Self-lifting diagnosis method for electromechanical composite transmission system based on memory sub-network

Abstract

The invention relates to the technical field of intelligent operation and maintenance of mechanical equipment, in particular to an electromechanical composite transmission system self-lifting diagnosis method based on a memory sub-network, and the method comprises the steps: constructing a self-lifting fault diagnosis framework which comprises a health category prediction network, a stable information memory sub-network and a rapid information memory sub-network; in the autonomous lifting learning stage, a fault diagnosis data set A is randomly extracted, and a data set B is randomly extracted from a learned information space; predicting the data set B by using the two sub-networks, and selecting an optimal playback log; predicting the data set A and the data set B on the basis of a health category prediction network to obtain two logs; calculating the total loss based on the playback logits and the two logits of the health category prediction network, and updating the weight and the learned information space of each network; and carrying out multiple times of autonomous lifting learning until a training target is met. According to the invention, the fault diagnosis network can be continuously trained from the continuously added data streams, and the autonomous improvement of the network is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent operation and maintenance of mechanical equipment, and more specifically to a self-lifting diagnosis method for an electromechanical composite transmission system based on a memory subnetwork. Background Art

[0002] With the vigorous development of modern science and technology, complex mechanical equipment such as large machine tools, high-speed trains and wind turbines have become important pillars of social production. Faced with the increasing operating intensity of mechanical equipment and the increasing technical precision, it is particularly important to ensure the safe and reliable operation of mechanical equipment. Mechanical equipment is a whole with strong coupling of multiple systems, and the normal operation of each subsystem is indispensable. Among them, the electromechanical composite transmission system undertakes the key task of efficient power transmission. Due to the complexity and changeability of its service environment, various types of failures are inevitable. Once a failure occurs, it will weaken the operating performance of the equipment and even cause the overall system to paralyze, causing significant economic losses. Equipment operation and maintenance personnel hope to discover faults in the early stage of transmission system abnormalities and take maintenance measures in time to reduce accidents and reduce maintenance costs.

[0003] Thanks to the progress of artificial intelligence and Internet of Things technology, the intelligent fault diagnosis method based on deep learning has overcome the limitation of insufficient equipment maintenance experience, can autonomously learn fault characteristics from the vibration signals of mechanical equipment, and achieve efficient and accurate diagnosis, which is highly respected in the field of mechanical equipment operation and maintenance. Traditional intelligent diagnosis methods rely on a complete training data set, that is, the data set covers all fault categories and provides sufficient data for each category. However, in the early stage of actual operation and maintenance, the equipment is in a healthy state for a long time, and it is difficult to build a training data set with a complete range of fault modes in a short period of time. Usually, the data of the equipment is gradually acquired over time, and the number of fault categories will increase accordingly. After the introduction of new fault categories, training the new fault category data alone may cause "catastrophic forgetting" of the model, that is, the model loses the ability to recognize the old fault categories; and retraining the model requires a lot of time and computing resources, which limits the application potential of intelligent fault diagnosis technology.

[0004] Continuous learning methods can solve the above problems well, but existing methods have the following shortcomings: it is impossible to retain the high-precision recognition ability of old categories while progressively learning new category samples, and it is difficult to achieve a balance between network plasticity and stability; it is impossible to efficiently retain the learned information, that is, it often relies on storing a large number of redundant task samples in the past, but these samples may not fully represent the core knowledge of the task, and as the number of tasks increases, the number of playback samples will also increase sharply, resulting in storage pressure. These limitations make it difficult to efficiently and flexibly apply the autonomous improvement diagnosis method in actual engineering. At present, there is an urgent need for a method that can continuously train the fault diagnosis network from the continuously increasing data stream to achieve autonomous improvement of the network. Summary of the invention

[0005] In view of this, the present invention provides a self-improvement diagnosis method for an electromechanical hybrid transmission system based on a memory sub-network, which can continuously train a fault diagnosis network from continuously added data streams to achieve autonomous improvement of the network.

