Anomaly detection device and anomaly detection method

Abstract

To detect wear abnormality of a tool with accuracy in real time.SOLUTION: An abnormality detection device includes: an acquisition unit which acquires time-sequence data of a measurement value relating to a tool; an estimation unit that inputs the time-sequence data of the measurement value acquired by the acquisition unit to a learned model which has been previously learned on the basis of the time-sequence data of the measurement value acquired during processing in a normal state, the learned model inputting the time-sequence data of the measurement value and outputting the time-sequence data of the measurement value, and that acquires output of the learned model; and a detection unit which compares the time-sequence data of the measurement value acquired by the acquisition unit and output of the learned model, and detects wear abnormality of the tool.SELECTED DRAWING: Figure 7

Description

[Technical Field]

[0001] The disclosed technology relates to an anomaly detection device and an anomaly detection method. [Background technology]

[0002] A method has been disclosed in the past for generating a learning model that predicts the life of a tool by applying machine learning based on sound data during machining (Patent Document 1). In this method, multiple learning models are prepared and one is selected from the multiple models depending on the state, thereby improving accuracy.

[0003] Also disclosed is a method of creating a normal model by machine learning of tool-related measurements (vibration, sound, motor current, etc.) during normal machining, and determining abnormalities based on this normal model (Patent Document 2).

[0004] Also, a method has been disclosed for predicting tool wear by generating a learning model that correlates tool sound and temperature data and tool wear data with machining conditions (Patent Document 3). [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent Publication No. 2021-071818 [Patent Document 2] Japanese Patent Application Publication No. 2019-139755 [Patent Document 3] Japanese Patent Application Publication No. 2018-024055 Summary of the Invention [Problem to be solved by the invention]

[0006] One approach is to use rule-based anomaly detection, but as systems become more diverse and sensors become more multi-channel, the amount of data becomes larger and more complex, making it impossible for workers to correctly grasp and understand the relationships between the data.

[0007] It is conceivable to perform deep learning using time-series data as input, but if feature values are extracted through preprocessing and used as input for a neural network model, offline preprocessing is required, making it impossible to perform real-time anomaly detection.

[0008] Furthermore, due to daily efforts to improve the system, there is almost no training data on abnormalities in the field, making it difficult to train a model that can accurately detect anomalies.

[0009] The disclosed technology has been made in consideration of the above points, and aims to provide an abnormality detection device and an abnormality detection method that can accurately detect abnormal wear of a tool in real time. [Means for solving the problem]

[0010] A first aspect of the present disclosure is an abnormality detection device that detects abnormal wear of a tool of a machine tool, and includes: an acquisition unit that acquires time series data of measurement values related to the tool; an estimation unit that inputs the time series data of measurement values acquired by the acquisition unit into a trained model that has been trained in advance based on the time series data of measurement values acquired during normal machining and outputs the time series data of measurement values, and acquires the output of the trained model; and a detection unit that compares the time series data of measurement values acquired by the acquisition unit with the output of the trained model to detect abnormal wear of the tool.

[0011] A second aspect of the present disclosure is an anomaly detection device that detects abnormal wear of a tool of a machine tool, and includes: an acquisition unit that acquires time series data of measurement values related to the tool; an estimation unit that inputs the time series data of measurement values acquired by the acquisition unit into a trained model including an encoder and a decoder that has been trained in advance based on the time series data of measurement values acquired during normal machining and outputs the time series data of measurement values, and acquires the output of the encoder of the trained model for each interval of the time series data of measurement values; and a detection unit that detects abnormal wear of the tool by comparing the output of the encoder of the trained model acquired for each interval of the time series data of measurement values.

[0012] A third aspect of the present disclosure is an anomaly detection method for detecting abnormal wear of a tool of a machine tool, wherein an acquisition unit acquires time series data of measurement values related to the tool, an estimation unit inputs the time series data of measurement values acquired by the acquisition unit into a trained model that has been trained in advance based on the time series data of measurement values acquired during normal machining and outputs the time series data of measurement values, and acquires an output of the trained model, and a detection unit compares the time series data of measurement values acquired by the acquisition unit with the output of the trained model to detect abnormal wear of the tool.

