A small sample incremental fault diagnosis method based on prototype adaptive network

Abstract

This invention provides a small-sample incremental fault diagnosis method based on a prototype adaptive network. The method includes the following steps: S1: data acquisition and processing in the base phase, which preprocesses the data and divides it into a pseudo-base dataset and a pseudo-incremental dataset; S2: pseudo-feature extraction network training, which uses the pseudo-base dataset to train the PMCNN in the pseudo-base phase to provide feature embedding for the PAN; S3: PAN training, which uses the pseudo-incremental dataset to train the PAN to update the initial prototype representation in the pseudo-incremental phase; S4: feature extraction network training, which uses the complete base dataset to train the MCNN; S5: incremental feature extraction, which uses the MCNN to extract features of new fault categories and solve for their prototype representations; S6: prototype representation update and classification, which uses the PAN to update the prototype representation and classify faults based on cosine similarity. This method significantly improves fault diagnosis accuracy under small sample conditions while maintaining the deep learning model's ability to memorize previous categories, making it suitable for complex industrial fault diagnosis scenarios.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial equipment fault diagnosis, in particular to fault prediction and health management technology based on deep learning, specifically a small sample incremental fault diagnosis method based on a prototype adaptive network. Background Art

[0002] The health of rotating machinery is crucial to the safe and stable operation of industrial systems. Frequent starts and stops, overloaded operation, and component wear and failure pose severe challenges to the operational reliability of equipment. To achieve real-time monitoring and prediction of equipment health, current research is increasingly focusing on fault diagnosis methods based on incremental learning. However, traditional deep learning models are prone to the "catastrophic forgetting" problem in incremental learning, where the model loses its ability to recognize previously learned fault categories when learning new ones, resulting in a decrease in overall diagnostic accuracy. Therefore, it is particularly important to develop a small-sample incremental fault diagnosis method that can take into account both new and old fault categories in an incremental learning environment.

[0003] Furthermore, traditional fault diagnosis methods typically rely on extensive full-lifecycle data for fault prediction and remaining life assessment. However, in practice, due to frequent replacements and difficulties in data collection, it is often difficult to obtain sufficient full-lifecycle data for prediction of rotating machinery. This is especially true for newly added fault categories, where the availability of relevant samples is even more limited.

[0004] Therefore, in order to accurately identify new fault categories under small sample conditions and maintain memory of old categories, a fault diagnosis method based on small sample incremental learning is urgently needed to improve the prediction accuracy and diagnostic robustness of the equipment. Summary of the Invention

[0005] In view of this, the present invention provides a small sample incremental fault diagnosis method based on a prototype adaptive network to at least solve the above problems.

[0006] The present invention provides a small sample incremental fault diagnosis method based on a prototype adaptive network, which includes a basic stage and an incremental stage. The basic stage includes a pseudo-basic stage and a pseudo-incremental stage, and specifically includes the following steps:

[0007] S1. Data acquisition and processing in the basic phase: In the basic phase, the basic dataset containing multiple fault types is preprocessed and divided into a pseudo-basic dataset and a pseudo-incremental dataset. The pseudo-basic dataset and pseudo-incremental dataset are used for training in the pseudo-basic phase and pseudo-incremental phase respectively.

[0008] S2. Pseudo-feature extraction network training: In the pseudo-basic stage, the pseudo-multi-scale convolutional neural network PMCNN is trained through the pseudo-basic data set, and the parameters of the pseudo-multi-scale convolutional neural network PMCNN are frozen; S3. Prototype adaptive network PAN training: In the pseudo-incremental stage, the prototype adaptive network PAN is trained through the pseudo-incremental data set and the pseudo-multi-scale convolutional neural network PMCNN, and the prototype representation of the fault category is expanded through small samples; S4. Feature extraction network training: The multi-scale convolutional neural network MCNN is trained through the complete basic data set, and the parameters of the multi-scale convolutional neural network MCNN are frozen to extract more comprehensive fault features; S5. Incremental stage feature extraction: In the incremental stage, small sample data of the new fault category is obtained, and the fault features of the new fault category are extracted through the trained multi-scale convolutional neural network MCNN, and the prototype representation of the new fault category is solved; S6. Prototype representation update and classification: The prototype representation of the new fault category is updated through the trained prototype adaptive network PAN, and the fault classification is performed by calculating the cosine similarity between the query sample of the new fault category and the prototype representation of the new fault category.

