Diagnostic device and program

Abstract

A diagnostic device (10) comprises a computation unit (11) that executes computations for managing an industrial machine (1). The computation unit: acquires first information (12A) which includes information relating to a plurality of drive units (6-n) constituting the industrial machine; analyzes, on the basis of the first information, one or more constituent elements (7-m) constituting each of the drive units; acquires, on the basis of the analysis results relating to the constituent elements, second information (12B) relating to the details of a failure occurring in the drive unit; calculates, on the basis of the second information, the degree of impact on the industrial machine imparted by a failure state in which a failure has occurred in the constituent element; calculates the ease-of-detection, which indicates the degree of ease when acquiring from the constituent element a detection value including a feature amount corresponding to the failure state of the constituent element; and calculates, on the basis of the degree of impact and the ease-of-detection, a priority indicating a priority order for acquiring the detection value.

Description

Diagnostic device and program

[0001] The present disclosure relates to a diagnostic device and a program for maintaining industrial machinery.

[0002] When industrial machinery such as machine tools breaks down, it can result in the generation of defective workpieces and a decrease in the availability rate of the production site. Therefore, it is desirable to adequately maintain industrial machinery to prevent the generation of defective workpieces and a decrease in the availability rate. Patent Document 1 proposes a technique for calculating a score of the failure impact of a managed object based on a database of failures of the managed object and presenting a failure mode of the managed object based on the score. Patent Document 2 proposes a technique for calculating the probability of breakage or the degree of damage of a managed object based on detected values. Patent Document 3 proposes a technique for constructing a model formula that shows the transition of a failure risk index according to a statistical distribution and statistically estimating the parameter values ​​of the model formula as an estimated value of the failure risk index.

[0003] JP 2023-45842 A JP 2023-167775 A International Publication No. 2018 / 105104

[0004] To maintain industrial machinery, it is desirable to efficiently acquire detected values. However, acquiring all detected values ​​from all drive sources of industrial machinery may result in unnecessary detected values ​​that are of little use for maintenance. Unlike pump equipment that operates continuously at rated speed, industrial machinery undergoes aperiodic stops and starts. To ensure the usefulness of industrial machinery as a measurement technology, it is desirable to be able to sufficiently aggregate detected values ​​that are meaningful for maintenance. Furthermore, when installing devices or measuring instruments to obtain detected values, industrial machinery often has structural constraints that make it impossible to install measuring instruments, making it virtually impossible to acquire detected values. Conventional technologies implicitly assume that measurements can be taken from industrial machinery without any constraints and that all detected values ​​are meaningful. Conventional technologies have not proposed a way to efficiently acquire detected values ​​that are useful for maintenance in the actual operation of industrial machinery.

[0005] The present disclosure aims to provide a diagnostic device and program that assists in efficiently acquiring detection values ​​from industrial machinery that is actually in operation. The present disclosure also solves the problem of ensuring the validity of detection values, which has been a problem in conventional technology, by automatically determining the drive units to be measured in the industrial machinery and the measurement time period based on the impact of a failure.

[0006] One aspect of the present disclosure is a diagnostic device that includes a calculation unit that performs calculations for managing industrial machinery, wherein the calculation unit acquires first information including information about a plurality of drive units that constitute the industrial machinery, analyzes one or more components that constitute each of the drive units based on the first information, acquires second information regarding a failure type that occurs in the drive unit based on the analysis results of the components, calculates the degree of impact on the industrial machinery of a failure state in which a failure has occurred in the component based on the second information, calculates a detectability that indicates the degree of ease of acquiring detection values ​​from the component when the industrial machinery is operating, and calculates a priority that indicates the order of precedence for acquiring the detection values ​​based on the impact and the detectability.

[0007] 1 is a block diagram showing the configuration of a diagnostic device according to an embodiment. FIG. 2 is a diagram showing an example of a data set stored in a storage unit. FIG. 3 is a diagram showing an example of a display image for executing a maintenance plan for an industrial machine. FIG. 4 is a diagram showing an example of a display image showing an analysis result of components of an industrial machine. FIG. 5 is a diagram showing an example of a display image showing a calculation result of priority. FIG. 6 is a diagram showing an example of a display image showing a schedule for acquiring detected values. FIG. 7 is a diagram showing an example of a display image showing an acquisition status of detected values. FIG. 8 is a diagram showing an example of a display image showing an updated schedule. FIG. 9 is a diagram showing an example of a display image for inputting a first question. FIG. 10 is a diagram showing an example of a display image showing a first answer. FIG. 11 is a diagram showing an example of a display image for inputting a second question. FIG. 12 is a diagram showing an example of a display image showing a second answer. FIG. 13 is a flowchart showing the processing flow of a diagnostic method executed in a diagnostic device.

