Diagnostic system, information processing device, diagnostic method, and program

Abstract

This diagnostic system (1) comprises: an operation state information acquisition unit that acquires operation state information that indicates an operation state of a machining facility (2) to be diagnosed; an extraction unit that extracts, from the operation state information that has been acquired by the operation state information acquisition unit, operation state information of a calculation target interval that indicates a time region that is determined according to a preset rule, in a stable machining interval in which a motor rotates in a stable manner; a feature amount calculation unit that calculates a feature amount from the operation state information of the calculation target interval that has been extracted by the extraction unit; and a diagnostic unit that determines, on the basis of the feature amount that has been calculated by the feature amount calculation unit, whether the machining facility 2 is normal or abnormal.

Description

Diagnostic system, information processing device, diagnostic method, and program

[0001] The present disclosure relates to a diagnostic system, an information processing device, a diagnostic method, and a program.

[0002] There is known a technique for collecting data from machining equipment at a manufacturing site and diagnosing the condition of the machining equipment using the collected data. For example, Patent Document 1 discloses a numerical control device that determines whether or not an abnormality has occurred in the machining equipment based on data on a current flowing through a motor that drives a tool.

[0003] Japanese Patent Application Laid-Open No. 2020-013433

[0004] This numerical control device determines whether an abnormality has occurred using data from all sections in which the motor is rotating at a constant speed. However, if the abnormality occurs for a short period of time, the relatively long period of normal data and the relatively short period of abnormal data are averaged, which may prevent the abnormality from being detected. Therefore, there is room for improvement in terms of accurately determining whether an abnormality has occurred in the processing equipment.

[0005] The present disclosure has been made in consideration of the above-described circumstances, and aims to provide a diagnostic system, an information processing device, a diagnostic method, and a program that are capable of accurately diagnosing the state of processing equipment.

[0006] In order to achieve the above-mentioned object, the diagnostic system according to the present disclosure includes an operating state information acquisition unit that acquires operating state information indicating the operating state of the processing equipment to be diagnosed; an extraction unit that extracts, from the operating state information acquired by the operating state information acquisition unit, operating state information of a calculation target section that indicates a time region determined by a predetermined rule within a stable processing section in which the motor rotates stably; a feature calculation unit that calculates feature amounts from the operating state information of the calculation target section extracted by the extraction unit; and a diagnostic unit that determines whether the processing equipment is normal or abnormal based on the feature amounts calculated by the feature calculation unit.

[0007] According to the present disclosure, whether the machining equipment is normal or abnormal is determined based on the operating status information of the calculation target section determined by a preset rule within the stable machining section in which the motor of the machining equipment to be diagnosed rotates stably. Therefore, the condition of the machining equipment can be diagnosed with high accuracy.

[0008] 1. A block diagram showing the functional configuration of a diagnostic system according to a first embodiment. 2. A diagram showing an example of the rotation speed of a spindle motor, an example of a cutting feed signal, and an example of a current value flowing through a spindle motor, all acquired by the machining data acquisition device shown in FIG. 1. 3. A diagram showing an example of a correspondence table stored in the signal processing device shown in FIG. 1. 4. A block diagram showing an example of the physical configuration of the machining data acquisition device, signal processing device, diagnostic device, learning model generation device, and control device shown in FIG. 1. 5. A flowchart showing the learning model generation process by the diagnostic system according to the embodiment. 6. A diagram showing an example of learning data generated by the signal processing device shown in FIG. 1.

[0009] Hereinafter, a diagnostic system, an information processing device, a diagnostic method, and a program according to embodiments of the present disclosure will be described with reference to the drawings. Note that the same or corresponding parts in the drawings are designated by the same reference numerals.

[0010] The diagnostic system according to this embodiment collects time-series status data indicating the operating status during machining from machining equipment. The diagnostic system extracts, from the collected status data, status data for time domains in which abnormalities in the machining equipment are likely to occur according to preset rules, and calculates feature quantities from the extracted status data. The diagnostic system applies the calculated feature quantities to a machine learning model to determine whether or not there is an abnormality in the machining equipment.

[0011] As shown in FIG. 1, the diagnostic system 1 according to this embodiment includes a processing data acquisition device 3 that acquires processing data including status data from the processing equipment 2 to be diagnosed, a signal processing device 4 that processes the status data and generates input data to be input to a learning model, a storage device 5 that stores various data generated by the signal processing device 4, a diagnostic device 6 that determines whether or not there is an abnormality in the processing equipment 2 based on the input data generated by the signal processing device 4, a learning model generation device 7 that generates a learning model to be used by the diagnostic device 6, a status indicator 8 that displays the diagnosis result by the diagnostic device 6, and a control device 9 that controls the equipment based on the determination result by the diagnostic device 6.

[0012] The processing equipment 2 is a machine for performing processes such as cutting, cutting, and polishing on a workpiece, and is, for example, a machining center, a lathe, a drill press, a milling machine, a polishing machine, a turning center, an electric discharge machine, a laser processing machine, an ultrasonic processing machine, etc. The processing equipment 2 is equipped with sensors such as a current sensor, a vibration sensor, a microphone, an acoustic emission (AE) meter, an acceleration sensor, a torque sensor, a rotation sensor, and a temperature sensor. The sensors detect physical quantities such as the current value flowing in a motor that drives a tool such as a drill, an end mill, a face mill, a long drill, a cutting tool, a grinding wheel, the motor rotation speed, the rotational torque, and the magnitude of vibration, and output information on the detected physical quantities.