[0009] In one implementation, in step S1, the obtained basic data set containing multiple fault types is preprocessed, and the basic data set is divided into a pseudo basic data set and a pseudo incremental data set, including: performing Fourier transform on the basic data set to obtain a frequency domain signal, and reshaping the one-dimensional frequency domain signal of the frequency domain signal into a two-dimensional frequency domain signal; dividing the basic data set into a pseudo basic data set and a pseudo incremental data set in a 1:1 ratio, wherein the pseudo basic data set is used to train a pseudo multi-scale convolutional neural network PMCNN, and the pseudo incremental data set is used to train a prototype adaptive network PAN.

[0010] In another implementation, the pseudo multi-scale convolutional neural network PMCNN in step S2 and the multi-scale convolutional neural network MCNN in step S4 both adopt a multi-scale convolution structure to simultaneously extract fault features of different scales.

[0011] In another implementation, the training process of the prototype adaptive network PAN in step S3 is as follows: introducing a self-attention mechanism, dynamically updating the prototype representation through the self-attention mechanism, wherein, in the pseudo-incremental stage, the prototype adaptive network PAN is trained using the pseudo-incremental data set, the pseudo-incremental data is divided into a support set and a query set, and the support set and the query set are respectively input into the pseudo multi-scale convolutional neural network PMCNN to obtain the support set embedding E s and queryset embedding E q ; Embed the support set E s Calculate the mean and get the new category prototype representation w in the pseudo-incremental stage new , input the pseudo basic data into the pseudo multi-scale convolutional neural network PMCNN to obtain the old category prototype representation wold ; Denote the new category prototype as w old and the old category prototype representation w new The replication expansion dimensions are: and Where L is the number of samples in the query set, N old is the number of categories in the pseudo-basic stage, N new is the number of categories in the pseudo-incremental stage, D is the number of dimensions of each embedding; the new category prototype is represented by w old , the old category prototype represents w new , query set embedding E q The prototype adaptive network PAN is trained as input. The principle of the prototype adaptive network PAN dynamically updating the prototype representation through the self-attention mechanism is as follows:

[0012]

[0013] Q=W Q X,K=W K X,V=W V X

[0014] Where X is the input vector, X={w old , w new , E q}, Q is the query vector, K is the key vector, V is the value vector, Q, K, V are respectively passed through three trainable linear layers W Q (·), W K (·) and W V (·) get, d k is the dimension of the key vector K, W Q W is the weight matrix that converts the input vector into the query vector. K W is the weight matrix that converts the input vector into the key vector. V is the weight matrix that converts the input vector into a value vector;

[0015] The input vector X is updated using the following formula to obtain the updated X′:

[0016] X′=Ψ(Attention(Q,K,V))+X

[0017] Among them, Ψ(·) is a trainable linear layer, and pseudo incremental data is used to simulate the incremental stage training W Q (·), W K (·), W V (·) and Ψ(·) four linear layers, and a trained prototype adaptive network PAN is obtained by multiple training of the four linear layers. The trained prototype adaptive network PAN can adaptively update the prototype representation of the new fault category according to the new and old prototype representations and feature embedding.

[0018] In another implementation, in step S6, fault classification is performed by calculating the cosine similarity between the query sample of the new fault category and the prototype representation of the new fault category, and the formula is as follows:

[0019]

[0020] Among them, w i Represents the prototype of the i-th category, q represents the feature vector of the query sample, and the category with the highest similarity is used as the fault classification result to achieve accurate diagnosis of new fault categories.

[0021] Compared with the prior art, the present invention has the following beneficial effects:

[0022] (1) This paper uses a multi-scale convolutional neural network (MCNN) to extract fault features at different scales, effectively capturing the characteristic information of industrial equipment at different levels in complex environments and improving the adaptability of deep learning models to various working conditions. After training, the MCNN freezes its parameters, providing a stable feature extraction foundation for the subsequent incremental learning phase. This prevents the forgetting of old category knowledge when learning new categories, improving the model's diagnostic accuracy and the robustness of incremental learning.