[0013] A fourth aspect of the present disclosure is an anomaly detection method for detecting abnormal wear of a tool of a machine tool, wherein an acquisition unit acquires time series data of measurement values related to the tool, an estimation unit inputs the time series data of measurement values that has been pre-trained based on the time series data of measurement values acquired during normal machining conditions, and outputs the time series data of measurement values, inputting the time series data of measurement values acquired by the acquisition unit into a trained model including an encoder and a decoder, and acquiring an output of the encoder of the trained model for each interval of the time series data of measurement values, and a detection unit compares the outputs of the encoder of the trained model acquired for each interval of the time series data of measurement values to detect abnormal wear of the tool. [Effects of the Invention]

[0014] According to the disclosed technology, abnormal wear of a tool can be detected accurately in real time. [Brief explanation of the drawings]

[0015] [Figure 1] FIG. 2 is a schematic block diagram of an example of a computer that functions as a model learning device and an anomaly detection device according to the first and second embodiments. [Figure 2] FIG. 2 is a diagram for explaining a strain gauge, an accelerometer, a thermocouple, and an AE sensor provided on the tool. [Figure 3] FIG. 10 is a diagram illustrating an example of time-series data of various measurement values. [Figure 4] FIG. 10 is a diagram showing an example of time-series data of an AE signal. [Figure 5] FIG. 1 is a block diagram showing the configuration of a model learning device according to a first embodiment and a second embodiment. [Figure 6] FIG. 2 is a diagram illustrating an example of a model according to the first embodiment. [Figure 7] 1 is a block diagram showing the configuration of an anomaly detection device according to a first embodiment and a second embodiment. [Figure 8] 4 is a flowchart showing an abnormality detection routine of the abnormality detection device of the first embodiment. [Figure 9] 10 is a graph showing an example of detecting wear abnormality from time-series data of an AE signal. [Figure 10] 10 is a graph showing an example of detecting abnormal wear from time-series sound data. [Figure 11] FIG. 10 is a diagram illustrating an example of a model according to the second embodiment. [Figure 12] 10 is a flowchart showing an abnormality detection routine of the abnormality detection device of the second embodiment. [Figure 13] 10 is a graph showing an example of detecting wear abnormality from time-series data of an AE signal. [Figure 14] 10 is a graph showing an example of detecting abnormal wear from time-series sound data. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of the disclosed technology will be described below with reference to the drawings. Note that the same or equivalent components and parts in each drawing are given the same reference numerals. Also, the dimensional proportions in the drawings are exaggerated for the convenience of explanation and may differ from the actual proportions.

[0017] [First embodiment] <Configuration of the model learning device according to the first embodiment> FIG. 1 is a block diagram showing the hardware configuration of a model learning device 10 according to this embodiment.

[0018] 1, a model learning device 10 includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a storage 14, an input unit 15, a display unit 16, and a communication interface (I / F) 17. Each component is connected to each other via a bus 19 so as to be able to communicate with each other.

[0019] The CPU 11 is a central processing unit that executes various programs and controls each component. That is, the CPU 11 reads a program from the ROM 12 or the storage 14 and executes the program using the RAM 13 as a work area. The CPU 11 controls the above components and performs various arithmetic processing in accordance with the program stored in the ROM 12 or the storage 14. In this embodiment, the ROM 12 or the storage 14 stores a learning program for learning a model. The learning program may be a single program, or may be a group of programs consisting of multiple programs or modules.

[0020] The ROM 12 stores various programs and various data. The RAM 13 temporarily stores programs or data as a working area. The storage 14 is configured with an HDD (Hard Disk Drive) or SSD (Solid State Drive) and stores various programs including the operating system and various data.

[0021] The input unit 15 includes a pointing device such as a mouse and a keyboard, and is used to perform various inputs.

[0022] The input unit 15 receives as input learning data, which is time-series data of measurement values related to the tool of the machine tool, acquired during machining when the tool of the machine tool is in a normal state.

