Part anomaly detection method and device based on generative adversarial network

Abstract

A part anomaly detection method based on a generative adversarial network (GAN) includes: deducing a first anomaly score of an input data through a noise reduction auto-encoder, including: extracting a manifold coordinate of the input data, and calculating a distance between the manifold coordinate and a normal data average coordinate as the first anomaly score; deducing a second abnormal score of the input data through a discriminator; and adding the first abnormal score and the second abnormal score to calculate an abnormal degree of the input data. The invention further relates to a device for part anomaly detection.

Description

Technical Field

[0001] The present disclosure relates to a method and device for detecting anomalies, and in particular to a method and device for detecting anomalies of parts based on a generative adversarial network (GAN). Background Art

[0002] In the process of detecting whether machine parts are abnormal, the following problems are mainly encountered:

[0003] (1) Since most of the data that can be collected in industrial applications is generated under normal operation, the amount of positive / abnormal data is uneven.

[0004] (2) Due to changes in production factors such as work orders, molds, and materials, a continuous production process will include multiple working conditions. Being in different working conditions will cause the AI ​​model to have certain difficulties in distinguishing between normal and abnormal states.

[0005] (3) The training data of supervised algorithms needs to have clear labels (e.g., the type of factor causing the anomaly). In industrial applications, many anomalies rarely occur or have never occurred. Unsupervised algorithms have better adaptability, but some unsupervised algorithms cannot adapt to problems under various working conditions.

[0006] In the case of an imbalance in the amount of positive / abnormal data, the AI ​​model training performance will be poor due to the small amount of abnormal data available. In addition, since machine parts have a variety of working conditions, most algorithms cannot effectively identify the actual abnormal state.

[0007] Therefore, a method and device for detecting anomalies of parts based on a generative adversarial network are needed to improve the above problems. Summary of the invention

[0008] Therefore, the main purpose of the present invention is to provide a method and device for detecting part anomalies based on a generative adversarial network.

[0009] The present disclosure proposes a part anomaly detection method for use in an industrial automation system, comprising: inferring a first anomaly score of input data through a denoising autoencoder, comprising: extracting a manifold coordinate of the input data, and calculating a distance between the manifold coordinate and an average coordinate of normal data as the first anomaly score; generating a second anomaly score of the input data through a discriminator; and adding the first anomaly score and the second anomaly score to calculate an abnormality degree of the input data.

[0010] The present disclosure provides a part anomaly detection device, comprising: a processor; and a computer storage medium, coupled to the processor and configured to store computer-readable instructions for instructing the processor to execute the part anomaly detection method.

[0011] Based on the Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP), the present invention uses a denoising autoencoder to replace the generator of WGAN-GP and retains the discriminator of WGAN-GP to form an AI model architecture. The part anomaly detection method and device based on the generative adversarial network disclosed in the present invention have the following advantages:

[0012] (1) The denoising autoencoder can extract the manifold coordinates of the input data. When the dimension of the input data is higher and different, the overlap probability of the manifold coordinates is lower, so the discrimination is higher. Therefore, in industrial automation applications, when machine parts face complex working conditions, the part anomaly detection method and device based on the generative adversarial network disclosed in the present invention have a higher discrimination.

[0013] (2) The AI ​​model architecture disclosed in the present invention utilizes both a denoising autoencoder and a discriminator to perform inference, which can improve discrimination. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 Schematic diagram of a parts anomaly detection system according to an embodiment of the present disclosure.

[0015] Figure 2 Schematic diagram of a model training system according to an embodiment of the present disclosure.

[0016] Figure 3 Schematic diagram of an inference system according to an embodiment of the present disclosure.

[0017] Figure 4 Flowchart of a method for training an AI model according to an embodiment of the present disclosure.

[0018] Figure 5 The figure is a flowchart of a method for detecting anomalies according to an embodiment of the present disclosure.

[0019] Figure 6 4 is a data characteristic coordinate diagram of manifold coordinates according to an embodiment of the present disclosure.

[0020] Figure 7 is a schematic diagram of an electronic device according to an embodiment of the present disclosure.