[0023] (2) The present invention artificially divides the learning process of different fault categories into a pseudo-basic phase and a pseudo-incremental phase to simulate in advance the learning order of different fault categories under small sample conditions. Training the PAN simulation in the pseudo-incremental phase gradually expands the category prototype representation, thereby improving the model's adaptability and generalization capabilities under different working conditions and when new categories appear. The prototype adaptive network can efficiently learn and update the prototype representation of fault categories when new category samples are limited, reducing the model's dependence on large amounts of data.

[0024] (3) Compared with existing fault diagnosis methods, the present invention generates clear fault category prototypes by comparing fault samples with fault category prototypes, allowing non-professionals to intuitively understand the diagnosis results. At the same time, based on the prototype similarity calculation method, the model can effectively classify new faults while maintaining the memory of old categories. Professionals can identify potential faults in a timely manner and make maintenance decisions based on the prototype change trend, thereby effectively ensuring the operational stability of the system and reducing the possibility of faults. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 is a flow chart of the present invention;

[0026] Figure 2 This is a feature extraction network structure diagram of the present invention;

[0027] Figure 3This is a diagram of the prototype adaptive network structure of the present invention;

[0028] Figure 4 This is the confusion matrix result of each method in the CRWU dataset of the present invention. DETAILED DESCRIPTION

[0029] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0030] See also Figure 1 The present invention provides a small sample incremental fault diagnosis method based on a prototype adaptive network, which includes a basic stage and an incremental stage. The basic stage includes a pseudo-basic stage and a pseudo-incremental stage. The main steps are as follows:

[0031] S1. Data acquisition and processing in the basic phase: In the basic phase, the basic dataset containing multiple fault types is preprocessed and divided into a pseudo-basic dataset and a pseudo-incremental dataset. The pseudo-basic dataset and pseudo-incremental dataset are used for training in the pseudo-basic phase and pseudo-incremental phase respectively.

[0032] S2. Pseudo feature extraction network training: In the pseudo basis stage, the pseudo multi-scale convolutional neural network PMCNN is trained using the pseudo basis dataset, and the parameters of the pseudo multi-scale convolutional neural network PMCNN are frozen;

[0033] S3. Prototype Adaptive Network (PAN) training: In the pseudo-incremental phase, the prototype adaptive network (PAN) is trained using a pseudo-incremental dataset and a pseudo multi-scale convolutional neural network (PMCNN), and the prototype representation of the fault category is expanded using small samples.

[0034] S4. Feature extraction network training: Train the multi-scale convolutional neural network (MCNN) using the complete basic data set and freeze the parameters of the multi-scale convolutional neural network (MCNN) to extract more comprehensive fault features.

[0035] S5. Feature extraction in the incremental stage: In the incremental stage, small sample data of the new fault category is obtained, and the fault features of the new fault category are extracted through the trained multi-scale convolutional neural network (MCNN), and the prototype representation of the new fault category is solved;

[0036] S6. Prototype representation update and classification: The prototype representation of the new fault category is updated through the trained prototype adaptive network PAN, and the fault classification is performed by calculating the cosine similarity between the query sample of the new fault category and the prototype representation of the new fault category.

[0037] It should be understood that the full name of the pseudo-multiscale convolutional neural network PMCNN (Pseudo-Multiscale Convolutional Neural Network, PMCNN), the full name of the prototype adaptive network PAN (Prototype Adaptive Network, PAN), and the full name of the multiscale convolutional neural network MCNN (Multiscale Convolutional Neural Network, MCNN).

[0038] Optionally, in step S1, the obtained basic data set containing multiple fault types is preprocessed, and the basic data set is divided into a pseudo basic data set and a pseudo incremental data set, including: performing Fourier transform on the basic data set to obtain a frequency domain signal, and reshaping the one-dimensional frequency domain signal of the frequency domain signal into a two-dimensional frequency domain signal; dividing the basic data set into a pseudo basic data set and a pseudo incremental data set in a 1:1 ratio, wherein the pseudo basic data set is used to train a pseudo multi-scale convolutional neural network PMCNN, and the pseudo incremental data set is used to train a prototype adaptive network PAN.