[0013] The machining data acquisition device 3 acquires machining data including time-series status data indicating the operating status during machining from the machining equipment 2, temporarily stores the data, lumps together a certain amount of machining data, and provides the data to the signal processing device 4. The machining data acquired by the machining data acquisition device 3 includes status data indicating the operating status of the machining equipment 2, such as information on physical quantities detected by sensors and instruction signals output from a control device 9 that controls the operation of the machining equipment 2, and machining-related information, which is information for identifying a machining process, such as a machining program number, a tool number, power consumption, coordinate information of the machining axis, hydraulic / air pressure, battery voltage, and number of days the equipment has been in use. The machining data acquisition device 3 is an example of an operating status information acquisition unit and a machining identification information acquisition unit, the status data is an example of operating status information, and the machining-related information is an example of machining identification information.

[0014] The signal processing device 4 processes time-series status data indicating the operating status of the processing equipment 2 transmitted from the processing data acquisition device 3, and generates input data to be input to the learning model. Specifically, the signal processing device 4 performs signal processing such as amplification of the analog signal acquired from the sensor by the processing data acquisition device 3, filtering using a high-pass filter or a low-pass filter, and A / D (Analog to Digital) conversion based on a sampling frequency and resolution preset by the user. The signal processing device 4 also performs cleansing processing such as removing noise and abnormal values ​​and filling in missing values.

[0015] After performing signal processing, the signal processing device 4 extracts data of a calculation target section, which is a section used to calculate feature quantities, from the state data after processing. Specifically, as illustrated in FIG. 3 , the signal processing device 4 stores a correspondence table, which is information for specifying which extraction rule from the extraction rules defined by the user is to be applied to each machining process. The signal processing device 4 refers to this correspondence table, identifies an extraction rule from the machining program number and tool number included in the machining data, and executes the identified extraction rule to extract state data of the calculation target section. As shown in FIG. 3 , the correspondence table includes items for the machining program number that identifies the machining program, the tool number that identifies the tool, and the extraction rule ID that identifies the extraction rule. In the illustrated example, it is indicated that extraction rule ID "r1" is applied to the machining process executed by machining program number "N001" and tool number "D01."

[0016] To illustrate a specific example, without limitation, FIG. 2 shows the transition of status data when a temporary dimensional error occurs when the workpiece and tool come into contact after cutting begins, and then normal operation is restored. The status data includes the rotation speed of the spindle motor of the machining equipment 2, a cutting feed signal output from the control device 9, and the current value flowing through the spindle motor, as shown in FIG. 2 . When cutting begins, the machining equipment 2 rotates the spindle motor and accelerates it to a rotation speed corresponding to the rotation speed command in the machining program. During this motor acceleration period, acceleration torque is generated, temporarily increasing the current flowing through the spindle motor. Once the motor rotation speed reaches a steady state, the current decreases. After the spindle motor rotation speed reaches the target rotation speed and stabilizes, actual machining begins in response to the cutting feed signal. When actual machining begins and the workpiece and tool come into contact, a load is placed on the spindle motor, causing the current flowing through the spindle motor to increase again. This example shows that the current flowing through the spindle motor temporarily increased during the abnormality occurrence period in which a dimensional error occurred. After that, normal operation resumes, and the current value settles to a steady level. After that, when actual machining is completed, the machining equipment 2 decelerates the spindle motor. During this motor deceleration period, deceleration torque is generated, and the current flowing through the spindle motor temporarily increases, as in the acceleration period. When the motor stops rotating, the current decreases. Thus, the current flowing through the spindle motor changes during the acceleration and deceleration periods of the spindle motor regardless of the machining phenomenon. Therefore, using data from these periods for diagnosis may result in erroneous results. Therefore, data from the stable machining period, which excludes the acceleration and deceleration periods of the spindle motor and in which the motor rotates at a constant speed, is used for diagnosis. Furthermore, as shown in the example shown, when a temporary abnormality occurs, calculating the feature values ​​using all the current data from the stable machining period may result in a small difference between the feature values ​​calculated from the normal data and the feature values ​​calculated from the data containing the abnormality, potentially leading to incorrect detection of the abnormality.Therefore, in each machining process, a calculation interval, which is a time region where an abnormality is likely to occur, i.e., where the probability or frequency of occurrence is high, is specified in advance, and rules for extracting status data for the calculation interval are defined for each machining process. The rules are arbitrary, but may include, for example, information including an event that serves as a trigger for specifying the calculation interval and the time from the trigger to the start and end points of the calculation interval. If the example in Figure 2 occurs frequently, the trigger that defines the calculation interval is, for example, a change in the cutting feed signal from low level to high level, and the start point of the calculation interval is synchronized with the trigger, and the end point is set to the timing when time t has elapsed since the trigger.

[0017] To design such rules, a user identifies the type of machining equipment and tool, the machining content, etc., and then identifies the time period in each machining process where anomalies are likely to occur, and then sets extraction rules. For example, the user may determine the calculation target interval by capturing machining phenomena with a high-speed camera to identify the timing of anomalies, observing the behavior of status data to identify the timing of anomalies, or setting multiple candidate calculation target intervals and applying the respective interval data to a learning model to determine the calculation target interval with the highest accuracy of diagnostic results. For example, if it is determined that anomalies are likely to occur immediately after the start of actual machining, an extraction rule may be defined to extract status data for five seconds from the time the tool and workpiece come into contact. For machining where anomalies are likely to occur at the end of actual machining, an extraction rule may be defined to extract status data for five seconds before and after the tool and workpiece separate. Note that two or more calculation target intervals may be set for a single process.

