediction device according to any one of claims 1 to 3, wherein: The abnormality prediction device further comprises an abnormality part prediction unit. The abnormal location prediction unit calculates the configuration of each component of the target device using the data indicating the target deteriorated component, and simulates the target behavior, which is the behavior of the target device, based on the calculated configuration. The abnormal part prediction unit calculates the configuration of each component of the target device using the data indicating the target component that has not degraded, and simulates a reference behavior that is a behavior of the target device based on the calculated configuration. The abnormal part prediction unit estimates, based on the properties of the target device, whether the distance between the driving unit corresponding to the target component and the other components reaches the abnormal distance due to further deterioration of the target deteriorated component, thereby causing an abnormality to occur in the target device, when there is a difference between the target behavior and the reference behavior. The abnormal part prediction unit calculates a remaining distance corresponding to the drive unit corresponding to the target deteriorated component and the other component when it is estimated that the distance between the drive unit corresponding to the target deteriorated component and the other component will reach the abnormal distance due to further deterioration of the target deteriorated component, thereby causing an abnormality to occur in the target device.

5. The abnormality prediction device according to any one of claims 1 to 4, wherein: The abnormality prediction device further includes a component degradation prediction unit. The component degradation prediction unit calculates, as an influence degree corresponding to the target component, a degree of improvement of remaining distances corresponding to the drive unit and the other components corresponding to the target component by replacing the degraded target component with the non-degraded target component.

6. The abnormality prediction device according to claim 5, wherein: The degradation prediction unit predicts a time point at which an abnormality occurs in the target device based on the remaining distance and the operating time of the target device at the target time point. The component degradation prediction unit estimates the degradation amount of the target component at a time point when an abnormality is predicted to occur in the target device, calculates a remaining distance corresponding to the drive unit corresponding to the target component and the other components when the degradation amount of the target component is the estimated degradation amount as a first remaining distance, calculates a remaining distance corresponding to the drive unit corresponding to the target component and the other components when the target degraded component is replaced with the non-degraded target component as a second remaining distance, and calculates an influence degree corresponding to the target component based on the first remaining distance and the second remaining distance.

7. The abnormality prediction device according to claim 5 or 6, wherein: When there are a plurality of degraded components that affect the remaining distance, the component degradation prediction unit calculates influence degrees corresponding to the plurality of degraded components, respectively, and calculates priority levels related to component replacement for the plurality of degraded components based on the calculated influence degrees.

8. An abnormality prediction system, wherein: The abnormality prediction system comprises: The abnormality prediction device according to any one of claims 1 to 7; and A device for measuring the degree of degradation of the target component.

9. A method for predicting anomalies, wherein: When it is assumed that a target component included in the target device has deteriorated at a target time point, and the target component at the target time point is set as a target deteriorated component, When there is a difference between the relative position of the drive unit corresponding to the target deteriorated component with respect to other components and the relative position of the drive unit corresponding to the target component with respect to the other components when the target component is not deteriorated, and it is estimated that the distance between the drive unit corresponding to the target component and the other components will reach an abnormal distance due to further deterioration of the target deteriorated component, thereby causing an abnormality to occur in the target device, the computer predicts a time point when the abnormality will occur in the target device based on a remaining distance that is a difference between the distance between the drive unit corresponding to the target deteriorated component and the other components and the abnormal distance.

10. An abnormality prediction program, wherein: The abnormality prediction program causes an abnormality prediction device as a computer to execute degradation prediction processing. When it is assumed that a target component included in the target device has deteriorated at a target time point, and the target component at the target time point is set as a target deteriorated component, In the degradation prediction process, when there is a difference between the relative position of the drive unit corresponding to the target degraded component with respect to other components and the relative position of the drive unit corresponding to the target component with respect to the other components when the target component is not degraded, and it is estimated that the distance between the drive unit corresponding to the target component and the other components will reach an abnormal distance due to further degradation of the target degraded component, thereby causing an abnormality to occur in the target device, a time point when the abnormality will occur in the target device is predicted based on a remaining distance that is a difference between the distance between the drive unit corresponding to the target degraded component and the other components and the abnormal distance.

Images