[0039] It should be understood that performing Fourier transform on the basic data set to obtain the frequency domain signal and reshaping the one-dimensional frequency domain signal into a two-dimensional frequency domain signal can more effectively extract information in different frequency bands and improve the expressiveness of fault characteristics.

[0040] Optionally, the pseudo multi-scale convolutional neural network PMCNN in step S2 and the multi-scale convolutional neural network MCNN in step S4 both adopt a multi-scale convolution structure to simultaneously extract fault features of different scales.

[0041] Specifically, these two networks can be configured with convolution kernels of varying sizes, such as 1×1, 3×3, and 5×5, to extract fault features at varying scales. Multi-scale convolution enables the model to capture more comprehensive frequency and time domain features, helping to adapt to varying fault signatures under varying operating conditions. Furthermore, parameter freezing is performed after training to ensure stability during the incremental phase.

[0042] It should be understood that step S2 of pseudo feature extraction network training is to train the pseudo multi-scale convolutional neural network PMCNN. The training process of the pseudo multi-scale convolutional neural network PMCNN is as follows:

[0043] In the pseudo-feature extraction network, multi-scale convolution operations are introduced, and convolution kernels of different sizes (1×1, 3×3, and 5×5) are used to extract fault features of different scales, ensuring the deep learning model's sensitivity to features and robustness to environmental changes, thereby improving the accuracy and robustness of fault feature extraction.

[0044] It should also be understood that step S4 of feature extraction network training is to train the multi-scale convolutional neural network MCNN. The training process of the multi-scale convolutional neural network MCNN is as follows:

[0045] In the feature extraction network, multi-scale convolution operation is introduced, and convolution kernels of different sizes (1×1, 3×3 and 5×5) are used to extract fault features of different scales and reliable fault features. The model parameters are frozen after training is completed to ensure the stability of the network in the feature extraction of new fault samples in the incremental stage and maintain consistency with the pseudo feature extraction network structure.

[0046] By adopting pseudo multi-scale convolutional neural network PMCNN in the pseudo feature extraction network training stage and multi-scale convolutional neural network MCNN in the feature extraction network training stage, the feature extraction effects of the real stage and the pseudo stage can be kept close.

[0047] This multi-scale convolution method can effectively extract feature information at different levels, improve the model's generalization ability and recognition accuracy for small sample data, and thus enhance its adaptability to new fault categories.

[0048] Optionally, the training process of the prototype adaptive network PAN in step S3 is as follows: introducing a self-attention mechanism, dynamically updating the prototype representation through the self-attention mechanism, wherein, in the pseudo-incremental stage, the prototype adaptive network PAN is trained using a pseudo-incremental data set, the pseudo-incremental data is divided into a support set and a query set, and the support set and the query set are respectively input into the pseudo multi-scale convolutional neural network PMCNN to obtain the support set embedding E s and queryset embedding E q ; Embed the support set E s Calculate the mean and get the new category prototype representation w in the pseudo-incremental stage new , input the pseudo basic data into the pseudo multi-scale convolutional neural network PMCNN to obtain the old category prototype representation w old ; Denote the new category prototype as w old and the old category prototype representation w new The replication expansion dimensions are: and Where L is the number of samples in the query set, N old is the number of categories in the pseudo-basic stage, N new is the number of categories in the pseudo-incremental stage, D is the number of dimensions of each embedding; the new category prototype is represented by w old , the old category prototype represents w new , query set embedding E q The prototype adaptive network PAN is trained as input. The principle of the prototype adaptive network PAN dynamically updating the prototype representation through the self-attention mechanism is as follows:

[0049]

[0050] Q=W Q X,K=W K X, V = W V X

[0051] Where x is the input vector, X={w old , w new , E q}, Q is the query vector, K is the key vector, V is the value vector, Q, K, V are respectively passed through three trainable linear layers W Q (·), W K (·) and W V (·) get, d k is the dimension of the key vector K, W Q W is the weight matrix that converts the input vector into the query vector. K W is the weight matrix that converts the input vector into the key vector. V is the weight matrix that converts the input vector into a value vector;

[0052] The input vector X is updated using the following formula to obtain the updated X′:

[0053] X′=Ψ(Attention(Q,K,V))+X

[0054] Among them, Ψ(·) is a linear layer that can be trained to obtain the updated X′, X′={w′ old , w′ new , E′ q}, then split X′ to get the updated prototype representation W′={w′ old , w′ new} and the updated embedding E′ q The prototype adaptive network PAN is obtained by training four linear layers multiple times.