[0008] As shown in FIG. 1 , the diagnostic system S is composed of an industrial machine 1 and a diagnostic device 10, which are interconnected via a network W. The industrial machine 1 is managed by the diagnostic device 10 via the network W. The diagnostic device 10 executes various calculations for managing the industrial machine 1. The managed industrial machine 1 is, for example, a machine tool that processes a workpiece (a workpiece) made of a metal material or the like into a desired shape. The industrial machine 1 is not limited to a machine tool, but may also be a device related to production facilities, such as a robot device that performs a predetermined task, a manufacturing device that manufactures an item, or a transport device that transports an item.

[0009] The industrial machine 1 includes a plurality of drive units 6-n (n is any natural number) that operate to process a workpiece. Each drive unit 6-n is configured to perform a predetermined operation, such as cutting, milling, drilling, moving, or cleaning. Each drive unit 6-n includes a plurality of components 7-m (m is any natural number) that realize a predetermined operation, such as rotation or sliding. Each component 7-m includes, for example, a motor or hydraulic power source, a mechanical configuration that performs an operation, or the like. The industrial machine 1 includes, for example, a control device 2 that controls the operation of the plurality of drive units 6-n.

[0010] The control device 2 is equipped with a control unit 3 for individually controlling the multiple drive units 6-n. The control unit 3 causes each drive unit 6-n to perform a predetermined operation in order to perform a predetermined process on the workpiece. The control unit 3 is configured with a processor such as a CPU (Central Processing Unit). The control unit 3 is configured to not only execute control, but also to execute predetermined control for detecting detection values ​​from the multiple drive units 6-n and calculations for managing the multiple drive units 6-n.

[0011] The control device 2 includes a storage unit 4 that stores data and programs necessary for control of machining. The storage unit 4 is configured with a non-transitory storage medium such as a hard disk drive (HDD) or a flash memory. The storage unit 4 may be configured with a storage device externally connected to the control device 2. The storage unit 4 may be configured with a server device that is connected via a network W and is capable of storing data.

[0012] The control device 2 includes a detection unit 8 that outputs detection values ​​detected by the multiple drive units 6-n. The detection unit 8 is configured with sensors corresponding to the type of each drive unit 6-n and control circuits associated with the sensors. The detection unit 8 detects, for example, vibration (acceleration), temperature, pressure, current, voltage, signals, etc. using sensors, converts the detected values ​​into signals using a control circuit, and outputs the signals. The detection unit 8 may be configured with a camera and output an image as the detection value. The image may be a captured image or a thermographic image showing temperature distribution. The detection values ​​are stored in, for example, the memory unit 4. The data set of detection values ​​stored in the memory unit 4 may be updated at predetermined times. The detection unit 8 may be configured to be externally connected to the industrial machine 1. The detection unit 8 may be configured as a device that is retrofitted to each drive unit 6-n that is not equipped with sensors.

[0013] The control device 2 includes a communication unit 5 that can be communicatively connected to the network W. The communication unit 5 is a communication interface that communicatively connects to the network W wirelessly or via a wire. With the above configuration, the control unit 3 generates operation information related to the operating state of the industrial machine 1 based on a data set of detection values ​​stored in the storage unit 4 at a predetermined timing. The control unit 3 outputs the operation information to the diagnostic device 10 via the network W based on an instruction from the diagnostic device 10.

[0014] The diagnostic device 10 is configured by an information processing terminal device such as a personal computer, a tablet terminal device, a smartphone, etc. The diagnostic device 10 includes a calculation unit 11 that executes calculations related to the maintenance of the industrial machine 1 based on information acquired from the industrial machine 1 via a network W. The calculation unit 11 is configured by a processor such as a CPU. The details of the calculations performed by the calculation unit 11 will be described later.

[0015] The diagnostic device 10 includes a storage unit 12 that stores data and programs required for calculations. The storage unit 12 is configured with a non-transitory storage medium such as a hard disk drive or a flash memory. The storage unit 12 may be configured with a storage device that is externally connected to the diagnostic device 10. The storage unit 12 may be configured with a server device that is connected via a network W and is capable of storing data. The storage unit 12 stores various data sets required for management and maintenance of the industrial machine 1, as described below. The diagnostic device 10 includes an input unit 13 that accepts input operations from a user. The input unit 13 is configured with, for example, a keyboard or a touch panel. The input unit 13 may also include a camera or a speaker.