[0021] Description of reference numerals:

[0022] 10: Parts abnormality detection system

[0023] 110: Belt

[0024] 112: Driving wheel

[0025] 12: Variable frequency drive

[0026] 13: Controller

[0027] 20: Model training system

[0028] 21: Data preprocessing module

[0029] 22: Model training module

[0030] 23: Denoising Autoencoder

[0031] 24: Discriminator

[0032] 25: Noise Generator

[0033] 26: First objective function

[0034] 27: Second objective function

[0035] 28: Data collection module

[0036] 30: Inference System

[0037] 31: Data preprocessing module

[0038] 32: AI Model

[0039] 33: Denoising Autoencoder

[0040] 34: Discriminator

[0041] 35: Numerical Converter

[0042] 36: Subtractor

[0043] 37: Adder

[0044] 40: Training AI Model Methods

[0045] S41~S48: Steps

[0046] 50: Parts Abnormality Detection Method

[0047] S51, S52, S53, S11, S12, S13, S14: Steps

[0048] 60: Data characteristic coordinate diagram

[0049] 70: Electronic devices

[0050] 71: Memory

[0051] 72: Processor

[0052] 73: Display components

[0053] 74: I / O ports

[0054] 75: Peripheral components

[0055] 76: Power supply

[0056] 77: Bus

[0057] 78: Program code DETAILED DESCRIPTION

[0058] The disclosed embodiment provides a method and device for detecting abnormal parts based on a generative adversarial network. In industrial automation applications, when abnormal data is not easily available, an AI model architecture based on a generative adversarial network (GAN) is trained with normal training data to solve the problem of difficulty in distinguishing normal / abnormal states in various working situations.

[0059] Figure 1 Schematic diagram of a part anomaly detection system 10 according to an embodiment of the present disclosure. The part anomaly detection system 10 includes a belt 110, a plurality of drive wheels 112, a variable frequency drive (VFD) 12 and a controller 13, wherein the controller 13 can be installed with an inference system 30.

[0060] like Figure 1 As shown, the belt 110 is wound around a plurality of drive wheels 112, and the plurality of drive wheels 112 are connected to and controlled by a motor (not shown), and the motor is connected to and controlled by a variable frequency drive 12. When the motor continues to run and drives the belt 110, the controller 13 collects part parameters (e.g., motor current, motor torque, motor speed, and motor operating parameters such as operating cycle) through the variable frequency drive 12 to generate a corresponding data set. The inference system 30 is configured to perform online inference based on the input real-time data to predict the degree of abnormality of the part.

[0061] Generally speaking, the inference system 30 must be trained before it can infer the abnormality of the part. In this embodiment, the inference system 30 is trained by the controller 13, wherein the inference system 30 receives the part parameters to generate a data set and performs training based on the data set. In one embodiment, the controller 13 outputs the data set to an external device, and the inference system 30 is trained by the external device (e.g. Figure 7The inference system 30 is trained by an external device 70, and then the external device outputs the trained inference system 30 to the controller 13 for online inference. In another embodiment, the controller 13 outputs the data set to the external device, the inference system 30 is trained by the external device, and online inference is performed in the external device. The advantage of training the inference system 30 by an external device is that a higher performance computer or processor can be selected to speed up the training process. The inference system 30 can be stored in a memory built into or external to the controller 13 or the external device.

[0062] In one embodiment, the controller 13 may be, for example, a central processing unit (CPU), a micro control unit (MCU), a system on chip (SoC) or a programmable logic controller (PLC), but is not limited thereto.

[0063] Figure 2 2 is a schematic diagram of a model training system 20 according to an embodiment of the present disclosure. The model training system 20 includes a data collection module 28, a data preprocessing module 21, and a model training module 22. The model training system 20 can be installed on the controller 13 or an external training device (e.g. Figure 7 electronic device 70).

[0064] In the data collection module 28, relevant historical data for model training must be collected before model training is performed. Taking motor operation as an example, motor current, motor torque, motor speed, and operation cycle can be collected as historical data. In one embodiment, the relevant historical data is numerical data or images. A portion of the historical data can be used as training data, and another portion can be used as test data.

[0065] The data preprocessing module 21 is configured to perform statistical analysis on the training data and the test data to obtain statistical values. Next, the data preprocessing module 21 is configured to select multiple influential features from the statistical values ​​to generate a feature set (Feature Set) for subsequent model training and testing. Specifically, when performing model training and online inference, the data preprocessing module 21 is configured to delete parameters and data that do not match the feature set, and retain parameters and data that match the feature set, so that this data is used as input data in the model training module 22 and the inference system 30.