[0055] Specifically, pseudo incremental data is used to simulate the incremental phase training W Q (·), W K (·), W V (·) and Ψ(·) four linear layers, and a trained prototype adaptive network PAN is obtained by multiple training of the four linear layers. The trained prototype adaptive network PAN can adaptively update the prototype representation of the new fault category according to the new and old prototype representations and feature embedding.

[0056] Optionally, in step S6, fault classification is performed by calculating the cosine similarity between the query sample of the new fault category and the prototype representation of the new fault category, and the formula is as follows:

[0057]

[0058] Among them, w i Represents the prototype of the i-th category, q represents the feature vector of the query sample, and the category with the highest similarity is used as the fault classification result to achieve accurate diagnosis of new fault categories.

[0059] It should be understood that the higher the cosine similarity, the closer the query sample is to the fault category. The model predicts the fault category of the query sample based on the prototype with the highest similarity, thereby realizing the identification of new faults in the incremental stage.

[0060] It should be understood that the method of the present invention is the first to propose PAN and combine it with a multi-scale convolutional neural network for incremental fault diagnosis of industrial equipment. This method extracts multi-scale features through MCNN, enabling comprehensive capture of fault characteristics and high adaptability under different operating conditions. The stability of feature extraction is ensured by freezing MCNN parameters. Incorporating the self-attention mechanism of PAN, the present invention dynamically updates the prototype representation of fault categories during the incremental phase, enabling the model to efficiently learn and identify new fault categories with a small sample size, effectively improving the model's adaptability and diagnostic robustness.

[0061] In addition, the present invention also classifies new fault categories through cosine similarity, allowing the model to complete incremental diagnosis without forgetting old categories. This helps professionals monitor the changing trends of fault prototypes, identify potential problems in advance, and make maintenance decisions, thereby effectively ensuring the operational stability of the system and reducing the risk of equipment failure.

[0062] Specifically, the solution of the present invention is further described according to the following examples:

[0063] Replay Figure 1 The present invention includes two parts: the basic stage and the incremental stage. The main steps are as follows:

[0064] S1. Data acquisition and processing in the basic stage: The present invention selects a fault data set from the CWRU bearing data set for the training of the small sample incremental fault diagnosis method. This data set is collected by Case Western Reserve University and contains bearing data under various fault states. It is widely used in the field of equipment fault diagnosis and state prediction. The experiment uses data collected by the drive end accelerometer (DE) running at a speed of 1797 rpm, as well as the normal operation data of the equipment to form the data set. The data used include three typical fault types with different fault diameters (0.007 inches, 0.014 inches and 0.021 inches): inner race fault (IRF), rolling element fault (BF) and outer race fault (ORF), and the sampling frequency of the data is 48 kHz. The specific information is shown in Table 1.

[0065] Table 1 Introduction to the CRWU bearing dataset

[0066]

[0067] The dataset used in the basic phase is the data of phase 0 in Table 1. The incremental phase includes three phases with gradually increasing faults, corresponding to phases 1, 2, and 3 in Table 1.

[0068] To improve the effect of feature extraction, the data preprocessing process first performs Fourier transform on the original data to convert the one-dimensional time domain data into frequency domain data, and then reshapes the one-dimensional data into a two-dimensional format to better capture the spatial distribution and frequency characteristics of the fault features.

[0069] The dataset for the basic phase consists of normal data and three 0.007-inch fault types. To meet the training requirements of the pseudo-basic and pseudo-incremental phases, this dataset is further divided: normal data and 0.007-inch inner race faults (IRFs) are used for the pseudo-basic phase; 0.007-inch rolling element faults (BFs) are used for the pseudo-incremental phase 1 dataset; and 0.007-inch outer race faults (ORFs) are used for the pseudo-incremental phase 2 dataset.