[0016] The diagnostic device 10 includes a display unit 14 for displaying display content and calculation results for accepting user input operations. The display unit 14 is configured as a display device such as a liquid crystal display or an organic EL (Electro-Luminescence) display. The display unit 14 may be configured as an output unit provided with a speaker for audio output. The display unit 14 may be configured as a touch panel. If the display unit 14 is configured as a touch panel, it may be configured as the input unit 13 by displaying an image for accepting input operations. The input unit 13 and the display unit 14 may be configured integrally with the diagnostic device 10 or may be configured as a separate information processing terminal device. The display unit 14 may be configured as an input / output unit that integrates not only image display but also audio input / output and the input unit 13. The diagnostic device 10 includes a communication unit 15 that can be communicatively connected to the network W. The communication unit 15 is a communication interface that communicatively connects to the network W wirelessly or via a wired connection. The communication unit 15 may be communicatively connected to the industrial machine 1 wirelessly or via a wire without going through the network W. The diagnostic device 10 is communicatively connected to the network W via the communication unit 15 and communicates with the industrial machine 1.

[0017] The following describes the details of the process related to the diagnostic method for maintaining the industrial machine 1, which is executed by the diagnostic device 10.

[0018] As shown in FIG. 2 , the storage unit 12 stores device data 12A (first information) related to the device configuration of the industrial machine 1. The device data 12A is a data set including data necessary for analyzing the device configuration of the industrial machine 1. The device data 12A includes, for example, drive information related to multiple drive units 6-n provided in the industrial machine 1. The drive information includes configuration information related to multiple components 7-m that make up each drive unit 6-n. The configuration information includes device information related to the motors and hydraulic power sources included in each component 7-m, as well as the mechanical configuration. The device information includes, for example, the type of power source and the details of the mechanical configuration. The device information may also include information such as the repair history and replacement history of the power source and the mechanical configuration. The device information includes information related to the detection unit 8 provided in the power source and information related to the detection unit 8 provided in the mechanical configuration. If the power source or the mechanical configuration does not include a detection unit 8, the device information may also include information on how to acquire detection values ​​from the power source or the mechanical configuration.

[0019] The memory unit 12 stores failure data 12B (second information) related to the details of a failure that occurs in the drive unit 6-n of the industrial machine 1. The failure data 12B is a data set including data necessary for analyzing the details of a failure that may occur in the industrial machine 1. The failure data 12B includes data related to failure modes that may occur in each drive unit 6-n and the details of a failure that occurs in each component 7-m in the failure mode. The data related to the details of the failure includes, for example, specific data of detected values ​​including feature quantities corresponding to the failure mode. The detected values ​​including feature quantities corresponding to the failure mode may include, for example, data on vibration, temperature, pressure, current, voltage, signal, etc. The data related to the details of the failure may include the details of the failure and set values ​​such as threshold values ​​for the detected values.

[0020] The storage unit 12 stores operation data 12C (third information) related to the operation period of the industrial machine 1 and the processing content of the industrial machine. The operation data 12C is a data set including data related to the past operation record and future operation schedule of the industrial machine 1. The operation data 12C includes, for example, data related to the date and time, operation duration, and work content when the industrial machine 1 actually operated, and data related to the date and time, operation duration, and work content when the industrial machine 1 will operate in the future.

[0021] 3 shows a display image M1 related to the maintenance of the industrial machine 1, which is displayed on the display unit 14. The user operates the diagnostic device 10 to obtain a maintenance plan for the industrial machine 1, inputs the identification number of the industrial machine 1, and causes the display unit 14 to display the display image M1. The display image M1 shows, for example, an input field for inputting the identification number for identifying the industrial machine 1, as well as operation buttons for inputting a two-dimensional code assigned to the industrial machine 1. The calculation unit 11 generates information for identifying the industrial machine 1 in the display image M1 based on the input information of the identification number of the industrial machine 1, and displays the information on the display unit 14. The user performs an input operation based on the display image M1, causing the diagnostic device 10 to calculate a maintenance plan for the industrial machine 1.

[0022] The calculation unit 11 starts processing to generate a schedule for acquiring detection values ​​from the industrial machine 1 based on an input operation by the user. The calculation unit 11 searches the storage unit 12 and acquires device data 12A including information about multiple drive units that constitute the industrial machine. The calculation unit 11 analyzes one or more components 7-m that constitute each drive unit 6-n based on the device data 12A (first information). The calculation unit 11 generates a display image M2 that shows the analysis results of each drive unit 6-n and component 7-m that constitute the industrial machine 1, and displays the display image M2 on the display unit 14.