[0018] In the example of FIG. 3, a combination of a machining program number and a tool number is used as information for identifying each machining process, but any information may be used as long as it can identify the machining process.

[0019] The signal processing device 4 calculates feature quantities from the extracted state data of the calculation target section. The feature quantities include, for example, the maximum, minimum, average, standard deviation, variance, kurtosis, and skewness of the current value. Note that, in addition to the current value, feature quantities may be calculated from vibration, sound, or AE frequency, magnitude, temperature, etc. When calculating feature quantities from vibration, sound, or AE, frequency analysis may be performed to calculate feature quantities from the magnitude of specific frequencies. The signal processing device 4 calculates feature quantities for each cycle, which is the period from the start to the end of machining of a workpiece. The signal processing device 4 generates input data by associating a combination of the calculated feature quantities with a cycle number indicating the number of the cycle. The signal processing device 4 associates the generated input data with machining-related information, including the machining program number, tool number, etc. output from the machining data acquisition device 3, and stores the associated input data in the storage device 5. Note that, when multiple machining processes are performed in one cycle, feature quantities may be calculated for each machining process, and input data may be generated for each machining process. The signal processing device 4 is an example of an extraction unit and a feature amount calculation unit.

[0020] Returning to FIG. 1, the storage device 5 stores input data including the feature amount and the number of cycles transmitted from the signal processing device 4 in association with machining-related information including the machining program number, tool number, etc.

[0021] The diagnostic device 6 diagnoses the machining equipment 2 using the input data generated by the signal processing device 4 and stored in the storage device 5 and the learning model generated by the learning model generation device 7. Specifically, the diagnostic device 6 applies the input data generated based on status data sequentially acquired during machining of the machining equipment 2 to the learning model, and outputs a diagnostic result determining whether the machining equipment 2 is normal or not. The diagnostic device 6 transmits the diagnostic result to the status indicator 8 and the control device 9. The diagnostic device 6 may be an edge computer installed at the production site, or may be a computer connected via the Internet from an office away from the production site. The diagnostic device 6 is an example of a diagnostic unit.

[0022] The learning model generation device 7 generates a learning model for determining whether or not the machining equipment 2 is abnormal. Specifically, the learning model generation device 7 generates the learning model by performing machine learning on the learning model, providing the learning model with learning data including input data generated by the signal processing device 4 and label information indicating whether each input data is normal or abnormal. The user determines whether the machining process of each cycle performed by actual machining or simulation is normal or abnormal, and creates learning data by assigning label information indicating normal or abnormal to feature values ​​associated with each cycle. The learning model is a model based on a machine learning algorithm such as a decision tree, k-nearest neighbor method, or support vector machine. It inputs feature values ​​calculated from status data and outputs determination result information indicating whether the machining equipment 2 being inspected is normal or abnormal. Note that the input data included in the learning data does not have to be status data acquired from the machining equipment 2. For example, computer-generated simulated data may be used depending on the type and processing content of the machining equipment 2. Furthermore, the label information included in the learning data is not limited to two patterns, normal and abnormal, and three or more patterns of labels may be assigned by further subdividing the abnormal label into dimensional abnormality, poor surface quality, etc. The learning model generation device 7 is an example of a learning model generation unit.

[0023] The status indicator 8 displays the diagnosis result by the diagnostic device 6. The status indicator 8 is, for example, an operation panel installed on the processing equipment 2. The status indicator 8 notifies the user of the occurrence of an abnormality by displaying information indicating that an abnormality has been diagnosed on a screen. The status indicator 8 may also include a lamp, a speaker, etc., and may turn on a lamp and emit a warning sound from a speaker when an abnormality is diagnosed. Furthermore, the status indicator 8 may have a function to automatically send an email indicating that an abnormality has been diagnosed to a preset email address.

[0024] The control device 9 controls the operation of the machining equipment 2. The control device 9 is, for example, a numerical control device that controls the machining equipment 2 by commands based on an NC (Numerical Control) program. When the control device 9 receives diagnosis result information from the diagnosis device 6 indicating that an abnormality has been determined to have occurred in the machining equipment 2, the control device 9 stops the machining equipment 2. Note that the control device 9 may not completely stop the machining equipment 2, but may limit some of the functions of the machining equipment 2 depending on the degree of the abnormality occurring in the machining equipment 2. Note that the control device 9 is an example of a control unit.

[0025] In the diagnostic system 1 having the functional configuration described above, the processed data acquisition device 3, the signal processing device 4, the diagnostic device 6, the learning model generation device 7, and the control device 9 physically include, as shown in Figure 4, a CPU (Central Processing Unit) 11 that executes processing according to a program, a RAM (Random Access Memory) 12 which is a volatile memory, a ROM (Read Only Memory) 13 which is a non-volatile memory, a memory unit 14 that stores data, an input unit 15 that accepts input of information, and a communication unit 16 that sends and receives information, which are connected via an internal bus 99.

[0026] The CPU 11 executes various processes by reading out the programs stored in the storage unit 14 into the RAM 12 and executing them. As main functions provided by the programs, the CPU 11 executes a process of processing the status data transmitted from the processing data acquisition device 3 by the signal processing device 4 to extract data of the calculation target section and calculate feature quantities from the extracted data, a diagnostic process of determining whether the processing equipment 2 is normal by the diagnostic device 6, a process of generating a learning model by the learning model generation device 7, etc.