[0070] S2. Pseudo feature extraction network training: In the pseudo basis stage, the present invention uses the pseudo basis data set to train PMCNN. The network structure of PMCNN adopts multi-scale convolution to enhance the extraction effect of fault features. The network structure of the feature extraction network and the size of the multi-scale convolution kernel are as follows: Figure 2 shown.

[0071] The pseudo-feature extraction network, or PMCNN, was trained with a batch size of 128, 50 epochs, and a learning rate of 0.05. The parameters, using 1×1, 3×3, and 5×5 convolutional kernels, were able to capture both fine-grained and coarse-grained fault feature information at different scales. After training, the PMCNN parameters were frozen to ensure stable feature embeddings for fault categories during PAN training.

[0072] S3. PAN training: In the pseudo-incremental stage, the present invention uses the pseudo-incremental dataset to train PAN, which aims to expand the prototype representation of fault categories through adaptive updates.

[0073] Specifically, the pseudo-incremental data is divided into a support set and a query set, and the support set embedding E can be obtained through the feature extraction network, namely PAN. s and queryset embedding E q . Let the support set be embedded in E s Taking the average value can get the new category prototype representation w in the pseudo-incremental stage new , the old category prototype representation w can be obtained through the original network old , w old and w new The replication expansion dimensions are: and Where L is the number of samples in the query set, N old is the number of categories in the pseudo-basic stage, N new is the number of categories in the pseudo-incremental stage, D is the number of dimensions of each embedding, and w old 、w new 、E q As input, we train PAN. The training process is as follows Figure 3 .

[0074] The input of the model is Through three trainable linear layers W Q (·), W K (·) and W V (·) to obtain the query vector Q, key vector K and value vector V respectively, and then pass it through a trainable linear layer Ψ(·) to obtain the updated X′:

[0075]

[0076]

[0077] We get X′={w′ old , w′ new , E′ q}, then split X′ to get the updated prototype representation W′={w′ old , w′new} and the updated embedding E′ q .

[0078] Among them, W Q (·), W K (·), W V (·) and Ψ(·) are trainable, and the specific training parameters are: training batch size is 128, number of training times is 50, and learning rate is 0.01.

[0079] S4. Feature extraction network training: In the last step of the basic stage, the MCNN is trained using the complete basic dataset. The network structure and convolution kernel size are as follows Figure 2 As shown in Figure 2, compared to PMCNN, this network uses more data and can further optimize multi-scale feature extraction, obtaining more comprehensive fault features. After training, the MCNN parameters are frozen and used to extract features for new fault categories in the incremental phase.

[0080] The specific training parameters are: training batch size is 128, training times is 50 times, and learning rate is 0.05.

[0081] S5. Incremental Phase Feature Extraction: In the incremental phase, small sample data for new fault categories is obtained and fed into the trained MCNN for feature extraction. The MCNN ensures comprehensiveness and consistency in extracted features, providing high-quality feature embeddings for prototype generation of new fault categories. After obtaining the feature embeddings for a particular fault type, the prototype representation of that fault type can be obtained by averaging the feature embeddings for that fault type.

[0082] 6. Prototype representation update and classification: Use the trained PAN network to update the prototype representation of the new fault type and the original fault type in the incremental stage.

[0083] The query samples of the new fault category are classified by cosine similarity calculation. The specific calculation formula is as follows:

[0084]

[0085] Among them, w i Represents the prototype of the i-th type of fault, q represents the query sample feature embedding, and the category with the highest similarity is used as the basis for judging the fault category, thereby achieving accurate identification of new fault types in the incremental stage.

[0086] Based on the above steps, the method of the present invention can effectively maintain the memory of old categories in the incremental learning scenario, and accurately identify new fault categories using only a small number of samples, and has high application value and robustness.

[0087] The comparison of the prediction results of the method MCNN-PAN of the present invention and fine-tuning FT, iCARL, and LLB is shown in Table 2.

[0088] Table 2 Comparison of performance indicators between the proposed method and small sample incremental learning

[0089]

[0090] The evaluation indicators used in this invention process the accuracy of each stage, as well as the average accuracy AA and the performance degradation rate PD, which are defined as follows:

[0091]

[0092] PD=A0-A I-1

[0093] Among them, A i It represents the accuracy of stage i. The higher the AA or the smaller the PD, the better the performance of the method.