[0066] The model training module 22 includes a denoising auto-encoder (DAE) 23, a discriminator 24, a noise generator 25, a first objective function 26 and a second objective function 27, wherein the denoising auto-encoder 23 and the discriminator 24 conform to a deep neural network (DNN) model architecture.

[0067] In operation, the noise generator 25 adds noise to normal data to generate a noisy data, and then outputs the noisy data to the denoising autoencoder 23. The denoising autoencoder 23 is an initial denoising autoencoder configured to convert the noisy data into a generated data, and input the generated data to the discriminator 24.

[0068] The discriminator 24 is an initial discriminator, configured to generate a discriminant value Dg of the generated data and a discriminant value Dn of the real data, respectively, and feed them back to the denoising autoencoder 23, wherein the discriminant values ​​Dg and Dn are arbitrary real numbers, indicating the degree to which the input data is real. Our experimental results show that this real number range falls between 1 and -1. The closer this real number is to 1, the higher the degree to which the input data is regarded as real data; the closer this real number is to -1, the higher the degree to which the input data is regarded as generated data. The discriminator 24 calculates the first expected value based on the discriminant values ​​Dg and Dn, and adjusts the parameters to achieve the maximized first objective function 26. Through multiple trainings, the performance of the discriminator 24 can be gradually optimized. The denoising autoencoder 23 calculates the second expected value based on the fed-back discriminant values ​​Dg and Dn, adjusts the parameters, and then conducts the next training to achieve the minimized second objective function 27. Through multiple trainings, the performance of the denoising autoencoder 23 can be gradually optimized.

[0069] Furthermore, the generated data and the real data (i.e., normal data) are input to the discriminator 24 to generate the discriminant values ​​Dg and Dn, and the first and second expected values ​​are calculated, so that the denoising autoencoder 23 and the discriminator 24 adjust the parameters according to their respective objective functions, wherein the formula of the first objective function 26 of the discriminator 24 is as follows:

[0070]

[0071] The formula of the second objective function 27 of the denoising autoencoder 23 is as follows:

[0072]

[0073] P data , P DAE are the probability distributions of real data (i.e. normal data) and generated data, respectively. are the expected values ​​of the real data and the generated data, respectively. The purpose of the first objective function 26 is to maximize the difference between the identification values ​​Dg and Dn, that is, the discriminator 24 has a better ability to distinguish between real data and synthetic data, while the purpose of the second objective function 27 is to minimize the difference between the identification values ​​Dg and Dn, that is, the generated data is closer to the real data, resulting in the discriminator 24 being unable to effectively distinguish. In addition, a penalty term is added to improve the problem that the previous GAN often fails to converge during training.

[0074] Specifically, the discriminator 24 refers to the first objective function max D To adjust the parameters, after multiple parameter iterations, the discriminator 24 can be gradually optimized; the denoising autoencoder 23 refers to the second objective function min DAE To adjust the parameters, the denoising autoencoder 23 can be gradually optimized after multiple parameter iterations. The parameter adjustment will continuously repeat the following steps, including: (1) fixing the parameters of the denoising autoencoder 23 and adjusting the parameters of the discriminator 24 until the discrimination gap is maximized; (2) fixing the parameters of the discriminator 24 and adjusting the parameters of the denoising autoencoder 23 until the discrimination gap is minimized.

[0075] Figure 3 3 is a schematic diagram of an inference system 30 according to an embodiment of the present disclosure. The inference system 30 includes a data preprocessing module 31 and an AI model 32, wherein the AI ​​model 32 includes a noise reduction autoencoder 33, a discriminator 34, a value converter 35, a subtractor 36 and an adder 37. The inference system 30 can be installed in the controller 13 or an external detection device (e.g. Figure 7 electronic device 70).