[0023] 2, a strain gauge 31 provided on a tool 30 of a machine tool is used to measure the distortion of the tool 30, an accelerometer 34 provided on the tool 30 is used to measure the acceleration of the tool 30, a thermocouple 32 provided on the tool 30 is used to measure the temperature of the tool 30, a microphone (not shown) provided on the machine tool is used to measure the sound of the tool 30, and AE sensors 36 and 38 provided on the tool 30 are used to measure the AE (acoustic emission) signal of the tool 30 (see FIG. 3). FIG. 3 shows an example of time series data of distortion, acceleration, temperature, sound, and AE signal of the tool 30.

[0024] The time series data of the distortion, acceleration, temperature, sound, and AE signal of the tool 30 acquired during machining when the tool 30 is in a normal state, i.e., when there is no wear abnormality, are used as learning data (see the time series data in normal state in Fig. 4). Fig. 4 shows an example of time series data of the AE signal when the tool 30 is normal, in a transition period just before an abnormality occurs, and when an abnormality occurs.

[0025] This learning data in the normal state is prepared for each of the plurality of tools 30, and the input unit 15 receives the learning data for each of the plurality of tools 30.

[0026] The display unit 16 is, for example, a liquid crystal display, and displays various information. The display unit 16 may also function as the input unit 15 by adopting a touch panel system.

[0027] The communication interface 17 is an interface for communicating with other devices, and uses standards such as Ethernet (registered trademark), FDDI (Fiber Distributed Data Interface), Wi-Fi (registered trademark), and USB (Universal Serial Bus).

[0028] Next, a description will be given of the functional configuration of model learning device 10. Fig. 5 is a block diagram showing an example of the functional configuration of model learning device 10.

[0029] As shown in FIG. 5, the model learning device 10 functionally comprises a learning database (DB) 20, a learning unit 24, and a model storage unit 26.

[0030] The learning database 20 stores learning data for each of the input tools 30.

[0031] The learning unit 24 learns a model that receives time-series data of measurement values as input and outputs time-series data of measurement values based on the received learning data for the plurality of tools 30.

[0032] Specifically, when time-series data of measurement values, which are training data, are input to the model, the model is trained so as to output time-series data of measurement values corresponding to the training data.

[0033] More specifically, as shown in Fig. 6, model 70 is a model based on LSTM (Long Short-Term Memory) and an autoencoder, and includes an encoder 72 and a decoder 74. The encoder 72 receives, for each type of measurement value, a measurement value at each time of one interval of time-series data as input, and outputs encoded data. The decoder 74 receives, for each type of measurement value, encoded data and decodes it into a measurement value at each time of one interval of time-series data.

[0034] The model storage unit 26 stores the trained model.

[0035] <Configuration of an abnormality detection device according to the first embodiment> FIG. 1 is a block diagram showing the hardware configuration of an abnormality detection device 50 of this embodiment.

[0036] As shown in FIG. 1, the anomaly detection device 50 has the same configuration as the model learning device 10, and the ROM 12 or the storage 14 stores an anomaly detection program for detecting wear abnormalities in a tool.

[0037] The input unit 15 receives as input time-series data of measurement values related to the tool 30. Specifically, the strain of the tool 30 is measured using a strain gauge 31 provided on the tool 30 of the machine tool, the acceleration of the tool 30 is measured using an accelerometer 34 provided on the tool 30, the temperature of the tool 30 is measured using a thermocouple 32 provided on the tool 30, the sound of the tool 30 is measured using a microphone (not shown) provided on the machine tool, and the AE (acoustic emission) signal of the tool 30 is measured using AE sensors 36, 38 provided on the tool 30.

[0038] The input unit 15 receives as input time series data of tool distortion, time series data of acceleration, time series data of temperature, time series data of sound, and time series data of AE signals, which are acquired during tool machining.

[0039] Next, a description will be given of the functional configuration of the anomaly detection device 50. FIG.

[0040] As shown in FIG. 7, the anomaly detection device 50 functionally comprises a model storage unit 60, an acquisition unit 62, an estimation unit 64, and a detection unit 66.

[0041] The model storage unit 60 stores the trained model trained by the model training device 10.