[0027] The RAM 12 is used as a work area for the CPU 11. The ROM 13 stores the control program executed by the CPU 11, a BIOS (Basic Input Output System), and the like.

[0028] The storage unit 14 includes a hard disk drive, stores the programs executed by the CPU 11, and stores various data used when the programs are executed. The storage unit 14 stores the processing data acquired from the processing equipment 2 by the processing data acquisition device 3, the input data generated by the signal processing device 4, the learning model generated by the learning model generation device 7, and the learning data used for learning the learning model.

[0029] The input unit 15 is a user interface including a keyboard, a mouse, a communication device, etc. The communication unit 16 is a network termination device or a wireless communication device connected to a network, and a serial interface or a LAN (Local Area Network) interface connected to them.

[0030] Next, a description will be given of the operation of the diagnostic system 1. In the following, an example will be described in which the processing equipment 2 to be diagnosed by the diagnostic system 1 is a cutting machine, and the presence or absence of an abnormality in the processing equipment 2 is determined based on feature values ​​calculated from the current flowing through a spindle motor having a drill attached at its tip.

[0031] (Preparation) The diagnostic system 1 calculates feature quantities from the current data within the stable machining section using current data within a calculation section, which is a time region previously specified by the user. The process of specifying the calculation section will now be described. The user observes the tendency for abnormalities to occur in the machining equipment 2, for example, using video footage captured with a high-speed camera during actual machining, and specifies a time region where abnormalities are likely to occur. For example, the user specifies that abnormalities are likely to occur within five seconds from the time the tool comes into contact with the workpiece. Next, the user sets an extraction rule in the signal processing device 4 for extracting current data for the specified time region. For example, the user sets an extraction rule in the signal processing device 4 to extract current data for five seconds from the time the cutting signal is output in order to extract current data for the specified time region. The user specifies a calculation section, which is a time region where abnormalities are likely to occur, for each machining process depending on the type of machining equipment and tool owned and the machining content, and sets an extraction rule for extracting current data for the specified calculation section.

[0032] Next, the user creates a correspondence table, which is information for identifying which extraction rule is applied to each machining process, and stores it in the signal processing device 4. The signal processing device 4 refers to this correspondence table to identify an extraction rule from the machining program number and tool number included in the machining data, and executes the identified extraction rule to extract current data for the calculation target section. As shown in FIG. 3 , the correspondence table includes items such as a machining program number that identifies the machining program, a tool number that identifies the tool, and an extraction rule ID that identifies the extraction rule. In the illustrated example, the machining program number "N001" is information that identifies the machining program as a cutting program, and the tool number "D01" is information that identifies the tool as a drill. The extraction rule ID "r1" is applied to the machining process executed by the machining program number "N001" and the tool number "D01," and current data for the calculation target section is extracted. The extraction rule for the extraction rule ID "r1" is, for example, a rule that extracts status data for five seconds from the time a cutting feed signal is transmitted as the calculation target section.

[0033] (Learning Model Generation Process) Next, a learning model generation process in which the diagnostic system 1 generates a learning model for determining whether or not there is an abnormality in the machining equipment 2 will be described with reference to Fig. 5. The learning model generation process is executed before the first diagnostic process is performed, when it becomes necessary to update the learning model due to replacement of the machining equipment 2 or a tool, when it is desired to improve the accuracy of determination using more data, etc. Below, a case will be described in which, in a machining process in which only cutting is performed, one cycle is defined as the period from the start to the end of machining of one workpiece, and a learning model is generated based on feature amounts calculated from current data for each cycle.

[0034] Prior to executing the learning model generation process, the user presets the sampling frequency and resolution in the signal processing device 4 when A / D converting the analog signal output from the current sensor that measures the current flowing through the spindle motor. The higher the sampling frequency, the more accurately the analog signal can be traced, allowing the computer to input a digital signal closer to the true signal for use in learning. Furthermore, since the frequency range F_range of the FFT performed after A / D conversion is determined by the following equation (1), it is advisable to increase the sampling frequency if a wider frequency range is desired: F_range = fs / 2.56 (fs: sampling frequency) Equation 1 Generally, it is considered best to set the sampling frequency to about 10 times the frequency of the analog signal to suppress aliasing. However, to obtain a more accurate learning model, it is preferable to set it to 1000 times or more the frequency of the analog signal.

[0035] When the user operates the input unit 15 of the learning model generation device 7 to request the start of the learning model generation process, the learning model generation device 7 starts the process.

[0036] When cutting of a workpiece is started by the machining equipment 2, the machining data acquisition device 3 acquires machining data including status data indicating the current value flowing through the spindle motor, the motor rotation speed, and a cutting feed signal, as well as machining-related information such as the machining program number and tool number (step S11). The machining data acquisition device 3 lumps together the status data for each cycle, which is the period from the start to the end of machining of one workpiece, and outputs the lumped data together with the machining-related information to the signal processing device 4.

[0037] Next, the signal processing device 4 performs signal processing on the received status data and extracts status data for the calculation target section from the processed status data (step S12). Specifically, the signal processing device 4 converts the analog signal included in the status data transmitted from the machining data acquisition device 3 into a digital signal at a preset sampling frequency. Note that the analog signal before conversion to a digital signal may be subjected to signal amplification and filtering using a high-pass filter and a low-pass filter. Next, the signal processing device 4 acquires the machining program number and tool number included in the machining data output from the machining data acquisition device 3 in step S11 and identifies an extraction rule by referring to the correspondence table. For example, if the signal processing device 4 acquires information on program number "N001" and tool number "D01," it identifies extraction rule ID "r1" as the extraction rule by referring to the correspondence table shown in FIG. 3. Next, the signal processing device 4 acquires the rotation speed of the spindle motor included in the status data after signal processing and identifies a stable machining section where the rotation speed is constant. Next, the signal processing device 4 reads out the extraction rule with the identified extraction rule ID "r1" and executes the extraction rule to extract the status data for 5 seconds from the time the cutting feed signal is sent as the calculation target section, thereby extracting the current data for the calculation target section from the current data for the stable machining section.