[0076] In operation, the inference system 30 obtains real-time data of the machine parts through the controller 13; taking the operation of the motor as an example, the motor current, motor torque, motor speed and operation cycle can be collected as real-time data. The data preprocessing module 31 preprocesses the real-time data 310 to generate input data to the noise reduction autoencoder 33 and the discriminator 34. The noise reduction autoencoder 33 and the discriminator 34 are both Figure 2The trained denoising autoencoder and discriminator. The denoising autoencoder 33 is configured to extract the manifold coordinates (Manifold) of the input data, and then the subtractor 36 calculates the distance between the manifold coordinates and the average coordinates of the normal data as the first anomaly score. In one embodiment, the dimension of the manifold coordinates corresponds to the number of nodes in the hidden layer of the denoising autoencoder. The discriminator 34 infers the discriminant value D(x) of the real-time data, where the discriminant value D(x) is an arbitrary real number. The larger the discriminant value D(x), the greater the similarity between the input data and the normal data; and the smaller the discriminant value D(x), the smaller the similarity between the input data and the normal data. The discriminant value D(x) can be expressed by the following formula:

[0077] D(x)=W×x+b

[0078] Where D(x) represents the judgment result of the discriminator 34 on the input data x, W refers to the weight matrix of the last layer of the neural network, and b is the bias. The role of the bias is to introduce an additional parameter into the discriminator 34 so that the discriminator 34 can better fit the input data to improve performance, where the bias b is usually initialized to a small constant. The discriminator 34 will finally convert the judgment result through an activation function and obtain the identification value, where the activation function can be a linear function.

[0079] The numerical converter 35 is configured to convert the identification value D(x) into a second anomaly score. In order to make the size of the identification value D(x) intuitively represent the similarity between the input data and the normal data, in one embodiment, the numerical converter 35 multiplies the identification value D(x) by -1 to convert it into the second anomaly score. In another embodiment, the numerical converter 35 subtracts the identification value D(x) from a preset value to convert it into the second anomaly score. In another embodiment, when the identification value D(x) is greater than zero and less than 1, the numerical converter 35 takes the reciprocal of the identification value D(x) as the second anomaly score. Finally, the adder 37 adds the first anomaly score and the second anomaly score to calculate the degree of anomaly of the input data. The larger the value of the degree of anomaly, the greater the degree of anomaly between the input data and the normal data; conversely, the smaller the value of the degree of anomaly, the smaller the degree of anomaly, the smaller the degree of anomaly.

[0080] It is worth noting that although Figures 1 to 3 The object of abnormal detection is a motor as an example, but the present disclosure should not be limited to this. As an example, the present disclosure can also be applied to a computer numerical control (CNC) milling machine process. The tool condition, feed rate, clamping pressure and other values ​​of the parts collected from the CNC machine can be used to determine whether the wear state of the parts is normal or abnormal.

[0081] Figure 4 FIG. 4 is a flowchart of a method 40 for training an AI model according to an embodiment of the present disclosure. The method 40 for training an AI model may be Figure 1 The controller 13 or Figure 7 The process is performed by the electronic device 70 and includes the following steps.

[0082] Step S41: inferring identification values ​​of multiple sets of input data through the identifier, wherein the multiple sets of input data include real data and generated data.

[0083] Step S42: using the identification values ​​of the real data and the generated data, obtain a first expected value and calculate a first objective function.

[0084] Step S43: Determine whether the first objective function is maximized, if so, proceed to step S45; if not, proceed to step S44.

[0085] Step S44: fix the denoising autoencoder parameters and adjust the discriminator parameters. Return to step S41.

[0086] Step S45: The discriminator is used to infer the discriminant values ​​of the real data and the generated data, and the discriminant values ​​are fed back to the denoising autoencoder to calculate the second expected value.

[0087] Step S46: Obtain a second expected value and calculate a second objective function.

[0088] Step S47: Determine whether the second objective function is minimized. If so, end; if not, proceed to step S48.

[0089] Step S48: fix the discriminator parameters and adjust the parameters of the denoising autoencoder. Return to step S45.

[0090] Steps S41, S42, S43, S44, and S45 may be performed by the discriminator 24, steps S45, S46, S47, and S48 may be performed by the denoising autoencoder 23, and steps S42 and S46 may be performed by the first and second objective functions. In one embodiment, after step S48, the controller 13 or the processor may determine whether to return to step S41 for training again. By repeatedly executing the training AI model method 40, the AI ​​model can be gradually optimized. Figure 2 The performance of the denoising autoencoder 23 and the discriminator 24 is applied to Figure 3 The denoising autoencoder 33 and the discriminator 34 in the AI ​​model 32.

[0091] Figure 5 FIG. 5 is a flow chart of a method 50 for detecting abnormal parts based on a generative adversarial network according to an embodiment of the present disclosure. The method 50 for detecting abnormal parts can be Figure 1The controller 13 or Figure 7 The process is performed by the electronic device 70 and includes the following steps.