[0006] In order to achieve the above object, the present invention adopts the following technical solution:

[0007] A self-lifting diagnosis method for an electromechanical hybrid transmission system based on a memory subnetwork comprises the following steps:

[0008] Construct an autonomous improvement fault diagnosis framework consisting of a health category prediction network, a stable information memory subnetwork, and a fast information memory subnetwork;

[0009] Entering the initial learning stage, a data set A is randomly selected from the continuously increasing mechatronic transmission system fault diagnosis data stream;

[0010] Predict the health status of samples in the current dataset A based on the health category prediction network;

[0011] Calculate the loss based on the logits output of the health category prediction network and update the weights and learned information space of each network;

[0012] Entering the autonomous learning stage, randomly extracting data set A from the continuously increasing mechatronic transmission system fault diagnosis data stream; randomly extracting data set B from the learned information space, and combining data set A and data set B as the training set for the current stage;

[0013] Use the stable information memory subnetwork and the fast information memory subnetwork to predict the health of the samples in the current stage dataset B, and select the one with the higher score as the final playback logits output;

[0014] Based on the health category prediction network, the health status of the samples in the current data set A and data set B is predicted respectively, and two logits outputs are obtained;

[0015] Calculate the total loss based on the final playback logits output and the two logits outputs of the healthy category prediction network, and update the weights and learned information space of each network;

[0016] Conduct multiple self-improvement learning sessions until the training goals are met.

[0017] Furthermore, in the initial learning stage, the loss L is calculated based on the cross entropy loss function, and its calculation formula is:

[0018]

[0019] in, Represents any sample X in the dataset A in the initial learning phase a The logits output value of the health category j, Represents the sample label Y a The true label value of the healthy category j is encoded in one-hot, C represents the number of healthy categories, and bs represents the batch size.

[0020] Furthermore, in the initial learning stage and the autonomous improvement learning stage, the weight update method of the health category prediction network is the same, and the update formula is:

[0021] φ←φ-η▽ φ L

[0022] Where η represents the learning rate of the health category prediction network; ▽ φ L is the gradient of the loss function with respect to the weight φ of the health category prediction network, indicating the direction and magnitude of the change of the loss L relative to the weight φ.

[0023] Furthermore, in the initial learning stage and the autonomous improvement learning stage, the weights of the stable information memory subnetwork and the fast information memory subnetwork are updated in the same way, and the updating process includes:

[0024] Generate two uniformly distributed random numbers a and b to decide whether to update the weights of the fast information memory subnetwork and the stable information memory subnetwork;

[0025] If a<σ p , then the weight of the fast information memory subnetwork is updated through the EMA formula, and the update formula is:

[0026] δ←ε p δ+(1-ε p )φ

[0027] Among them, σ p represents the upgrade rate of the fast information memory subnetwork, ε p represents the forgetting rate of the fast information memory subnetwork, δ represents the weight of the fast information memory subnetwork, and φ represents the weight of the health category prediction network at the current stage;

[0028] If b < σ s , then the weight of the stable information memory subnetwork is updated through the EMA formula, and the update formula is:

[0029]

[0030] Among them, σ s represents the upgrade rate of the stable information memory subnetwork, ε s represents the forgetting rate of the stable information sub-network, Represents the weights of the stable information memory sub-network.

[0031] Furthermore, in the initial learning stage and the self-improving learning stage, the way of updating the learned information space is the same, and the update process includes:

[0032] For any sample X in the dataset A extracted in each learning stage a , if the learned information space has not reached the capacity M, then directly add the current sample X a to the memory bank;

[0033] If the learned information space is full, generate a random integer j in the interval [0, N], where N represents the total number of samples received so far; if j < M, replace the j-th sample in the memory bank with the current sample X a , and if j ≥ M, do not store the current sample.

[0034] Furthermore, in the self-improving learning stage, the determination method of the final replay logits output includes:

[0035] Select the learning method based on the softmax function, compare the logits output O of the stable information memory sub-network s and the logits output O of the fast information memory sub-network p , and select the one with a higher score as the final replay logits output. The comparison formula is as follows:

[0036] if Softmax(O p )(Y b ) > Softmax(O s )(Y b )

[0037] O r = O p else O r = O s

[0038] where Y b represents the true sample label, and O r represents the final replay logits output.