[0042] The acquisition unit 62 acquires time-series data of the input measurement values related to the tool 30 .

[0043] The estimation unit 64 inputs the time series data of the measurement values acquired by the acquisition unit 62 into the trained model and acquires the output of the trained model.

[0044] Specifically, for each type of measurement value, the measurement value at each time of one interval of time-series data is input to the encoder 72, and the measurement value at each time of one interval of time-series data decoded by the decoder 74 is obtained.

[0045] The detection unit 66 compares the time-series data of the measurement values acquired by the acquisition unit 62 with the output of the trained model to detect abnormal wear of the tool 30.

[0046] Specifically, the detection unit 66 calculates an abnormality score for each interval of the time series data using an error value that is the sum of the differences between the measurement values and the output of the trained model, and detects wear abnormalities in the tool 30 based on the abnormality score for each interval.

[0047] More specifically, for each time t in one interval, the difference a(t) between the measurement value x(t) and the output ^y(t) of the trained model is calculated according to the following formula, and the error value ε(t) is calculated by summing up the differences a(t) for one interval.

[0048] JPEG0007723926000001.jpg1381 JPEG0007723926000002.jpg1853

[0049] Then, the error value ε(t) of the section is used to calculate the abnormality score S(t) according to the following formula.

[0050] JPEG0007723926000003.jpg1689

[0051] Here, α and β are predetermined values.

[0052] The detection unit 66 detects a wear abnormality in the tool 30 when the abnormality score S(t) for each section is equal to or greater than a threshold value.

[0053] <Operation of the model learning device according to the first embodiment> Next, the operation of the model learning device 10 according to this embodiment will be described.

[0054] First, the CPU 11 of the model learning device 10 reads out a learning program from the ROM 12 or storage 14, expands it into the RAM 13, and executes it, thereby performing a learning process. Furthermore, learning data for each of the multiple tools 30 is input to the model learning device 10 and stored in the learning database 20.

[0055] Then, the CPU 11, as the learning unit 24, learns a model that takes time series data of measurement values as input and outputs time series data of measurement values based on the received learning data for the multiple tools 30, stores the learned model in the model memory unit 26, and terminates the learning process.

[0056] <Action of the anomaly detection device according to the first embodiment> Next, the operation of the abnormality detection device 50 according to this embodiment will be described.

[0057] 8 is a flowchart showing the flow of an anomaly detection process performed by the anomaly detection device 50. The CPU 11 reads an anomaly detection program from the ROM 12 or the storage 14, deploys it in the RAM 13, and executes it to perform the anomaly detection process. Time-series data of measurement values related to the tool 30 is also input to the anomaly detection device 50. The anomaly detection process is an example of an anomaly detection method.

[0058] In step S100, the CPU 11 functions as the acquisition unit 62 and acquires time-series data of input measurement values related to the tool 30 for one section.

[0059] In step S102, the CPU 11, functioning as the estimation unit 64, inputs the time-series data for one interval acquired by the acquisition unit 62 to the trained model, and acquires the output of the trained model.

[0060] Specifically, the measured value at each time of one interval of time-series data is input to the encoder 72, and the measured value at each time of one interval of time-series data decoded by the decoder 74 is obtained.

[0061] In step S104, the CPU 11, functioning as the detection unit 66, calculates an error value by summing up the differences between the measurement values and the outputs of the trained model in the one section.

[0062] In step S106, the CPU 11 as the detection unit 66 calculates an abnormality score for the one section using the error value.

[0063] In step S108, the CPU 11, functioning as the detection unit 66, determines whether the abnormality score is equal to or greater than the threshold. If the abnormality score is less than the threshold, the process returns to step S100, and the processes of steps S100 to S108 are repeated for the time-series data of the next section. On the other hand, if the abnormality score is equal to or greater than the threshold, the process proceeds to step S110.

[0064] In step S110, the CPU 11 outputs a message indicating that the tool 30 is abnormally worn on the display unit 16, and ends the abnormality detection process.

[0065] Example 1 An example of detecting wear abnormalities using the model learning device 10 and the abnormality detection device 50 of the first embodiment described above will be described.