[0023] FIG. 4 shows an example of a display image M2 generated by the calculation unit 11. The display image M2 displays, for example, analysis results for the components 7-m, such as the motors, hydraulic power sources, and mechanical components that make up each drive unit 6-n. Based on the analysis results for the components 7-m, the calculation unit 11 acquires failure data 12B (second information) related to the nature of failures that may occur in the drive unit 6-n. The calculation unit 11 calculates the impact of failure modes that may occur in the industrial machine 1, for example, based on an analysis method using Failure Mode and Effects Analysis (FMEA). The failure data 12B includes failure modes that may occur in the drive unit 6-n. Examples of failure modes include component wear (flaking, cracking, chipping, etc.), loose assembly, and imbalance. For each failure, the severity (the degree to which it leads to a functional breakdown), ease of detection, and frequency of occurrence are set in stages. The failure data 12B also includes the causes and countermeasures for each failure mode. The calculation unit 11 associates each component 7-m with a failure mode based on the failure data 12B, and calculates the degree of impact that a failure state in which a failure has occurred in the component 7-m will have on the industrial machine 1. For example, the calculation unit 11 calculates the degree of impact so that it is higher the closer the state is to a state in which the industrial machine 1 stops operating. For example, the calculation unit 11 calculates the degree of impact so that it is lower the closer the state is to a state in which the industrial machine 1 operates normally. The calculation unit 11 may use any calculation method as long as it is possible to calculate the degree of impact.

[0024] The calculation unit 11 calculates a detectability indicating the degree of ease in acquiring a detection value including a feature quantity corresponding to a fault state of the component 7-m from the component 7-m. In this embodiment, the calculation unit 11 calculates the detectability based on the association between the fault state and the vibration data. For example, the calculation unit 11 performs an FFT (Fast Fourier Transform) analysis using the vibration data included in the detection value acquired in the fault state to calculate a vibration spectrum. The calculation unit calculates the detectability based on the association between the vibration spectrum and the driver 6-n.

[0025] The following are specific examples illustrating the relationship between fault conditions and feature quantities contained in vibration data. If component 7-m is a linear guide, it repeatedly moves under load, resulting in continuous, repeated stress acting on the sliding surfaces of the linear guide rail and the rolling surfaces and rolling elements of the ball screw. As a result, damage known as flaking occurs on the material surfaces of the rolling surfaces and rolling elements. When flaking occurs, a feature indicating an increase in torque average appears. If component 7-m contains a rotating shaft and an imbalance occurs due to a mass imbalance in the shaft of the rotating shaft, the first-order component of the vibration data increases. If component 7-m contains a rotating shaft and misalignment occurs due to a misalignment of the joint that affects rotation, the second-order, third-order, and fourth-order components of the vibration data increase. If component 7-m contains a rotating shaft and wear progresses on the bearing raceway, the sidebands of the first-order component of the vibration data increase.

[0026] The calculation unit 11 calculates the detectability based on the vibration spectrum corresponding to the feature quantity that appears in a faulty state and the correlation with the drive unit 6-n. The calculation unit 11, for example, scores the detectability of each feature quantity. An example of the correspondence between each feature quantity and the score is shown by the following formula (1): (1st order component, 2nd order component, 3rd order component, 4th order component, 1 / 2nd order component, torque average, sideband) = (10, 8, 6, 4, 2, 10, 8) (1)

[0027] The calculation unit 11 assigns a weight to each score according to the content of the feature amount. For example, if the component 7-m is a main shaft, the torque average hardly changes, so the weight for the torque average is set low. The weight may be adjusted appropriately based on the past performance of detected values. An example of the weight value is shown in the following formula (2): (1, 1, 1, 1, 1, 0.1, 1) (2) The calculation unit 11 assigns a weight to each score and calculates the detectability shown in formula (3). Detectability=(10, 8, 6, 4, 2, 1, 8) (3)

[0028] The calculation unit 11 multiplies the influence degree by the detectability degree to calculate a priority indicating the order of precedence for obtaining detection values ​​from the drive units 6-n. If there is a drive unit 6-n with a priority of 0, the calculation unit 11 may exclude the corresponding drive unit 6-n from detection targets. The calculation unit 11 generates a display image indicating the relationship between the priority and the drive units 6-n, and displays it on the display unit 14. By performing the above process, a user who is not knowledgeable about the industrial machine 1 can select a drive unit 6-n from which to obtain detection values ​​from among multiple drive units 6-n. The calculation unit 11 may use any calculation method as long as it is capable of calculating the priority.

[0029] FIG. 5 shows an example of a display image M3 showing the relationship between priority and driver 6-n. The calculation unit 11 indicates the relationship between priority and driver 6-n in the display image M3, generates evaluation content related to acquiring detected values ​​from the driver 6-n, and displays the evaluation content on the display unit 14. The calculation unit 11 generates a schedule for acquiring detected values ​​from the driver 6-n based on the calculated priority. The calculation unit 11 acquires operation data 12C (third information) related to the operating period during which the industrial machine 1 operates and the processing content of the industrial machine 1. The calculation unit 11 extracts driver 6-n in descending order of priority based on the third information, and extracts the future operating period during which the corresponding driver 6-n will be operating. The calculation unit 11 may also extract the future operating period during which the corresponding driver 6-n will be operating by referring to the past operating history of the driver 6-n. The calculation unit 11 generates a schedule for acquiring detected values ​​from the driver 6-n during the operating period.