[0039] Furthermore, in the self-improving learning stage, calculate the total loss L based on the cross-entropy loss function and the consistency loss function. The calculation formula of the total loss L is:

[0040]

[0041] where O Arepresents the set of logits values ​​predicted by the health category prediction network for data set A during the autonomous learning phase, O B represents the collection of logits values ​​predicted by the health category prediction network for data set B; O R is the final collection of playback logits values; L CE represents the cross entropy loss function; L MSE represents the consistency loss function; Represents any sample X in the dataset A during the autonomous learning phase a The logits output value of the health category j; It represents the logits output value of the health category j of any sample in the dataset B during the autonomous improvement learning phase; Indicates O R The logits output value of the health category j; Represents the sample label Y a The true label value encoded in one-hot, C represents the number of healthy categories.

[0042] It can be seen from the above technical solutions that, compared with the prior art, the present invention has the following beneficial effects:

[0043] The present invention establishes a learned information space and uses a stable information memory subnetwork and a fast information memory subnetwork to carry out autonomous improvement.

[0044] 1) The present invention adopts a dual information memory subnetwork formed by using a stable information memory subnetwork and a fast information memory subnetwork. The fast information subnetwork simulates rapid learning ability, and the stable information subnetwork maintains long-term knowledge. According to the output scores of the dual networks, the best playback logits are selected to maximize the recognition ability of the network; the new sample and old sample data are comprehensively learned, the consistency loss and cross entropy loss are calculated, and the parameters of the health category prediction network are updated, so as to achieve a balance between the ability to adapt to new knowledge and the ability to retain old knowledge. While improving the ability to identify new category faults, the accuracy of identifying old category faults is guaranteed to the greatest extent.

[0045] 2) The present invention stores long-term knowledge in the learned information space and uses the local shuffle sampling method to dynamically update the stored old task samples, efficiently integrating the core samples of the task, and facilitating the continuous review of old sample knowledge in the subsequent incremental information learning process; it does not require a large amount of sample storage space, and uses the memory subnetwork to continuously integrate long-term knowledge in subsequent learning, effectively avoiding catastrophic forgetting caused by continuous learning.

[0046] 3) The present invention is a general autonomous improvement diagnosis method that does not make any requirements on data and tasks, can adapt to non-independent and identically distributed data streams from dynamic environments, conforms to engineering practice, and is more flexible. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0048] Figure 1 A flow chart of a self-lifting diagnostic method for an electromechanical hybrid transmission system based on a memory subnetwork provided by the present invention;

[0049] Figure 2 A schematic diagram of the autonomous lifting fault diagnosis framework provided by the present invention;

[0050] Figure 3 A schematic diagram of the updating strategy of the health category prediction network provided by the present invention;

[0051] Figure 4 4 is a performance comparison chart of the method of the present invention and the existing learning method. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0053] like Figure 1 As shown, the embodiment of the present invention discloses a self-lifting diagnosis method for a mechatronic transmission system based on a memory subnetwork, comprising the following steps:

[0054] Construct an autonomous improvement fault diagnosis framework consisting of a health category prediction network, a stable information memory subnetwork, and a fast information memory subnetwork;

[0055] Entering the initial learning stage, a data set A is randomly selected from the continuously increasing mechatronic transmission system fault diagnosis data stream;

[0056] Predict the health status of samples in the current dataset A based on the health category prediction network;

[0057] Calculate the loss based on the logits output of the health category prediction network and update the weights and learned information space of each network;

[0058] Entering the autonomous learning stage, randomly extracting data set A from the continuously increasing mechatronic transmission system fault diagnosis data stream; randomly extracting data set B from the learned information space, and combining data set A and data set B as the training set for the current stage;

[0059] Use the stable information memory subnetwork and the fast information memory subnetwork to predict the health of the samples in the current stage dataset B, and select the one with the higher score as the final playback logits output;

[0060] Based on the health category prediction network, the health status of the samples in the current data set A and data set B is predicted respectively, and two logits outputs are obtained;

[0061] Calculate the total loss based on the final playback logits output and the two logits outputs of the healthy category prediction network, and update the weights and learned information space of each network;

[0062] Conduct multiple self-improvement learning sessions until the training goals are met.