[0066] Figures 9(A) and (B) show examples of the measurement value x(t), the output ^y(t) of the trained model, the difference a(t), the error value ε(t), and the anomaly score S(t) when time series data of an AE signal is input.

[0067] As shown in Figure 9(A), it can be seen that an anomaly is detected in the transient period before the anomaly occurs. In Figure 9(B), it can be seen that the anomaly score S(t) is equal to or greater than the threshold for an unpredictable event. For such unpredictable events, anomalies can be detected with high accuracy by performing processing such as noise removal on the anomaly score S(t).

[0068] Figures 10(A) and (B) show examples of the measurement value x(t), the output ^y(t) of the trained model, the difference a(t), the error value ε(t), and the anomaly score S(t) when sound time series data is input.

[0069] As shown in FIGS. 10(A) and 10(B), it can be seen that an abnormality is detected in the transient period before the abnormality occurs.

[0070] As described above, the anomaly detection device according to the first embodiment inputs the time-series data of acquired measurement values into a trained model that has been trained in advance based on the time-series data of measurement values acquired during machining in a normal state, obtains the output of the trained model, and compares the time-series data of acquired measurement values with the output of the trained model to detect abnormal tool wear. This enables accurate detection of abnormal tool wear in real time.

[0071] [Second embodiment] Next, a second embodiment will be described. Note that the configurations of the learning device and the anomaly detection device according to the second embodiment are the same as those of the first embodiment, so the same reference numerals are used and the description will be omitted.

[0072] In the second embodiment, the configuration of the model is different from that in the first embodiment.

[0073] <Configuration of the model learning device according to the second embodiment> The learning unit 24 of the model learning device 10 according to the second embodiment learns a model that receives time-series data of measurement values as input and outputs time-series data of measurement values, based on received learning data for a plurality of tools 30.

[0074] Specifically, when time-series data of measurement values, which are training data, are input to the model, the model is trained so as to output time-series data of measurement values corresponding to the training data.

[0075] 11(A), model 270 is a model based on an autoencoder and includes an encoder 272 and a decoder 274. Encoder 272 receives, for each type of measurement value, a measurement value at each time of one interval of time-series data as input, and outputs encoded data. Decoder 274 receives, for each type of measurement value, encoded data and decodes it into a measurement value at each time of one interval of time-series data.

[0076] <Configuration of an abnormality detection device according to the second embodiment> The anomaly detection device 50 according to the second embodiment functionally comprises a model storage unit 60, an acquisition unit 62, an estimation unit 64, and a detection unit 66, as shown in FIG.

[0077] The model storage unit 60 stores the trained model trained by the model training device 10.

[0078] The acquisition unit 62 acquires time-series data of the input measurement values related to the tool 30 .

[0079] The estimation unit 64 inputs the time series data of the measurement values acquired by the acquisition unit 62 into the trained model, and acquires the output of the encoder 272 of the trained model as a feature for each section of the time series data of the measurement values.

[0080] Specifically, for each type of measurement value, the measurement value at each time of one interval of time-series data is input to the encoder 72, and the encoded data output from the encoder 72 is obtained as a feature.

[0081] The detection unit 66 detects abnormal wear of the tool 30 by comparing the outputs of the encoder 272 of the trained model acquired for each section of the time-series data of the measurement values.

[0082] Specifically, for each type of measurement value, the detection unit 66 calculates an anomaly score for each interval of the time-series data using the local density of the output of the trained model encoder 272 acquired for that interval and the output of the trained model encoder 272 acquired during normal machining, and detects wear abnormalities in the tool 30 based on the anomaly score for each interval. Here, the output of the trained model encoder 272 acquired during normal machining is the output of the trained model encoder 272 acquired for an interval prior to the interval in which wear abnormalities in the tool 30 were not detected.

[0083] 11(B), for each section, the local density ratio between the output of the encoder 272 of the trained model acquired for that section and the output of the encoder 272 of the trained model acquired during processing in a normal state is calculated using the local outlier factor (LOF).The local density ratio for that section is then normalized to calculate the anomaly score. JPEG0007723926000004.jpg50164 However, N k(P) is a set of outputs of the encoder 272 obtained for the section before the current section, and reachability_distance k(P,A) is the distance to the output A of the k neighbors, and lrd k(P) is the local density and lof(P) is the local density ratio.