[0030] 6, the calculation unit 11 generates a display image M4 indicating a schedule for acquiring detection values ​​from the drive units 6-n based on the priority, and displays the display image M4 on the display unit 14. The user checks the schedule for acquiring detection values ​​based on the display image M4 displayed on the display unit 14. The user inputs an operation to acquire detection values ​​based on the display image M4. When the user performs an input operation, the calculation unit 11 executes a process for acquiring detection values ​​output from the detection unit 8 according to the schedule. The calculation unit 11 acquires detection values ​​from the drive units 6-n according to the schedule during a predetermined period while the industrial machine 1 is operating, and calculates the acquisition status of the detection values.

[0031] As shown in Figure 7, the calculation unit 11, for example, calculates the number of detection values ​​detected from the drive unit 6-n, calculates the acquisition rate (%) of the current detection values ​​relative to the target number of detection values ​​to be acquired, generates a display image M5, and displays it on the display unit 14.

[0032] As shown in FIG. 8 , the calculation unit 11 generates a display image M6 with an updated schedule based on the acquisition status and priority of the detection values ​​acquired based on the schedule, and displays the updated schedule on the display unit 14. For example, the calculation unit 11 subtracts the current number of detection values ​​from the target number of detection values ​​to be acquired to calculate the number of remaining detection values ​​to be acquired. The calculation unit 11 readjusts the schedule based on the priority and the number of remaining detection values ​​to be acquired, and generates the display image M6. By performing the above process, it is possible to avoid a situation in which the number of detection values ​​differs from the target value after the process of acquiring detection values ​​is performed. By performing the above process, the user can reliably acquire detection values ​​even if they do not know the operating status of the industrial machine 1.

[0033] The calculation unit 11 may generate an answer based on a question entered by a user. The following description uses an example of two exchanges of questions in natural language. However, the total number of questions may be one or more than two, and there is no restriction. The calculation unit 11 may generate the question and answer in other formats, such as images or audio, in addition to natural language. The calculation unit 11 is configured to perform machine learning using deep learning or other methods based on training data in advance and output the answer to the question. The calculation unit 11 may generate an answer to the question based on text, for example, using Retrieval Augmented Generation (RAG). The calculation unit acquires fourth information related to the question entered by the user based on a sentence. The calculation unit 11 extracts the component 7-m included in the fourth information. The calculation unit 11 searches the equipment data 12A (first information) and the fault data 12B (second information) of the industrial machine 1 and performs a calculation related to the component 7-m based on the first information and the second information. The calculation unit 11 generates an answer to the question based on the calculation result, and outputs the answer to the display unit 14 .

[0034] As shown in FIG. 9 , the user inputs a first question related to a maintenance plan for the industrial machine 1 from the input unit 13 based on the display image M7. If the user's first question is, for example, "Which should be measured, the X-axis or the Y-axis?", the calculation unit 11 extracts the X-axis and Y-axis, which are the component 7-m, from the first question. Based on the first question, the calculation unit 11 recognizes the purpose of acquiring the detected values ​​of the X-axis and the Y-axis. Based on the device data 12A (first information) and the fault data 12B (second information), the calculation unit 11 calculates simplified information including the priority for acquiring the detected values ​​and a schedule for acquiring the detected values. For example, the calculation unit 11 generates simplified information based on the following content in response to the question: "Configuration information: axis information (X-axis = large feed axis stroke, Y-axis = medium feed axis stroke, U-axis = rotary axis) FMEA information: impact of feed axis damage is large, rotary axis failures are rare Detectability: X-axis -> large, Y-axis -> medium, U-axis not possible Schedule information: since only one axis can be monitored at a time, if you wish to monitor multiple axes this can be achieved by setting staggered time periods. Operating hours: 9:00 to 17:00" The calculation unit 11 uses a template that corresponds to the calculation results of the simplified information to generate a first answer content based on text.

[0035] As shown in FIG. 10 , the calculation unit 11 generates a display image M8 showing a first answer based on natural language in response to the first question, and displays the display image M8 on the display unit 14. The calculation unit 11 generates a first answer to the first question, including a method for acquiring a detection value from the component 7-m, and displays the first answer on the display unit 14. The first answer allows a user, even an unskilled user, to select which axis to measure without having to examine the detailed configuration of the machine. By using the first answer, the user can explain to the manager why they selected the axis to be measured. By accumulating knowledge based on the content of the first answer, the user can deepen their understanding of the industrial machine 1.