[0063] The above steps are further explained below.

[0064] 1. Build Figure 2 The autonomous improvement fault diagnosis framework shown in Figure 1 includes a health category prediction network F(X,φ) and a stable information memory subnetwork. and fast information memory subnetwork F p (X,δ); where X is the input sample of the network, φ, δ are F, F s , F p The learnable network parameters (i.e. weights). At the same time, set the hyperparameters, including the cross entropy loss function L CE And the consistency loss function L MSE , learning rate η, consistency weight ω, training batch bs, number of iterations, upgrade rate σ s and σ p , the forgetting rate ε s and ε p , the learned information space size M. The above network is composed of a stack of input layers, convolutional layers, and fully connected layers without Softmax activation. Its output is logits that have not been processed by the Softmax function. They are the "raw scores" of the model for each category.

[0065] 2. Receive fault diagnosis data stream. Randomly obtain data sets from the continuously increasing non-independent and identically distributed mechatronic transmission system fault diagnosis data stream, where non-independent and identically distributed means that the data does not meet the conditions of mutual independence or identical distribution, or neither. Any data can be expressed as (X, Y), where Represents the multi-channel signal data of the transmission system, l is the signal sampling length, c is the number of signal channels, and Y is the corresponding health type label.

[0066] 3. Enter the initial learning stage, which includes:

[0067] 3.1) Dataset acquisition.

[0068] A data set A is randomly obtained from the continuously increasing non-independent and identically distributed electromechanical hybrid transmission system fault diagnosis data stream, where any data can be expressed as (X a ,Y a ). It should be noted that the learned information space is empty at this time.

[0069] 3.2) Predict the health category and obtain the output result.

[0070] The health status of samples in the current task dataset A is predicted through the health category prediction network F(X,φ), where any sample can be represented as (X a ,Y a ), logits output is O a , O a =F(X a ,φ).

[0071] 3.3) Calculate the cross entropy loss.

[0072] In the initial learning stage, the loss L is calculated based on the cross entropy loss function, and its calculation formula is:

[0073]

[0074] in, Represents any sample X in the dataset A in the initial learning phase a The logits output value of the health category j, Represents the sample label Y a The true label value of the healthy category j is encoded in one-hot, C represents the number of healthy categories, and bs represents the batch size.

[0075] 3.4) Use the back propagation algorithm to train the health category prediction network, and the update formula is:

[0076] φ←φ-η▽ φ L

[0077] Where η represents the learning rate of the health category prediction network; ▽ φ L is the gradient of the loss function with respect to the weight φ of the health category prediction network, indicating the direction and magnitude of the change of the loss L relative to the weight φ.

[0078] 3.5) Update the weights of the dual memory sub-network. The update process includes:

[0079] Generate two random numbers a and b that are uniformly distributed on [0, 1] to determine whether to update the weights of the fast information memory sub-network and the stable information memory sub-network;

[0080] If a < σ p , then update the weights of the fast information memory sub-network through the EMA formula. The update formula is:

[0081] δ ← ε p δ+(1 - ε p )φ

[0082] where σ p represents the upgrade rate of the fast information memory sub-network, ε p represents the forgetting rate of the fast information memory sub-network, δ represents the weights of the fast information memory sub-network, and φ represents the weights of the healthy class prediction network in the current stage;

[0083] If b < σ s , then update the weights of the stable information memory sub-network through the EMA formula. The update formula is:

[0084]

[0085] where σ s represents the upgrade rate of the stable information memory sub-network, ε s represents the forgetting rate of the stable information sub-network, represents the weights of the stable information memory sub-network.