[0084] The detection unit 66 detects a wear abnormality in the tool 30 when the abnormality score for each section is equal to or greater than the threshold value.

[0085] <Operation of the model learning device according to the second embodiment> Next, the operation of the model learning device 10 according to this embodiment will be described.

[0086] First, the CPU 11 of the model learning device 10 reads out a learning program from the ROM 12 or storage 14, expands it into the RAM 13, and executes it, thereby performing a learning process. Furthermore, learning data for each of the multiple tools 30 is input to the model learning device 10 and stored in the learning database 20.

[0087] Then, the CPU 11, as the learning unit 24, learns a model that takes time series data of measurement values as input and outputs time series data of measurement values based on the received learning data for the multiple tools 30, stores the learned model in the model memory unit 26, and terminates the learning process.

[0088] <Action of the anomaly detection device according to the second embodiment> Next, the operation of the abnormality detection device 50 according to this embodiment will be described.

[0089] 12 is a flowchart showing the flow of an abnormality detection process by the abnormality detection device 50. The abnormality detection process is performed by the CPU 11 reading out an abnormality detection program from the ROM 12 or the storage 14, expanding it into the RAM 13, and executing it. In addition, time-series data of measurement values related to the tool 30 is input to the abnormality detection device 50.

[0090] In step S200, the CPU 11 functions as the acquisition unit 62 and acquires time-series data of input measurement values related to the tool 30 for one section.

[0091] In step S202, the CPU 11, functioning as the estimation unit 64, inputs the time-series data for one section acquired by the acquisition unit 62 to the trained model, and acquires the output of the encoder 272 of the trained model as a feature.

[0092] Specifically, the measured values at each time of one interval of time-series data are input to the encoder 272, and the encoded data output from the encoder 272 is acquired as the feature amount.

[0093] In step S204, the CPU 11, as the detection unit 66, calculates the local density ratio between the feature that is the output of the encoder 272 of the trained model acquired for that one section and the feature that is the output of the encoder 272 of the trained model acquired during processing in a normal state.

[0094] In step S206, the CPU 11 as the detection unit 66 calculates an anomaly score for the one section using the local density ratio.

[0095] In step S208, the CPU 11, functioning as the detection unit 66, determines whether the abnormality score is equal to or greater than the threshold. If the abnormality score is less than the threshold, the process returns to step S200, and the processes of steps S200 to S208 are repeated for the time-series data of the next interval. On the other hand, if the abnormality score is equal to or greater than the threshold, the process proceeds to step S210.

[0096] In step S210, the CPU 11 outputs a message indicating that the tool 30 is abnormally worn on the display unit 16, and ends the abnormality detection process.

[0097] <Example 2> An example of detecting wear abnormalities using the model learning device 10 and the abnormality detection device 50 of the second embodiment described above will be described.

[0098] Figures 13(A) and (B) show examples of measurement values when time-series data of an AE signal is input, the results of performing envelope processing on the measurement values, the average value of the results, and the anomaly score when the average value is input to the trained model. The closer the anomaly score value is to 1, the more abnormal it is. As shown in Figures 13(A) and (B), it can be seen that an anomaly is detected in the transient period before the anomaly occurs.

[0099] Figures 14(A) and (B) show examples of measurement values and anomaly scores when sound time-series data is input. As shown in Figures 14(A) and (B), it can be seen that an anomaly is detected in the transient period before the anomaly occurs.

[0100] As described above, the anomaly detection device according to the second embodiment inputs the time-series data of acquired measurement values into a trained model that has been trained in advance based on the time-series data of measurement values acquired during machining in a normal state, acquires the encoder output of the trained model for each interval of the time-series data of measurement values, and compares the encoder output of the trained model acquired for each interval of the time-series data of measurement values to detect abnormal tool wear. This enables accurate detection of abnormal tool wear in real time.

