Proton exchange membrane fuel cell fault diagnosis method based on transfer learning

Through transfer learning and UMAP dimensionality reduction technology, the TimesNet model was built, and the problems of incomplete data labels and lack of fault data sets in fuel cell fault diagnosis were solved, efficient and accurate fault diagnosis was achieved, and the diagnostic accuracy and applicability of PEMFC were improved.

CN118919778AActive Publication Date: 2024-11-08HUAIYIN INSTITUTE OF TECHNOLOGY
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202410942557.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-15
Publication Date
2024-11-08
Estimated Expiration
2044-07-15

AI Technical Summary

Technical Problem

The existing fuel cell fault diagnosis method relies on the consistency of a large number of label data and data distribution, resulting in low diagnostic accuracy in the case of incomplete data labels and lack of fault data sets, especially under different load drives of PEMFC. When conditions are complex, traditional methods are difficult to accurately diagnose faults.

Method used

Using a transfer learning-based method, the source domain high-dimensional data set and the target domain labeled data set are constructed, and the uniform manifold approximation and projection algorithm (UMAP) is used to reduce the dimensions, build the TimesNet model and pre-train it, and use a small number of labeled data sets. The data is fine-tuned for transfer learning, and a model is established for fault diagnosis, and the model is optimized by the cross entropy loss function and the combined maximum mean difference loss function.

Benefits of technology

In the case of scarce data labels and insufficient fault data sets, efficient and accurate fault diagnosis is achieved, improving the accuracy and applicability of PEMFC diagnosis, and reducing the impact of invalid signals on model accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118919778A_ABST
    Figure CN118919778A_ABST
Patent Text Reader

Abstract

The invention discloses a transfer learning-based proton exchange membrane fuel cell fault diagnosis method, which comprises the following steps of: firstly, based on existing high-dimensional plenty of PEMFC (Proton Exchange Membrane Fuel Cell) labeled data, corresponding to normal and different fault types, taking the data as a uniform manifold approximation and projection algorithm UMAP input, extracting key components in the high-dimensional data, and carrying out transfer learning on the key components; then inputting a large amount of dimensionality-reduced data as source data into a pre-training model in a TimesNet model diagnosis framework, and then finely tuning the TimesNet model through a transfer learning method by using a small amount of labeled high-dimensional data collected by a current target domain PEMFC to obtain a final diagnosis model after migration; and finally, inputting target domain label-free data acquired by each sensor into the final diagnosis model, and diagnosing newly acquired PEMFC feature data. According to the method, the problem of scarce data volume of the diagnosis object can be solved, the target domain PEMFC can be diagnosed when the existing data set is less, the PEMFC diagnosis efficiency is improved, and the method has a relatively good application prospect.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of fuel cells, and in particular relates to a proton exchange membrane fuel cell fault diagnosis method based on transfer learning. Background Art

[0002] In recent years, with the increasingly serious energy crisis and environmental pollution problems, fuel cell technology has developed rapidly. Proton exchange membrane fuel has broad application prospects due to its advantages such as high battery energy conversion efficiency, no pollution to the environment, low noise, and good compatibility and integration with other subsystems in the vehicle. Therefore, it is of great significance to accurately and quickly detect faults that occur in PEMFC fuel cells during operation.

[0003] At present, the main fault diagnosis methods at home and abroad are divided into two categories. The first category is the model-based fault diagnosis method, and the second category is the data-driven fault diagnosis method, which makes full use of the key parameter data monitored by the sensor and the historically stored data, and combines artificial intelligence and other technologies to mine fault feature information to achieve accurate diagnosis of system faults. Traditional diagnosis methods include RF, ELM and SVM, but traditional diagnosis methods are too dependent on the integrity of data labels and the consistency of data distribution, and require a large number of fault data sets to train fault diagnosis models. In most practical application scenarios, since data labels are difficult to obtain or the cost of obtaining them is too high, and PEMFC fuel cells will make the working conditions diverse and complex under different load drives, the use of a large number of sensors will cause many sensors to detect data deviations. The above problems have caused the traditional data-driven method to have unsatisfactory fault diagnosis results and low accuracy. Therefore, there is an urgent need for a method that can accurately diagnose proton exchange membrane fuel cell faults in the case of incomplete data labels and a lack of a large amount of PEMFC fault data. Summary of the invention

[0004] Purpose of the invention: The present invention proposes a proton exchange membrane fuel cell fault diagnosis method based on transfer learning, which solves the problem of decreased performance of the fault diagnosis model caused by the difficulty in obtaining data labels and the lack of fault data sets, and improves the PEMFC diagnosis efficiency and applicability.