[0038] 5, the signal processing device 4 then performs a cleansing process on the extracted current data for the calculation target interval (step S13). Specifically, the signal processing device 4 performs a process to remove noise and abnormal values ​​from the current data and to complement missing values.

[0039] Next, the signal processing device 4 calculates feature quantities from the machining data cleansed in step S13 (step S14). Specifically, the signal processing device 4 calculates feature quantities by determining the average value, maximum value, minimum value, standard deviation, variance, kurtosis, skewness, etc. of the current values ​​in the cleansed calculation target section. The signal processing device 4 calculates feature quantities for each cycle from the start to the end of cutting processing of one workpiece. The signal processing device 4 sequentially stores the calculated feature quantities and the current data used to calculate the feature quantities in the storage device 5, together with the cycle number indicating the number of machining cycles.

[0040] Next, the learning model generation device 7 generates learning data (step S15). Specifically, based on user input, the learning model generation device 7 generates learning data by assigning labels to the feature quantities for each cycle stored in the storage device 5 in step S14, indicating whether the data is from when the machining equipment 2 is operating normally or when an abnormality is present. As illustrated in FIG. 6 , the learning data includes a "cycle count" indicating the number of times the workpiece has been processed, "feature quantity A," "feature quantity B," etc. indicating a data set of multiple feature quantities for each cycle calculated by the signal processing device 4 in step S14, and a "state label" indicating the label assigned to the feature quantity for each cycle. The learning model generation device 7 stores the generated learning data in the storage device 5.

[0041] Returning to FIG. 5 , next, the learning model generation device 7 generates a learning model (step S16). Specifically, the learning model is a model based on a machine learning algorithm such as a decision tree, a k-nearest neighbor method, or a support vector machine, and outputs determination result information indicating whether the processing equipment 2 to be inspected is normal or abnormal, using as input the feature values ​​for each cycle calculated from the current data. The learning model generation device 7 generates the learning model by performing machine learning using learning data including the feature values ​​for each cycle included in the learning data generated in step S15 and label information indicating normality or abnormality assigned to the feature values ​​for each cycle. The learning model generation device 7 stores the generated learning model in the storage device 5.

[0042] In this way, a learning model for determining whether the processing equipment 2 is normal or not is completed.

[0043] (Diagnostic Processing) Next, the operation of the diagnostic processing for determining whether or not the processing equipment 2 is normal using a learning model in an actual processing situation will be described with reference to FIG.

[0044] The memory device 5 stores the learning model generated by the above-mentioned learning model generation process, and the learning model stored in the memory device 5 is pre-installed in the diagnostic device 6 by the user.

[0045] As with the learning model generation process, the diagnostic system 1 starts the diagnostic process when the machining equipment 2 starts machining a workpiece. Steps S21 to S24 of the diagnostic process are similar to steps S11 to S14 of the learning model generation process shown in Fig. 5, in which machining data is acquired sequentially and feature amounts are calculated for each cycle of the cutting process from the current data included in the machining data.

[0046] 7 , next, the diagnostic device 6 determines whether the target processing equipment 2 is normal or abnormal (step S25). Specifically, the diagnostic device 6 inputs the feature amount calculated in step S24 into a learning model and obtains determination result information indicating whether the processing equipment 2 is normal or abnormal.

[0047] If the judgment result information indicates that the machining equipment 2 is normal (step S26; Yes), the diagnostic device 6 determines whether the machining process has ended, and if it determines that it has ended (step S27; Yes), it ends the diagnostic process. If the diagnostic device 6 determines that the machining process has not ended (step S27; No), it returns to step S21 and acquires machining data for the next cycle (step S21).

[0048] Returning to step S26, if the judgment result information indicates that the processing equipment 2 is abnormal (step S26; No), the diagnostic device 6 notifies the status indicator 8 and the control device 9 that the processing equipment 2 has been judged to be abnormal (step S28), and ends the process. Thereafter, the status indicator 8 displays information indicating that the processing equipment 2 has been diagnosed as abnormal on the screen, thereby notifying the user of the occurrence of the abnormality. The control device 9 stops the processing equipment 2.

[0049] As described above, the diagnostic system 1 extracts state data for a calculation target section, which is a time region in which abnormalities are likely to occur, from state data for a section from the start to the end of machining of one workpiece, and calculates feature quantities. The diagnostic system 1 determines the presence or absence of an abnormality in the machining equipment 2 based on the calculated feature quantities. The feature quantities calculated from the state data for the calculation target section have a larger difference between normal and abnormal values ​​than feature quantities calculated from all data within the machining section, making it possible to accurately determine the presence or absence of an abnormality.

[0050] Furthermore, since the diagnostic system 1 determines the presence or absence of an abnormality using less data, there is no need to store and process a large amount of data, which improves the processing speed of the diagnostic process and makes it possible to save storage capacity.

[0051] As long as it does not deviate from the gist of the present disclosure, it is possible to select and discard the configurations given in the above embodiments, or to change them to other configurations as appropriate.