[0092] Step S51: inferring a first anomaly score of the input data by using the denoising autoencoder. In this embodiment, step S51 includes step S11: extracting manifold coordinates of the input data; and step S12: calculating the distance between the manifold coordinates and the average coordinates of the normal data as the first anomaly score.

[0093] Step S52: Inferring a second anomaly score of the input data through the discriminator. In this embodiment, step S52 includes step S13: Inferring an identification value of the input data through the discriminator; and step S14: Converting the identification value into a second anomaly score.

[0094] Step S53: Add the first abnormality score and the second abnormality score to calculate the abnormality level of the input data. In one embodiment, when the abnormality level is higher than a custom threshold, the controller 13 or the electronic device 70 determines that the input data is abnormal and sends a warning signal to notify the user.

[0095] Steps S51 and S11 may be executed by the denoising autoencoder 33 , step S12 may be executed by the subtractor 36 , steps S52 and S13 may be executed by the discriminator 34 , step S14 may be executed by the digital converter 35 , and step S53 may be executed by the adder 37 .

[0096] Before the part anomaly detection method 50 is started, real-time data can be obtained through the controller 13, and the real-time data can be pre-processed (including statistical analysis, deleting non-matching feature set data and retaining matching feature set data) to generate input data. By executing the part anomaly detection method 50, the controller 13 or the electronic device 70 can perform online inference to generate the degree of abnormality of the part and then determine whether the input data is abnormal.

[0097] Figure 6 The data characteristic coordinate diagram 60 of the manifold coordinates according to the embodiment of the present disclosure is shown. The historical data, training data, test data and input data used in the embodiment of the present disclosure may be numerical data or images. Figure 6 Taking pictures as an example, different types of pictures will be gathered in low-dimensional manifold space in high-dimensional space, and the manifold coordinates of different types of pictures are almost non-overlapping. In other words, the higher the difference and the higher the dimension, the lower the overlap probability, so the higher the discrimination.

[0098] As described above, the disclosed method and device for detecting abnormal parts only need to train the denoising autoencoder and the discriminator with normal training data to solve the problem that the amount of abnormal data is too small and cannot be distinguished under various working conditions.

[0099] It should be noted that Figures 2 to 3 The noise reduction self-encoder 23, 33 and the discriminator 24, 34 are configured to be implemented in hardware, software, firmware or any combination thereof. For example, the noise reduction self-encoder 23, 33 and the discriminator 24, 34 can be implemented as a computer program code configured to be executed in one or more processors. Alternatively, the noise reduction self-encoder 23, 33 and the discriminator 24, 34 can be implemented in hardware logic / circuitry.

[0100] Figure 7 FIG. 7 is a schematic diagram of an electronic device 70 according to an embodiment of the present invention.

[0101] The present invention may be implemented in computer program code or machine-usable instructions, which may be computer executable instructions in the form of program modules, which are executed by a computer or other machine, such as a personal digital assistant or other portable device. In general, program modules include routines, programs, objects, components, data structures, etc., and program modules refer to program codes that perform specific tasks or implement specific abstract data types. The present invention may be implemented in a variety of system configurations, including portable devices, consumer electronics, general-purpose computers, more specialized computing devices, etc. The present invention may also be implemented in a distributed computing environment, processing devices connected by a communication network.

[0102] refer to Figure 7 Electronic device 70 includes bus 77 that directly or indirectly couples the following devices, memory 71, one or more processors 72, one or more display elements 73, input / output (I / O) ports 74, peripheral components 75, and an illustrative power supply 76. Bus 77 represents an element that can be one or more buses (e.g., an address bus, a data bus, or a combination thereof).

[0103] The memory 71 includes but is not limited to random access memory (RAM), read-only memory (ROM), electronically-erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical disc storage devices, magnetic disks, disks, magnetic disk storage devices or other magnetic storage devices, or any other media that can be used to store the required information and can be accessed by the electronic device 70.

[0104] The electronic device 70 includes a processor that reads data from various entities such as a memory 71 or a peripheral component 75. The display component 73 displays information or instructions to a user or other device, such as a display device, a speaker, a printing component, a vibration component, etc.