[0094] As can be seen from Table 2, all methods have good diagnostic accuracy in the basic stage. As the stage increases, the diagnostic accuracy will continue to decline. The diagnostic accuracy of the method proposed in this invention is better than other small sample incremental learning methods. Therefore, the scheme of this invention has high diagnostic accuracy.

[0095] Figure 4 This paper presents a comparison of confusion matrices between the proposed method and other methods. The proposed method utilizes MCNN and introduces PAN. MCNN can extract features at different scales, effectively capturing the diversity and complexity of fault characteristics, thereby improving the comprehensiveness of feature extraction. PAN adaptively adjusts the prototype representation, enabling the model to not only maintain a stable memory of old knowledge during the incremental learning phase but also flexibly update the prototype representation to adapt to changes in new categories. This improvement achieves a better balance between stability and flexibility, resulting in superior performance in identifying new fault categories.

[0096] Based on this, the present invention utilizes multiple fault data from the basic phase to train MCNN and PAN offline to learn the representation and evolution patterns of various fault characteristics. The trained MCNN and PAN are then applied to real-time fault data from the incremental phase to dynamically update the prototype representation of fault categories and accurately diagnose new fault categories. As an incremental fault diagnosis solution, the present method can retain memory of old categories under small sample conditions and promptly identify new faults. This helps personnel quickly perceive changes in equipment status, supports maintenance decisions, and significantly reduces failure risks. The method has high engineering application value and practical significance.

[0097] It should be noted that the present invention may be a method, system, apparatus and / or computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present invention.

[0098] Computer-readable storage medium can be a tangible device that can keep and store the instructions used by the instruction execution device.Computer-readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device or any suitable combination thereof.More specific examples (non-exhaustive list) of computer-readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, for example, a punch card or a convex structure in a groove having instructions stored thereon, and any suitable combination thereof.Computer-readable storage medium used herein is not interpreted as a transient signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagated by waveguides or other transmission media (for example, light pulses by fiber optic cables), or electrical signals transmitted by wires.

[0099] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in the computer-readable storage medium in each computing / processing device.

[0100] The computer program instructions for performing the operation of the present invention can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, Python, and conventional procedural programming languages ​​such as "C" language or similar programming languages. The computer readable program instructions can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), is personalized by utilizing the state information of the computer readable program instructions, and the electronic circuit can execute the computer readable program instructions, thereby realizing various aspects of the present invention.

[0101] Various aspects of the present invention are described herein with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present invention. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0102] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0103] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0104] The flowcharts and block diagrams in the accompanying drawings show the possible implementation architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, program segment or part of an instruction, and the module, program segment or part of the instruction contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that implementation by hardware, implementation by software, and implementation by a combination of software and hardware are all equivalent.

[0105] While various embodiments of the present invention have been described above, the foregoing description is intended to be illustrative, non-exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is selected to best explain the principles of the embodiments, their practical applications, or technological improvements in the marketplace, or to enable others skilled in the art to understand the embodiments disclosed herein. The scope of the present invention is defined by the appended claims.

Claims

1. A small sample incremental fault diagnosis method based on a prototype adaptive network, comprising a basic stage and an incremental stage, wherein the basic stage comprises a pseudo-basic stage and a pseudo-incremental stage, and is characterized in that: The specific steps include: S1. Data acquisition and processing in the basic phase: In the basic phase, the basic dataset containing multiple fault types is preprocessed and divided into a pseudo-basic dataset and a pseudo-incremental dataset. The pseudo-basic dataset and pseudo-incremental dataset are used for training in the pseudo-basic phase and pseudo-incremental phase respectively. S2. Pseudo feature extraction network training: In the pseudo basis stage, the pseudo multi-scale convolutional neural network PMCNN is trained using the pseudo basis dataset, and the parameters of the pseudo multi-scale convolutional neural network PMCNN are frozen; S3. Prototype Adaptive Network (PAN) training: In the pseudo-incremental phase, the prototype adaptive network (PAN) is trained using a pseudo-incremental dataset and a pseudo multi-scale convolutional neural network (PMCNN), and the prototype representation of the fault category is expanded using small samples. S4. Feature extraction network training: Train the multi-scale convolutional neural network (MCNN) using the complete basic data set and freeze the parameters of the multi-scale convolutional neural network (MCNN) to extract more comprehensive fault features. S5. Feature extraction in the incremental stage: In the incremental stage, small sample data of the new fault category is obtained, and the fault features of the new fault category are extracted through the trained multi-scale convolutional neural network (MCNN), and the prototype representation of the new fault category is solved; S6. Prototype representation update and classification: The prototype representation of the new fault category is updated through the trained prototype adaptive network PAN, and the fault classification is performed by calculating the cosine similarity between the query sample of the new fault category and the prototype representation of the new fault category.