[0086] 3.6) Update the learned information space, specifically including:

[0087] For any sample X in the dataset A extracted in each learning stage a , if the learned information space has not reached the capacity M, then directly add the current sample X a to the memory bank;

[0088] If the learned information space is full, generate a random integer j in the interval [0, N), where N represents the total number of samples received so far; if j < M, then replace the j-th sample in the memory bank with the current sample X a , if j ≥ M, do not store the current sample. This method ensures that each sample in the data stream is sampled into the learned information space with equal probability.

[0089] 4. Enter the autonomous improvement learning stage, specifically including:

[0090] 4.1) Input data stream, obtain data set: Randomly obtain data set A from the continuously increasing non-independent and identically distributed electromechanical hybrid transmission system fault diagnosis data stream, where any data can be expressed as

[0091] (X a ,Y a ), randomly extract a data set B from the learned information space, where any data can be expressed as (X b ,Y b ), Y b is the corresponding health type label. The above dataset samples are combined into a training set S, where S = A∪B.

[0092] 4.2) Predict the health type of samples in dataset B and obtain the output results: Use different memory subnetworks to predict the health type of samples in dataset B, where any sample can be expressed as (X b ,Y b ), and obtain a stable information memory subnetwork and fast information memory subnetwork F p The logits prediction result of (X,δ) is O s and O p , O p =F p (X b ,δ).

[0093] 4.3) Compare the output results of the two memory subnetworks and select the final playback logits output, including:

[0094] Based on the softmax function, the learning method is selected to stabilize the logits output of the information memory subnetwork. s and the output O of the logits of the fast information memory subnetwork p , select the one with a higher score as the final playback logits output, and the comparison formula is as follows:

[0095] if Softmax(O p )(Y b )>Softmax(O s )(Y b )

[0096] O r =O p else O r =O s

[0097] Among them, Y b represents the true sample label, O rRepresents the final replay logits output. This method ensures that the health category prediction selects the appropriate replay logits when processing new and old tasks.

[0098] 4.4) Calculate the cross entropy loss and consistency loss.

[0099] Use the health category prediction network to predict datasets A and B, where any sample can be represented as X a and X b , and obtain the result O a =F(X a ,φ) and O b =F(X b ,φ), and calculate the total loss L, which consists of two parts, namely the cross entropy loss function L CE And the consistency loss function L MSE , whose expression is:

[0100]

[0101] Among them, O A represents the set of logits values ​​predicted by the health category prediction network for data set A during the autonomous learning phase, O B represents the collection of logits values ​​predicted by the health category prediction network for data set B; O R is the final collection of playback logits values; L CE represents the cross entropy loss function; L MSE represents the consistency loss function; Represents any sample X in the dataset A during the autonomous learning phase a The logits output value of the health category j; It represents the logits output value of the health category j of any sample in the dataset B during the autonomous improvement learning phase; Indicates O R The logits output value of the health category j; Represents the sample label Y a The true label value encoded in one-hot, C represents the number of healthy categories.

[0102] 4.5) Use the back propagation algorithm to update the health category prediction network weights. The specific update method is as follows:

[0103] φ←φ-η▽ φ L

[0104] Where η is the learning rate, ▽ φ L represents the gradient of the loss function with respect to the weight φ of the health category prediction network, which indicates the direction and magnitude of the change of the loss L relative to the weight φ.

[0105] 4.6) As shown in Figure 3 , update the weights of the dual memory sub-networks. This part is the same as in the initial learning stage and specifically includes:

[0106] Generate two random numbers a and b that are uniformly distributed to determine whether to update the weights of the fast information memory sub-network and the stable information memory sub-network. For the fast information memory, if a < σ p , then use the EMA formula to update the weights of the fast information memory sub-network:

[0107] δ ← ε p δ+(1 - ε p )φ

[0108] where ε p is the forgetting rate of the fast information sub-network.

[0109] For the long-term semantic memory, if b < σ s , then use the EMA formula of the weights of the health recognition model to update the weights of the stable information memory sub-network:

[0110]

[0111] where ε s is the forgetting rate of the stable information sub-network.