[0105] I / O ports 74 allow the electronic device 70 to be logically connected to other devices including peripheral components 75, some of which are built-in devices. Exemplary components include microphones, rockers, game consoles, satellite dish signal receivers, scanners, printers, wireless devices, etc. Peripheral components 75 can provide a user interface for processing gestures, sounds or other physiological inputs generated by the user. In some examples, these inputs can be transmitted to a suitable network element for further processing. The electronic device 70 can be equipped with a depth camera, such as a stereo camera system, an infrared camera system, an RGB camera system, and a combination of these systems to detect and identify objects.

[0106] In addition, the processor 72 in the electronic device 70 may also execute the program code 78 and instructions in the memory 71 to present the actions and steps of the above-mentioned embodiments, or other descriptions of the contents in the specification.

[0107] The present disclosure has been disclosed as above by way of implementation examples. Anyone familiar with this art may make some changes and modifications without departing from the concept and scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be determined by the definition of the claims.

Claims

1. A method for detecting abnormal parts based on a generative adversarial network, comprising the steps of: 1) Inferring a first anomaly score of an input data through a denoising autoencoder, comprising: 11) extracting a manifold coordinate of the above input data; as well as 12) calculating a distance between the manifold coordinates and an average coordinate of normal data as the first anomaly score; 2) inferring a second anomaly score of the input data through a discriminator; and 3) Adding the first anomaly score and the second anomaly score to calculate an anomaly level of the input data.

2. The method for detecting abnormal parts according to claim 1, wherein step 2) comprises: 21) inferring a first identification value of the input data through the identification device; and 22) Converting the first identification value into the second anomaly score.

3. The method for detecting abnormal parts according to claim 2, wherein step 22) comprises one of the following steps: Multiplying the first identification value by -1 to convert it into the second anomaly score, wherein the identification value is an arbitrary real number; Subtracting the first identification value from a preset value to convert it into the second anomaly score; and When the first identification value is greater than zero and less than 1, the reciprocal of the first identification value is taken as the second abnormality score.

4. The method for detecting abnormal parts according to claim 1, wherein before step 1), it further comprises: Preprocessing real-time data to generate processed data; Deleting the processed data that does not match a feature set; as well as The processed data matching the feature set is retained as the input data.

5. The method for detecting abnormal parts according to claim 1, wherein before step 1), a training process is further performed, comprising: A1) inferring second identification values ​​of a plurality of sets of input data through an initial identification device, wherein the plurality of sets of input data include at least one real data and at least one generated data; A2) calculating a first expected value according to the second identification value by the initial identification device; A3) inputting the first expected value into a first objective function to determine whether the first objective function is maximized; A4) when the first objective function has not been maximized, fixing the parameters of the initial denoising autoencoder, and adjusting the parameters of the initial discriminator according to the first expected value; and A5) Repeat steps A1) to A4) to train the initial discriminator until the first objective function is maximized, thereby generating the discriminator.

6. The method for detecting abnormal parts according to claim 5, wherein the training process further comprises the steps of: A6) inferring a third identification value between the generated data and the at least one real data through the initial identification device, and feeding it back to the denoising autoencoder; A7) calculating a second expected value according to the third identification value by the denoising autoencoder; A8) inputting the second expected value into a second objective function to determine whether the second objective function is minimized; A9) when the second objective function has not been minimized, fixing the parameters of the discriminator, and adjusting the parameters of the initial denoising autoencoder according to the second expected value; and A10) Repeat steps A6) to A9) to train the initial denoising autoencoder until the second objective function is minimized, thereby generating the denoising autoencoder.

7. The method for detecting abnormal parts according to claim 5, wherein step A1) comprises: adding noise to the normal data to generate noisy data; and The noisy data is converted into the generated data through the initial discriminator, and the generated data is input into the discriminator.

8. The method for detecting abnormal parts according to claim 5, wherein before the training process, a pre-processing process is further performed, including: B1) selecting a plurality of influential features from the statistical values ​​of a training data set by a feature selection method to generate a feature set; as well as B2) Selecting data and parameters matching the above feature set as a training data set and providing it to the model training stage.

9. The method for detecting abnormal parts according to claim 1, further comprising: 4) When the abnormality level is higher than a custom threshold, the input data is determined to be abnormal.

10. A device for detecting abnormality of a part, comprising: A processor; as well as A computer storage medium is coupled to the processor and is configured to store computer-readable instructions for instructing the processor to execute the part abnormality detection method as claimed in claim 1.

Images