[0052] In the above embodiment, the functions of the diagnostic system 1 have been described as being executed by individual devices, namely, the processed data acquisition device 3, the signal processing device 4, the storage device 5, the diagnostic device 6, the learning model generation device 7, the status indicator 8, and the control device 9. However, this is not limited to this, and the functions of each device may be executed by an information processing device that is a single computer. Furthermore, each process of the diagnostic system 1 may be executed by multiple computers that execute the functions of several devices, such as by executing the functions of the processed data acquisition device 3 and the signal processing device 4 by a single computer and the functions of the diagnostic device 6 and the learning model generation device 7 by a single computer.

[0053] In the above description, the diagnostic system 1 includes the learning model generation device 7, but the diagnostic system 1 does not necessarily need to include the learning model generation device 7. For example, the training data may be supplied to a machine learning device prepared on another computer to generate a learning model, which may then be set in the diagnostic device 6.

[0054] Furthermore, in the above embodiment, the diagnostic device 6 determines whether or not an abnormality exists in the processing equipment 2 using a learning model, but this is not limited to this. For example, the presence or absence of an abnormality in the processing equipment 2 may be determined by a diagnostic rule in which a threshold is set for a feature amount calculated from status data, and it is determined that an abnormality exists in the processing equipment 2 if the feature amount is equal to or greater than the threshold. In this case, in the process of setting the calculation target section, the user determines a threshold for the feature amount using status data in which an abnormality exists, and sets the diagnostic rule in the diagnostic device 6. In step S25, the diagnostic device 6 reads out the set diagnostic rule and determines whether or not an abnormality exists by comparing the feature amount with the threshold.

[0055] The status display 8 may not only display the diagnostic results but also the processed data stored in the storage device 5. Furthermore, since the feature quantities calculated from the status data are sequentially stored in the storage device 5 during the diagnostic process, the feature quantities may be displayed in real time using trend graphs, scatter diagrams, etc.

[0056] The diagnostic device 6 may not only determine whether an abnormality is currently occurring in the processing equipment 2, but also predict when an abnormality will occur. Specifically, the diagnostic device 6 creates a trend graph of the feature values, performs linear regression analysis or nonlinear regression analysis, and fits an approximate curve to predict future feature value values ​​and calculate the time until an abnormality occurs. When the time until an abnormality occurs becomes shorter and exceeds a preset threshold, the status indicator 8 may notify an operator of an alarm or display a message urging maintenance. The status indicator 8 may also display the threshold together with the trend graph.

[0057] Furthermore, while the above embodiment has been described with reference to a case where one machining process is performed in one cycle, the present invention is not limited to this. For example, multiple machining processes, such as cutting, cutting, and polishing, may be performed in one cycle. In this case, an extraction rule for extracting a calculation interval for each machining process may be set, and feature values ​​may be calculated from the state data of each calculation interval to generate a learning model. The diagnostic device 6 may then input each feature value into each learning model and determine whether or not an abnormality exists in the machining equipment 2.

[0058] Furthermore, the information stored in the storage device 5 may be collectively managed by a cloud server present on the network, and the signal processing device 4, the diagnostic device 6, and the learning model generation device 7 may access the cloud server as necessary to read and write information. In this case, the diagnostic system 1 does not need to include the storage device 5. Furthermore, the signal processing of data by the signal processing device 4 and the learning model generation processing by the learning model generation device 7 may be performed on the cloud using information stored in the cloud server.

[0059] In the above explanation, the signal processing device 4 has mainly been described as an example in which one or more calculation intervals are set for each period from the start to the end of processing of one workpiece, but if one cycle includes multiple processing steps, a calculation interval may be set for each processing step, and the quality of the processing may be determined for each processing step.

[0060] Although the signal processing device 4 has been described with a focus on an example in which it extracts status data for a calculation target section based on a preset extraction rule, it may also identify a section in which a difference between normal processing and an abnormality is likely to appear based on output values ​​from a sensor installed in the machining equipment 2 as the calculation target section. Specifically, for example, in the above-described advance preparation stage, the signal processing device 4 calculates the difference in sensor output values ​​between the normal processing section and the abnormality occurrence section from multiple time-series status data including the sensor output values ​​when an abnormality occurs. The difference in sensor output values ​​is calculated, for example, by the difference in average, maximum, and minimum current values ​​between the normal processing section and the abnormality occurrence section. Next, the signal processing device 4 identifies the calculation target section based on the abnormality occurrence section of the status data with the largest calculated difference. For example, it may identify the abnormality occurrence section of the status data with the largest difference as the calculation target section, or it may identify a section such as 3 seconds before or 5 seconds before or after the abnormality occurrence section as the calculation target section, or it may identify a time region including each abnormality occurrence section of each of the multiple status data with the largest difference, or a time region overlapping each abnormality occurrence section as the calculation target section. For example, if the abnormality occurrence periods for three status data with large differences are between 10 and 15 seconds after the start of actual machining, between 8 and 18 seconds after the start of actual machining, and between 12 and 20 seconds after the start of actual machining, the calculation period may be specified as the period from 8 to 20 seconds after the start of actual machining, which is a time range that includes each of the abnormality occurrence periods, or the calculation period may be specified as the period from 12 to 15 seconds after the start of actual machining, which is a time range that overlaps each of the abnormality occurrence periods.The signal processing device 4 then specifies the calculation period for each machining process and sets an extraction rule for extracting status data for the specified calculation period.The signal processing device 4 then extracts status data for the calculation processing period specified for each machining process from the status data acquired by the machining data acquisition device 3 in the processing of step S12 or step S22.