[0036] If a question arises about the first answer, the user may input a new second question about the first answer from the input unit 13 based on the display image M9. The calculation unit 11 acquires fifth information about the new second question about the first answer. The calculation unit 11 extracts the component 7-m related to the fifth information and searches the equipment data 12A (first information) and the failure data 12B (second information) of the industrial machine 1. The calculation unit 11 performs a calculation related to the component 7-m based on the equipment data 12A (first information) and the failure data 12B (second information). The calculation unit 11 generates a second answer by updating the first answer to the second question based on the calculation result. The calculation unit 11 outputs the second answer to the output unit.

[0037] As shown in FIG. 10 , the user inputs a second question in response to the first answer from the input unit 13 based on the display image M9. For example, if the user's second question is, "Which axis should I measure, the X-axis or the Y-axis?", the calculation unit 11 extracts the X-axis and Y-axis, which are components 7-m, from the second question. The calculation unit 11 re-identifies the purpose of acquiring the detected values ​​of the X-axis and Y-axis based on the second question. If the purpose of acquiring the detected values ​​of the X-axis and Y-axis based on the second question is such that simplified information for the first question is available, the calculation unit 11 uses a template corresponding to the calculation result of the simplified information to generate a second answer by updating the first answer based on the text. If the purpose of acquiring the detected values ​​of the X-axis and Y-axis based on the second question is such that simplified information for the first question is unavailable, the calculation unit 11 calculates new simplified information including the priority of acquiring the detected values ​​and a schedule for acquiring the detected values ​​based on the device data 12A (first information) and the fault data 12B (second information). The calculation unit 11 uses a template corresponding to the calculation result of the new simplified information to generate a second answer to the second question based on the text.

[0038] The calculation unit 11 may acquire an additional question and / or an additional command input at least once by the user in response to the question and the answer, and generate a new answer. The calculation unit 11 extracts a component 7-m related to the additional question and / or the additional command, and searches for first information and second information of the industrial machine 1. The calculation unit 11 executes a calculation related to the component 7-m based on the first information and the second information. The calculation unit 11 generates a new answer to the additional question and / or the additional command based on the calculation result. The calculation unit 11 outputs the generated new response to the output unit.

[0039] The calculation unit 11 may generate the answer content based on a conversation with the user. The calculation unit 11 may output the answer content not only as text but also as voice. The process of generating the answer content may be executed not only by an AI (Artificial Intelligence) device using Large Language Models (LLM) incorporated in the diagnostic device 10, but also by a server device connected to the network W.

[0040] As shown in FIG. 12 , the calculation unit generates a display image M10 showing a second answer based on natural language in response to the second question, and displays it on the display unit 14. Even if the user has questions about the first answer, the second answer adds information to the first answer, enabling suggestions tailored to the user's purpose. To aid the user's understanding, the calculation unit 11 may generate images, videos, and audio in addition to answer text in natural language. The calculation unit 11 may generate the second answer by quoting a reference page in the equipment's manual. The user may provide one or more additional questions or commands in response to the answer. While the present embodiment illustrates a total of two commands, the user may provide one or more additional commands, such as "summarize the answer in a table," "rewrite the program," or "illustrate the answer." The calculation unit 11 may generate new answers in response to additional inputs or commands to meet the user's needs.

[0041] 13 shows the flow of processing of a diagnostic method executed in the diagnostic device 10. The diagnostic method is executed based on a computer program installed on a computer mounted on the diagnostic device 10, which executes calculations for managing the industrial machine 1. The computer program causes a calculation unit 11 (processor) of the diagnostic device 10 to execute the following processing. The calculation unit 11 acquires device data 12A (first information) including information about a plurality of drive units 6-n that constitute the industrial machine 1 (S100). The calculation unit 11 analyzes one or more components 7-m that constitute each drive unit 6-n based on the device data 12A (first information) (S102). The calculation unit 11 acquires fault data 12B (second information) related to the details of a fault that occurs in the drive unit 6-n based on the analysis results of the components 7-m (S104).

[0042] The calculation unit 11 calculates the degree of impact on the industrial machine 1 of the failure state in which a failure has occurred in the component 7-m, based on the failure data 12B (second information) (S106). The calculation unit 11 calculates a detectability indicating the degree of ease in acquiring, from the component, a detection value including a feature quantity corresponding to the failure state of the component 7-m (S108). The calculation unit 11 calculates a priority indicating the order of priority for acquiring the detection value, based on the impact and the detectability (S110). The calculation unit 11 acquires operation data 12C (third information) related to the operating period during which the industrial machine 1 operates and the processing details of the industrial machine 1 (S112). The calculation unit 11 generates a schedule for acquiring the detection value, based on the operation data 12C (third information) and the priority (S114).