[0101] The normal, transitional, and abnormal periods in Figures 13 and 14 above are determined by the on-site worker, and experienced on-site workers generally tend to change tools with ample time to spare, so they change tools towards the end of normal operation.

[0102] On the other hand, in this embodiment, an abnormality is detected once the transition period has begun, and by replacing the tool when the abnormality detection device detects an abnormality, the tool can be used longer than the operator. Specifically, the tool life can be extended by about 40 seconds, which is equivalent to 15 to 20% of the tool life, and when the reduction in downtime of the machine tool is also taken into account, the utilization rate of the machine and tool can be improved by nearly 30%.

[0103] Furthermore, as can be seen from the results of abnormality detection by the abnormality detection device, even if new tools of the same model number are used, the tool lifespans are different for each tool, and the timing of abnormality detection will differ, and the abnormality detection device of this embodiment can also handle these cases.

[0104] <Modification> The present invention is not limited to the above-described embodiment, and various modifications and applications are possible without departing from the spirit and scope of the present invention.

[0105] For example, although the example has been described in which the model learning device and the anomaly detection device are configured as separate devices, this is not limited to this, and the model learning device and the anomaly detection device may be configured as a single device.

[0106] Furthermore, various processes executed by the CPU after reading software (programs) in the above embodiments may be executed by various processors other than the CPU. Examples of such processors include dedicated electrical circuits, such as a graphics processing unit (GPU), a programmable logic device (PLD) whose circuit configuration can be changed after manufacture, such as a field-programmable gate array (FPGA), and an application-specific integrated circuit (ASIC), which are processors having a circuit configuration specifically designed to execute specific processes. Furthermore, the learning process and the anomaly detection process may be executed by one of these various processors, or may be executed by a combination of two or more processors of the same or different types (e.g., multiple FPGAs, or a combination of a CPU and an FPGA). Furthermore, the hardware structure of these various processors is, more specifically, an electrical circuit that combines circuit elements such as semiconductor elements.

[0107] In addition, in each of the above embodiments, the learning program and the anomaly detection program are described as being pre-stored (installed) in the storage 14, but the present invention is not limited to this. The programs may be provided in a form stored in a non-transitory storage medium such as a CD-ROM (Compact Disk Read Only Memory), a DVD-ROM (Digital Versatile Disk Read Only Memory), or a USB (Universal Serial Bus) memory. The programs may also be downloaded from an external device via a network. [Explanation of symbols]

[0108] 10 Model learning device 11 CPU 14. Storage 15 Input section 16 Display section 20 Learning Database 24 Learning Department 26 Model memory section 30 Tools 31 Strain gauge 34 Accelerometer 32 Thermocouple 36, 38 AE sensor 50 Anomaly detection device 60 Model memory section 62 Acquisition Department 64 Estimation part 66 Detection unit 70, 270 models 72, 272 encoder 74, 274 decoder

Claims

1. An abnormality detection device that detects abnormal wear of a tool of a machine tool, an acquisition unit that acquires time series data of measurement values related to the tool; an estimation unit that inputs the time series data of the measurement values acquired by the acquisition unit into a trained model that has been trained in advance based on the time series data of the measurement values acquired during processing in a normal state and outputs the time series data of the measurement values, and acquires an output of the trained model; a detection unit that compares the time series data of the measurement values acquired by the acquisition unit with an output of the trained model to detect wear abnormalities of the tool; Including, The detection unit calculates an abnormality score for each interval of the time series data using an error value that is the sum of the differences between the measurement values at each time of the interval and the output of the trained model, and detects abnormal wear of the tool when the abnormality score for each interval is equal to or greater than a threshold.

2. The acquisition unit acquires time series data of measurement values for each type of measurement value related to the tool, which is at least two or more types of distortion, acceleration, temperature, sound, and AE (acoustic emission) of the tool, the estimation unit inputs the time series data of the measurement values acquired by the acquisition unit into a trained model that has been trained in advance for each type of measurement value based on the time series data of the measurement values acquired during processing in a normal state, and outputs the time series data of the measurement values, and acquires an output of the trained model; 2. The anomaly detection device according to claim 1, wherein the detection unit calculates, for each type of measurement value, an anomaly score for each interval of the time series data using an error value that is the sum of the differences between the measurement value at each time point in the interval and the output of the trained model, and detects wear abnormality in the tool when the anomaly score for each interval is equal to or greater than a threshold value.