[0061] 2 into a plurality of sections, calculates the feature values ​​for each of the sections, and identifies the calculation target section based on the calculated feature values ​​for each section. For example, the signal processing device 4 divides the plurality of status data acquired by the processing data acquisition device 3 into a first section, a second section, a third section, and so on, each of which is a set number of sections, such as five or ten. Next, the signal processing device 4 calculates the feature values ​​for each of the divided sections for each of the status data. Next, the signal processing device 4 calculates the variation in the feature values ​​for each of the plurality of status data sections, such as the first section, the second section, the third section, and so on, and compares the variations to identify the section with the largest variation as the calculation target section. Alternatively, the signal processing device 4 may calculate the average value of the feature values ​​for each section and identify the section with the largest difference in average value from the other sections as the calculation target section.

[0062] Furthermore, the processed data acquisition device 3, the signal processing device 4, the storage device 5, the diagnostic device 6, and the learning model generation device 7 can be realized using a normal computer system, rather than using dedicated devices. For example, a program for realizing each function may be stored and distributed on a computer-readable recording medium such as a CD-ROM (Compact Disc Read Only Memory) or a DVD-ROM (Digital Versatile Disc Read Only Memory), and the program may be installed on a computer to configure a computer capable of realizing each of the above-mentioned functions.

[0063] Furthermore, when each function is realized by sharing the functions between an OS (Operating System) and an application, or by cooperation between the OS and the application, only the application may be stored on the recording medium.

[0064] The present disclosure allows various embodiments and modifications without departing from the broad spirit and scope of the present disclosure. Furthermore, the above-described embodiments are intended to explain the present disclosure and do not limit the scope of the present disclosure. In other words, the scope of the present disclosure is defined by the claims, not the embodiments. Various modifications made within the scope of the claims and the meaning of equivalent disclosures are considered to be within the scope of the present disclosure.

[0065] This application is based on Japanese Patent Application No. 2022-159730 filed on October 3, 2022. The entire specification, claims, and drawings of Japanese Patent Application No. 2022-159730 are incorporated herein by reference.

[0066] Various aspects of the present disclosure are summarized below as appendices.

[0067] (Supplementary Note 1) A diagnostic system comprising: an operating state information acquisition unit that acquires operating state information indicating the operating state of processing equipment to be diagnosed; an extraction unit that extracts, from the operating state information acquired by the operating state information acquisition unit, operating state information of a calculation target section that indicates a time region determined by a preset rule within a stable processing section in which a motor rotates stably; a feature calculation unit that calculates feature amounts from the operating state information of the calculation target section extracted by the extraction unit; and a diagnosis unit that determines whether the processing equipment is normal or abnormal based on the feature amounts calculated by the feature calculation unit.

[0068] (Supplementary Note 2) The diagnostic system according to Supplementary Note 1, wherein the diagnostic unit determines whether the processing equipment to be diagnosed is normal or abnormal based on an output obtained by inputting the feature calculated by the feature calculation unit into a preset machine learning model.

[0069] (Supplementary Note 3) The diagnostic system according to Supplementary Note 2, further comprising: a learning model generation unit that generates the machine learning model based on learning data including the features calculated by the feature calculation unit and label information assigned to each feature.

[0070] (Supplementary Note 4) A diagnostic system described in any one of Supplementary Notes 1 to 3, further comprising a processing identification information acquisition unit that acquires processing identification information that identifies the processing content performed by the processing equipment to be diagnosed, wherein the extraction unit identifies a rule for extracting the operating status information of the calculation target section from the operating status information of the processing equipment to be diagnosed based on correspondence information that associates the processing content with a rule for extracting the operating status information of the calculation target section, and extracts the operating status information to be used for calculating the feature by executing the identified rule.

[0071] (Appendix 5) A diagnostic system described in any one of Appendices 1 to 4, further comprising a control unit that controls the operation of the processing equipment to be diagnosed, wherein the diagnostic unit notifies the control unit of a determination result indicating an abnormality when it determines that the processing equipment to be diagnosed is abnormal, and when the control unit receives the determination result from the diagnostic unit, it stops the operation of some or all of the processing equipment to be diagnosed.

[0072] (Supplementary Note 6) The diagnostic system described in any one of Supplementary Notes 1 to 5, wherein the operating status information includes a sensor output indicating a physical quantity detected by a sensor installed in the processing equipment, and the extraction unit calculates a difference between the sensor output in a normal processing section and the sensor output in the abnormality occurrence section from a plurality of pieces of operating status information including the operating status of an abnormality occurrence section of the processing equipment, identifies the calculation target section based on the abnormality occurrence section of the operating status information including a sensor output with a large calculated difference, and extracts the operating status information of the identified calculation target section from the operating status information acquired by the operating status information acquisition unit.

[0073] (Supplementary Note 7) The diagnostic system according to any one of Supplementary Notes 1 to 6, wherein the extraction unit divides the stable processing section of the operating status information acquired by the operating status information acquisition unit into a plurality of sections, calculates a feature value for each of the divided sections, compares the calculated feature values ​​for each of the sections, and identifies the calculation target section based on a comparison result, and extracts operating status information for the identified calculation target section.

[0074] (Supplementary Note 8) An information processing device comprising: an extraction unit that extracts, from operation status information indicating the operation status of the machining equipment to be diagnosed, operation status information of a calculation target section that indicates a time region determined by a preset rule within a stable machining section in which the motor rotates stably; and a diagnosis unit that determines whether the machining equipment to be diagnosed is normal or abnormal based on the operation status information of the calculation target section extracted by the extraction unit.