2. The method according to claim 1, characterized in that In step S1, the basic data set containing multiple fault types is preprocessed and the basic data set is divided into a pseudo basic data set and a pseudo incremental data set, including: Perform Fourier transform on the basic data set to obtain the frequency domain signal, and reshape the one-dimensional frequency domain signal into a two-dimensional frequency domain signal; The basic dataset is divided into a pseudo basic dataset and a pseudo incremental dataset in a 1:1 ratio. The pseudo basic dataset is used to train the pseudo multi-scale convolutional neural network PMCNN, and the pseudo incremental dataset is used to train the prototype adaptive network PAN.

3. The method according to claim 1, characterized in that Both the pseudo multi-scale convolutional neural network PMCNN in step S2 and the multi-scale convolutional neural network MCNN in step S4 adopt a multi-scale convolution structure to simultaneously extract fault features of different scales.

4. The method according to claim 1, wherein The training process of the prototype adaptive network PAN in step S3 is: The self-attention mechanism is introduced to dynamically update the prototype representation. In the pseudo-incremental stage, the pseudo-incremental data set is used to train the prototype adaptive network PAN, the pseudo-incremental data is divided into a support set and a query set, and the support set and query set are respectively input into the pseudo multi-scale convolutional neural network PMCNN to obtain the support set embedding E s and queryset embedding E q ; Embed the support set E s Calculate the mean and get the new category prototype representation w in the pseudo-incremental stage new , input the pseudo basic data into the pseudo multi-scale convolutional neural network PMCNN to obtain the old category prototype representation w old ; Denote the new category prototype as w old and the old category prototype representation w new The replication expansion dimensions are: and Where L is the number of samples in the query set, N old is the number of categories in the pseudo-basic stage, N new is the number of categories in the pseudo-incremental phase, and D is the number of dimensions of each embedding; Denote the new category prototype as w old , the old category prototype represents w new , query set embedding E q The prototype adaptive network PAN is trained as input. The principle of the prototype adaptive network PAN dynamically updating the prototype representation through the self-attention mechanism is as follows: Q=W Q X,K=W K X,V=W V X Where X is the input vector, X={w old , w new , E q }, Q is the query vector, K is the key vector, V is the value vector, Q, K, V are respectively passed through three trainable linear layers W Q (·), W K (·) and W V (·) get, d k is the dimension of the key vector K, W Q W is the weight matrix that converts the input vector into the query vector. K W is the weight matrix that converts the input vector into the key vector. V is the weight matrix that converts the input vector into a value vector; The input vector X is updated using the following formula to obtain the updated X′: X′=Ψ(Attention(Q,K,V))+X Among them, Ψ(·) is a trainable linear layer, and pseudo incremental data is used to simulate the incremental stage training W Q (·), W K (·), W V (·) and Ψ(·) four linear layers, and a trained prototype adaptive network PAN is obtained by multiple training of the four linear layers. The trained prototype adaptive network PAN can adaptively update the prototype representation of the new fault category according to the new and old prototype representations and feature embedding.

5. The method according to claim 1, characterized in that In step S6, fault classification is performed by calculating the cosine similarity between the query sample of the new fault category and the prototype representation of the new fault category. The formula is as follows: Among them, w i Represents the prototype of the i-th category, q represents the feature vector of the query sample, and the category with the highest similarity is used as the fault classification result to achieve accurate diagnosis of new fault categories.

Images