[0112] 4.7) Update the learned information space. This part is similar to the initial learning stage and specifically includes:

[0113] For each data sample X of the new task a , if the learned information space has not reached the capacity M, directly add the current sample X a to the memory bank. If the learned information space is full, generate a random integer j in the interval [0, N], where N is the total number of samples received so far. If j < M, replace the j-th sample in the memory bank with the current sample. This method ensures that each sample in the data stream is sampled into the learned information space with equal probability.

[0114] 5. Repeat the above step 4 until the training objective is met.

[0115] The present invention also takes the fault diagnosis of the electromechanical composite drive system of the rail train as an example, and verifies the effectiveness of the method of the present invention through the fault simulation data of the test bench.

[0116] The experimental bench used in this embodiment controls different motor speeds by a frequency converter, and the electro-hydraulic load device applies different lateral loads. The signals collected in the experiment include 18 channels with a sampling frequency of 64kHz, including the three-axis acceleration of the motor, gearbox and axle box and the three-phase current of the motor. 16 health states of the electromechanical composite transmission system were considered in the experiment, including normal state, 4 axle box bearing faults (inner ring fault, outer ring fault, rolling element fault and cage fault), 4 pinion support bearing faults, 4 pinion faults (cracks, wear, broken teeth and missing teeth) and 3 motor faults (short circuit, rotor bending and rotor broken bars). Each health state includes 1000 samples, and each sample includes 1024 sampling points. The experiment uses the method proposed in the present invention to diagnose faults of motors, gearboxes and axle boxes.

[0117] On this basis, in order to facilitate comparative experiments with traditional methods, the data set is divided into three stages according to axle box failure, gearbox failure and motor failure. The data in each stage is used for training and testing in a 1:1 ratio. The training set of each stage includes a small number of examples sampled from the training data of the previous stage and the training data of the current stage. For the test set, it includes all the test data of the previous stage and the current stage.

[0118] The experiment compares the proposed method with two common methods: classifier parameter fine-tuning and full network parameter fine-tuning. Full network parameter fine-tuning updates all trainable parameters of the feature extraction layer and the output layer based on the parameters of the previous stage, while classifier fine-tuning only updates the parameters of the output layer. The basic structure of the network is shown in Table 1, and the training related parameters are shown in Table 2. The experimental results are summarized in Tables 3 and Figure 4 .

[0119] Table 1. Summary of basic network structure

[0120]

[0121]

[0122] Table 2. Summary of training related parameters

[0123]

[0124] Table 3. Summary of accuracy at the final stage

[0125]

[0126] It can be seen from the experimental results that as the learning continues, the network's diagnostic effect is significantly better than the two comparison methods, and can better achieve autonomous improvement diagnosis.

[0127] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0128] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A self-lifting diagnosis method for a mechatronic transmission system based on a memory subnetwork, characterized in that: The following steps are involved: Construct an autonomous improvement fault diagnosis framework consisting of a health category prediction network, a stable information memory subnetwork, and a fast information memory subnetwork; Entering the initial learning stage, a data set A is randomly selected from the continuously increasing mechatronic transmission system fault diagnosis data stream; Predict the health status of samples in the current dataset A based on the health category prediction network; Calculate the loss based on the logits output of the health category prediction network and update the weights and learned information space of each network; Entering the autonomous learning stage, randomly extracting data set A from the continuously increasing mechatronic transmission system fault diagnosis data stream; Randomly extract dataset B from the learned information space, and combine dataset A and dataset B as the training set for the current stage; Use the stable information memory subnetwork and the fast information memory subnetwork to predict the health of the samples in the current stage dataset B, and select the one with the higher score as the final playback logits output; Based on the health category prediction network, the health status of the samples in the current data set A and data set B is predicted respectively, and two logits outputs are obtained; Calculate the total loss based on the final playback logits output and the two logits outputs of the healthy category prediction network, and update the weights and learned information space of each network; Conduct multiple self-improvement learning sessions until the training goals are met.