3. The anomaly detection device according to claim 1 , wherein the trained model includes an encoder and a decoder.

4. An abnormality detection device that detects abnormal wear of a tool of a machine tool, an acquisition unit that acquires time series data of measurement values related to the tool; an estimation unit that inputs the time series data of the measurement values acquired by the acquisition unit into a trained model including an encoder and a decoder that has been trained in advance based on the time series data of the measurement values acquired during processing in a normal state and that outputs the time series data of the measurement values, and acquires the output of the encoder of the trained model for each section of the time series data of the measurement values; a detection unit that detects abnormal wear of the tool by comparing, for each section of the time-series data of the measurement values, the output of the encoder of the trained model acquired for that section with the output of the encoder of the trained model acquired during normal machining; Including, The detection unit calculates an abnormality score for each interval of the time series data using a local density ratio between the output of the encoder of the trained model obtained for that interval and the output of the encoder of the trained model obtained during normal processing, and detects abnormal wear of the tool when the abnormality score for each interval is equal to or greater than a threshold.

5. The acquisition unit acquires time series data of measurement values for each type of measurement value related to the tool, which is at least two or more types of distortion, acceleration, temperature, sound, and AE (acoustic emission) of the tool, the estimation unit inputs the time series data of the measurement values acquired by the acquisition unit into a trained model including an encoder and a decoder that has been trained in advance based on the time series data of the measurement values acquired during processing in a normal state for each type of measurement value and outputs the time series data of the measurement values, and acquires an output of the encoder of the trained model for each section of the time series data of the measurement values; 5. The anomaly detection device according to claim 4, wherein the detection unit calculates an anomaly score for each type of measurement value in each interval of the time series data using a local density ratio between the output of the encoder of the trained model acquired for that interval and the output of the encoder of the trained model acquired during machining in a normal state, and detects wear abnormality in the tool when the anomaly score for that interval is equal to or greater than a threshold.

6. 5. The abnormality detection device according to claim 1, wherein the measured value is distortion, acceleration, temperature, sound, or acoustic emission (AE) of the tool.

7. An abnormality detection method for detecting abnormal wear of a tool of a machine tool, comprising: an acquisition unit acquires time series data of measurement values related to the tool; an estimation unit inputs the time series data of the measurement values acquired by the acquisition unit into a trained model that has been trained in advance based on the time series data of the measurement values acquired during processing in a normal state and that outputs the time series data of the measurement values, and acquires an output of the trained model; A detection unit compares the time-series data of the measurement values acquired by the acquisition unit with an output of the trained model to detect abnormal wear of the tool. This includes: The detection unit calculates an abnormality score for each interval of the time series data using an error value obtained by summing up the differences between the measurement values at each time of the interval and the output of the trained model, and detects wear abnormality of the tool when the abnormality score for each interval is equal to or greater than a threshold value. Anomaly detection methods.

8. An abnormality detection method for detecting abnormal wear of a tool of a machine tool, comprising: an acquisition unit acquires time series data of measurement values related to the tool; an estimation unit inputs the time series data of the measurement values acquired by the acquisition unit into a trained model including an encoder and a decoder, the trained model having been trained in advance based on the time series data of the measurement values acquired during processing in a normal state, and outputs the time series data of the measurement values, and acquires an output of the encoder of the trained model for each section of the time series data of the measurement values; The detection unit compares the output of the encoder of the trained model acquired for each section of the time-series data of the measurement values with the output of the encoder of the trained model acquired during machining in a normal state, and detects abnormal wear of the tool. This includes: The detection unit calculates an abnormality score for each interval of the time series data using a local density ratio between the output of the encoder of the trained model obtained for that interval and the output of the encoder of the trained model obtained during normal processing, and detects abnormal wear of the tool for each interval if the abnormality score for that interval is equal to or greater than a threshold.

Images