[0075] (Supplementary Note 9) A diagnostic method including the steps of: extracting, from operational status information indicating the operational status of the machining equipment to be diagnosed, operational status information of a calculation target section indicating a time region determined by a preset rule within a stable machining section in which the motor rotates stably; and determining whether the machining equipment to be diagnosed is normal or abnormal based on the extracted operational status information of the calculation target section.

[0076] (Supplementary Note 10) A program that causes a computer to execute the following steps: extracting, from operating status information indicating the operating status of the machining equipment to be diagnosed, operating status information of a calculation target section that indicates a time region determined by a preset rule within a stable machining section in which the motor rotates stably; and determining whether the machining equipment to be diagnosed is normal or abnormal based on the extracted operating status information of the calculation target section.

[0077] 1 diagnostic system, 2 machining equipment, 3 machining data acquisition device, 4 signal processing device, 5 storage device, 6 diagnostic device, 7 learning model generation device, 8 status indicator, 9 control device, 99 internal bus, 11 CPU, 12 RAM, 13 ROM, 14 storage unit, 15 input unit, 16 communication unit.

Claims

1. an operation status information acquisition unit that acquires operation status information indicating an operation status of the processing equipment to be diagnosed; an extraction unit that extracts, from the operation status information acquired by the operation status information acquisition unit, operation status information of a calculation target section that indicates a time region in which an abnormality of the processing equipment is likely to occur, which is determined according to a preset rule within a stable processing section in which the motor rotates stably; a feature amount calculation unit that calculates a feature amount from the motion state information of the calculation target section extracted by the extraction unit; a diagnosis unit that determines whether the processing equipment is normal or abnormal based on the feature amount calculated by the feature amount calculation unit; A diagnostic system comprising:

2. The extraction unit divides the stable processing section of the operating status information acquired by the operating status information acquisition unit into a plurality of sections, calculates a feature value for each of the divided sections, compares the calculated feature values ​​for each of the sections, and based on a comparison result, identifies the calculation target section, and extracts operating status information for the identified calculation target section. The diagnostic system of claim 1 .

3. The extraction unit calculates the variance of the feature amount of each of the divided sections, and identifies a section having a large variance as the calculation target section. The diagnostic system of claim 2 .

4. The diagnosis unit inputs the feature amount calculated by the feature amount calculation unit into a preset machine learning model, and based on the output obtained, determines whether the processing equipment to be diagnosed is normal or abnormal. The diagnostic system according to claim 1 or 2.

5. a learning model generation unit that generates the machine learning model based on learning data including the features calculated by the feature calculation unit and label information assigned to each feature; The diagnostic system of claim 4 further comprising:

6. The diagnostic device further includes a processing identification information acquisition unit that acquires processing identification information that identifies processing content performed by the diagnostic target processing equipment, the extraction unit specifies a rule for extracting the operation state information of the calculation target section from the operation state information of the processing equipment to be diagnosed, based on correspondence information that associates the processing content with a rule for extracting the operation state information of the calculation target section, and executes the specified rule to extract the operation state information to be used in calculating the feature amount. The diagnostic system according to claim 1 or 2.

7. A control unit that controls an operation of the processing equipment to be diagnosed is further provided. When the diagnosis unit determines that the processing equipment to be diagnosed is abnormal, the diagnosis unit notifies the control unit of a determination result indicating that the processing equipment is abnormal; When the control unit receives the determination result from the diagnosis unit, the control unit stops operation of a part or all of the processing equipment to be diagnosed. The diagnostic system according to claim 1 or 2.

8. The operational status information includes a sensor output indicating a physical quantity detected by a sensor installed in the processing equipment, the extraction unit obtains a difference between the sensor output in a normal processing section and the sensor output in the abnormality occurrence section from a plurality of pieces of operation status information including operation states of the abnormality occurrence section of the processing equipment, identifies the calculation target section based on the abnormality occurrence section of the operation status information including a sensor output in which the obtained difference is large, and extracts operation status information of the identified calculation target section from the operation status information acquired by the operation status information acquisition unit. The diagnostic system according to claim 1 or 2.

9. an extraction unit that extracts, from operation status information indicating the operation status of the processing equipment to be diagnosed, operation status information of a calculation target section that indicates a time region in which an abnormality of the processing equipment is likely to occur, which is determined according to a preset rule within a stable processing section in which a motor rotates stably; a diagnosis unit that judges whether the processing equipment to be diagnosed is normal or abnormal based on the operation state information of the calculation target section extracted by the extraction unit; An information processing device comprising:

10. A step of extracting, from operation status information indicating the operation status of the processing equipment to be diagnosed, operation status information of a calculation target section indicating a time region in which an abnormality of the processing equipment is likely to occur, which is determined according to a preset rule, within a stable processing section in which a motor rotates stably; A step of determining whether the processing equipment to be diagnosed is normal or abnormal based on the extracted operation state information of the calculation target section; A diagnostic method comprising:

11. On the computer, A process of extracting, from operation status information indicating the operation status of the processing equipment to be diagnosed, operation status information of a calculation target section indicating a time region in which an abnormality of the processing equipment is likely to occur, which is determined according to a preset rule, within a stable processing section in which a motor rotates stably; A process of determining whether the processing equipment to be diagnosed is normal or abnormal based on the extracted operation state information of the calculation target section; A program that executes the following.