[0043] As described above, the diagnostic device 10 can generate a schedule for acquiring detected values ​​used to maintain the industrial machine 1. By calculating the priority, the diagnostic device 10 can indicate to the user which of the multiple drive units 6-n should acquire detected values ​​from, without requiring the user's knowledge of the industrial machine 1. The diagnostic device 10 can automatically generate answers to questions entered by the user and present the answers to the user. The diagnostic device 10 can perform interactive question and answer sessions based on natural language.

[0044] [Modifications] In the above-described embodiment, the calculation unit 11 is configured to calculate the detectability based on vibration data. The calculation unit 11 may use any data that can determine the feature quantities related to the failure of the component 7-m based on detected values ​​such as not only vibration data but also temperature, pressure (stress), current, voltage, flow rate, pressure, and velocity of the working fluid, and signals. The calculation unit 11 may determine the feature quantities related to the failure of the component 7-m based on image data captured by a camera. The calculation unit 11 may determine the feature quantities related to the failure of the component 7-m based on video captured by a camera showing the component 7-m in operation. The calculation unit 11 may search the repair and replacement history of the component 7-m of the industrial machine 1 based on the identification number of the industrial machine 1, and adjust the weighting of the feature quantities based on the repair and replacement history of the component 7-m. If the drive unit 6-n does not have a detection unit 8, the calculation unit 11 may be configured to select the type of detection unit 8 according to the content of the component 7-m of the drive unit 6-n and to present a method for connecting the detection unit 8 to the component 7-m. If it is difficult to obtain the detection value based on the schedule, the calculation unit 11 may output a command to the control device 2 and generate a schedule for operating the industrial machine 1 based on a measurement mode for detecting the detection value outside of operating hours.

[0045] In the above-described embodiment, the computer program installed in the diagnostic device 10 to realize the processing executed by the calculation unit 11 configured by a processor may be provided in a form recorded on a computer-readable non-transitory recording medium such as a semiconductor memory, a magnetic recording medium, or an optical recording medium. The calculation unit 11 is, for example, a functional module realized by a computer program executed on a processor.

[0046] Although the embodiments of the present disclosure have been described in detail, the present disclosure is not limited to the individual embodiments described above. Various additions, substitutions, modifications, partial deletions, etc. are possible to these embodiments without departing from the gist of the invention or the concept and spirit of the present invention derived from the content of the claims and their equivalents. For example, in the above-described embodiments, the order of each operation and the order of each process are shown as examples and are not limited to these. The same applies when numerical values ​​or mathematical formulas are used in the description of the above-described embodiments. Furthermore, appropriate combinations of several of the above-described embodiments are within the scope of the present disclosure.

[0047] The following supplementary notes are further disclosed regarding the above-described embodiments and variations: (Supplementary Note 1) A diagnostic device comprising a calculation unit that performs calculations for managing an industrial machine, wherein the calculation unit: acquires first information including information on a plurality of drive units that constitute the industrial machine; analyzes one or more components that constitute each of the drive units based on the first information; acquires second information regarding a fault that has occurred in the drive units based on analysis results of the components; calculates, based on the second information, a degree of impact on the industrial machine of a fault state in which a fault has occurred in the component; calculates a detectability indicating a degree of ease in acquiring, from the component, detection values ​​including feature quantities corresponding to the fault state of the component; and calculates a priority indicating a priority order for acquiring the detection values ​​based on the impact and the detectability.

[0048] (Supplementary Note 2) The diagnostic device according to Supplementary Note 1, wherein the calculation unit acquires third information relating to an operating period during which the industrial machine operates and a processing content of the industrial machine, and generates a schedule for acquiring the detection values ​​based on the third information and the priority.

[0049] (Supplementary Note 3) The diagnostic device according to Supplementary Note 2, wherein the calculation unit updates the schedule based on the priority and an acquisition state of the detection value acquired based on the schedule.

[0050] (Supplementary Note 4) The diagnostic device described in Supplementary Note 1, wherein the calculation unit calculates a vibration spectrum using vibration data included in the detection value acquired in the fault state, and calculates the detectability based on the correlation between the vibration spectrum corresponding to the feature and the drive unit.

[0051] (Supplementary Note 5) The diagnostic device according to Supplementary Note 1, wherein the calculation unit acquires fourth information related to a first question input by a user, extracts the components related to the fourth information, searches the first information and the second information of the industrial machine, performs a calculation related to the components based on the first information and the second information, generates a first answer related to the first question based on a result of the calculation, and outputs the first answer to an output unit.