2. The self-lifting diagnosis method of the electromechanical hybrid transmission system based on the memory sub-network according to claim 1 is characterized in that: In the initial learning stage, the loss L is calculated based on the cross entropy loss function, and its calculation formula is: in, Represents any sample X in the dataset A in the initial learning phase a The logits output value of the health category j, Represents the sample label Y a The true label value of the healthy category j is encoded in one-hot, C represents the number of healthy categories, and bs represents the batch size.

3. The self-lifting diagnosis method of the electromechanical hybrid transmission system based on the memory sub-network according to claim 1 is characterized in that: In the initial learning stage and the autonomous learning stage, the weight update method of the health category prediction network is the same, and the update formula is: Where η represents the learning rate of the health category prediction network; It is the gradient of the loss function for the weight φ of the health category prediction network, indicating the direction and magnitude of the change of the loss L relative to the weight φ.

4. The self-lifting diagnosis method of the electromechanical hybrid transmission system based on the memory sub-network according to claim 1 is characterized in that: In the initial learning stage and the autonomous improvement learning stage, the weights of the stable information memory subnetwork and the fast information memory subnetwork are updated in the same way. The update process includes: Generate two uniformly distributed random numbers a and b to decide whether to update the weights of the fast information memory subnetwork and the stable information memory subnetwork; If a<σ p , then the weight of the fast information memory subnetwork is updated through the EMA formula, and the update formula is: d←e p d+(1-e p )φ Among them, σ p represents the upgrade rate of the fast information memory subnetwork, ε p represents the forgetting rate of the fast information memory subnetwork, δ represents the weight of the fast information memory subnetwork, and φ represents the weight of the health category prediction network at the current stage; If b < σ s , then the weight of the stable information memory subnetwork is updated through the EMA formula, and the update formula is: Among them, σ s represents the upgrade rate of the stable information memory subnetwork, ε s represents the forgetting rate of the stable information sub-network, Represents the weight of the stable information memory sub-network.

5. The self-lifting diagnosis method of the electromechanical hybrid transmission system based on the memory sub-network according to claim 1 is characterized in that: In the initial learning stage and the self-improvement learning stage, the updated method of the learned information space is the same, and the update process includes: For any sample X in the dataset A extracted in each learning stage a If the learned information space has not reached the capacity M, then directly convert the current sample X a , added to the memory bank; If the learned information space is full, generate a random integer j in the range [0, N], where N represents the total number of samples received so far; if j < M, replace the j-th sample in the memory bank with the current sample X a If j ≥ M, do not store the current sample.

6. The self-lifting diagnosis method of the electromechanical hybrid transmission system based on the memory sub-network according to claim 1 is characterized in that: In the self-improvement learning stage, the final playback logits output is determined in the following ways: Select the learning method based on the softmax function to stabilize the logits output of the information memory subnetwork. s and the output O of the logits of the fast information memory subnetwork p , select the one with a higher score as the final playback logits output, and the comparison formula is as follows: if Softmax(O p )(AND b )>Softmax(O s )(AND b ) O r =O p else O r =O s Among them, Y b represents the true sample label, O r Represents the final playback logits output.

7. The self-lifting diagnosis method of the electromechanical hybrid transmission system based on the memory sub-network according to claim 6 is characterized in that: In the autonomous learning stage, the total loss L is calculated based on the cross entropy loss function and the consistency loss function. The calculation formula of the total loss L is: Among them, O A represents the set of logits values ​​predicted by the health category prediction network for data set A during the autonomous learning phase, O B represents the collection of logits values ​​predicted by the health category prediction network for data set B; O R is the final collection of playback logits values; L CE represents the cross entropy loss function; L MSE represents the consistency loss function; Represents any sample X in the dataset A during the autonomous learning phase a The logits output value of the health category j; It represents the logits output value of the health category j of any sample in the dataset B during the autonomous improvement learning phase; Indicates O R The logits output value of the health category j; Represents the sample label Y a The true label value encoded in one-hot, C represents the number of healthy categories.

Images