[0052] (Supplementary Note 6) The diagnostic device according to Supplementary Note 5, wherein the calculation unit generates the answer to the question about a method for acquiring the detection value from the component.

[0053] (Supplementary Note 7) The diagnostic device according to Supplementary Note 5, wherein the calculation unit: acquires additional question content and command content input by a user at least once in response to the question content and the answer content; extracts the components related to the question content and the command content; searches the first information and the second information of the industrial machine; executes a calculation related to the components based on the first information and the second information; generates a second answer content by updating the first answer content for the second question content based on a calculation result; and outputs the second answer content to an output unit.

[0054] (Supplementary Note 8) A program installed in a computer mounted on a diagnostic device that executes calculations for managing industrial machinery, the program causing the computer to perform the following processes: acquire first information including information on a plurality of drive units that constitute the industrial machinery; analyze one or more components that constitute each of the drive units based on the first information; acquire second information regarding a failure content that occurs in the drive unit based on analysis results on the components; calculate, based on the second information, a degree of impact on the industrial machinery of a failure state in which a failure has occurred in the component; calculate a degree of detectability that indicates the degree of ease in acquiring, from the component, a detection value including a feature quantity that corresponds to the failure state of the component; and calculate a priority that indicates a priority order for acquiring the detection value based on the degree of impact and the detectability.

[0055] REFERENCE SIGNS LIST 1 Industrial machine, 2 Control device, 3 Control unit, 4 Memory unit, 5 Communication unit, 6 Drive unit, 6-n Drive unit, 7-m Component, 8 Detection unit, 10 Diagnosis device, 11 Calculation unit, 12 Memory unit, 12A Device data (first information), 12B Failure data (second information), 12C Operation data (third information), 13 Input unit, 14 Display unit, 15 Communication unit, M1-M10 Display image, S Diagnosis system, W Network

Claims

1. A diagnostic device comprising a calculation unit that performs calculations for managing industrial machinery, wherein the calculation unit: acquires first information including information on a plurality of drive units that make up the industrial machinery; analyzes one or more components that make up each of the drive units based on the first information; acquires second information regarding the type of failure that will occur in the drive units based on the analysis results of the components; calculates, based on the second information, the impact that a failure state in which a failure has occurred in the component will have on the industrial machinery; calculates a detectability that indicates the degree of ease in obtaining, from the component, a detection value including a feature quantity that corresponds to the failure state of the component; and calculates a priority that indicates the order of precedence for obtaining the detection value based on the impact and the detectability.

2. The diagnostic device according to claim 1, wherein the calculation unit acquires third information relating to the operating period during which the industrial machine is in operation and the processing content of the industrial machine, and generates a schedule for acquiring the detection values ​​based on the third information and the priority.

3. The diagnostic device according to claim 2, wherein the calculation unit updates the schedule based on the acquisition state of the detection values ​​acquired based on the schedule and the priority.

4. The diagnostic device of claim 1, wherein the calculation unit calculates a vibration spectrum using vibration data contained in the detection value obtained in the fault state, and calculates the detectability based on the correlation between the vibration spectrum corresponding to the feature and the drive unit.

5. The diagnostic device according to claim 1, wherein the calculation unit acquires a question input in natural language by a user, extracts the components related to the question, searches the first information and the second information of the industrial machine, performs a calculation related to the components based on the first information and the second information, generates an answer to the question based on the calculation result, and outputs the answer to an output unit.

6. The diagnostic device according to claim 5, wherein the calculation unit generates the answer to the question about a method for acquiring the detection value from the component.

7. The diagnostic device according to claim 5, wherein the calculation unit: acquires additional question content and additional command content input at least once by a user in response to the question content and the answer content; extracts the components related to the additional question content and / or the additional command content; searches the first information and the second information of the industrial machine; executes a calculation related to the components based on the first information and the second information; generates a new answer content for the additional question content and / or the additional command content based on a result of the calculation; and outputs the new answer content to an output unit.

8. A program installed in a computer mounted on a diagnostic device that executes calculations for managing industrial machinery, the program causing the computer to perform the following processes: acquire first information including information on multiple drive units that make up the industrial machinery; analyze one or more components that make up each of the drive units based on the first information; acquire second information regarding the type of failure that occurs in the drive unit based on the analysis results of the components; calculate, based on the second information, the impact on the industrial machinery of a failure state in which a failure has occurred in the component; calculate a detectability that indicates the degree of ease in acquiring, from the component, a detection value including a feature quantity that corresponds to the failure state of the component; and calculate a priority that indicates the order of priority for acquiring the detection value based on the impact and the detectability.

Images