[0005] Technical solution: The present invention provides a proton exchange membrane fuel cell fault diagnosis method based on transfer learning, comprising the following steps:

[0006] (1) Construct a high-dimensional PEMFC dataset in the source domain and a labeled PEMFC dataset in the current target domain, corresponding to different fault states of PEMFC;

[0007] (2) The source domain high-dimensional PEMFC data and the current target domain PEMFC data are used as the input of the uniform manifold approximation and projection algorithm UMAP to reduce the dimensionality of the high-dimensional data set and remove the influence of redundant information;

[0008] (3) Divide the data set and build a TimesNet model diagnostic framework;

[0009] (4) The high-dimensional PEMFC data after dimensionality reduction is used as the source domain of the TimesNet model for pre-training;

[0010] (5) Using a small amount of labeled data from the current target domain PEMFC, the parameters of the TimesNet model are fine-tuned through transfer learning to obtain the final diagnostic model;

[0011] (6) For the unlabeled data of the fuel cell to be diagnosed, the same sensor working signal acquisition method as the labeled data set is adopted. The PEMFC data set collected by the current sensor is input into the TimesNet diagnosis model for classification to obtain the different working states of the PEMFC.

[0012] Furthermore, the source domain high-dimensional PEMFC data in step (1) includes voltage, current, temperature, and concentration of the cathode and anode of the proton exchange membrane fuel cell.

[0013] Furthermore, the source domain high-dimensional PEMFC dataset in step (1) is S s :

[0014] S s ={(x n,i ,y n,i ),x n,i ∈A n ,y n,i ∈B n} (1)

[0015] Among them, A n Represents a labeled dataset S s The working signal data sample set of the fuel cell, x n,i Represents the working signal data sample set A n The i-th working signal data sample in B n Represents a labeled dataset S s The health status label set of the fuel cell in y n,i Represents the working signal data sample x n,i The corresponding health status label.

[0016] Furthermore, the implementation process of step (2) is as follows:

[0017] For the input data set {x1,…,x1,…,xn} for each x i , γ is a given hyperparameter, define θ i and δ i :

[0018]

[0019] Among them, θ i The choice of must ensure that there is at least one data point with an edge weight of 1 with x i Connected, δ i is the length scale parameter, x n represents the number of samples in the data set, d(x i ,x j ) represents the sample point x i and its neighboring point x j The distance between

[0020] Defining a directed weighted graph use The symmetric property of defines an undirected weighted graph Z; let B be the weighted adjacency matrix of Z, and we get a symmetric matrix D:

[0021]

[0022] Among them, the undirected weighted neighborhood graph Z is defined using the adjacency matrix D. is the Hadamard product;

[0023] UMAP applies gravitational and repulsive forces along the boundaries and vertices to evolve a point set {f i The cross entropy metric is used to calculate the difference between the weighted neighborhood graphs Z and H, so that the topological structure of the source data captured by H and Z matches, thereby obtaining a low-dimensional representation of the overall topology of the data.

[0024] Furthermore, the implementation process of step (3) is as follows:

[0025] The dataset is divided into training set and test set, the first 80% is the training set and the last 20% is the test set; TimesNet consists of stacked TimesBlocks, and the input sequence is embedded in the layer to obtain deep features. For the time block of the lth layer, the input is Then, 2D convolution is used to extract the two-dimensional temporal changes:

[0026]

[0027] The original one-dimensional time series data X is converted into 1D Fold according to the following formula:

[0028]

[0029] In the formula, is the 2D tensor after the i-th transformation, Padding(X 1D ) pads the end of the sequence with zeros to align it so that the sequence length can be i Divisible by Reshape the one-dimensional sequence data after zero padding. i Indicates the corresponding X 1D The frequency, P i For X 1D cycle.

[0030] Furthermore, the specific process of the time block is as follows: Convert one dimension into two dimensions: First, the one-dimensional time series feature of the input Extract the period and convert it into a two-dimensional tensor to represent the two-dimensional time series changes;

[0031] Extracting two-dimensional temporal change representation: For two-dimensional tensors, due to their two-dimensional locality, the Inception model is used to extract information, namely:

[0032]

[0033] Transform two dimensions to one dimension: For the extracted temporal features, transform them back to one-dimensional space for information aggregation:

[0034]

[0035] In the formula, Indicates that Padding(X 1D ) The 0 added by the operation is removed;

[0036] Adaptive Fusion: Representing One Dimension The final output is obtained by weighted summing according to the corresponding frequency:

[0037]

[0038] in, Indicates the corresponding X 1D The magnitude of , Softmax() represents the Softmax classifier, Represents the output after the Softmax classifier.

[0039] Furthermore, the implementation process of step (4) is as follows:

[0040] The TimesNet model is used to perform Fourier transform on PEMFC data, expand the analysis of time series signals to two-dimensional space, reconstruct one-dimensional data into two-dimensional tensors, and thus obtain two-dimensional changes in time. Before selection, the harmonic information in the input data is obtained by Fourier transform, including amplitude, frequency and cycle length;

[0041] According to the selected frequency and cycle length, the Padding layer is used to zero-expand the time series signal along the time dimension, and the one-dimensional time series signal is reconstructed into multiple two-dimensional tensors;

[0042] TimesBlock based on TimesNet captures various time changes of k different reconstruction tensors and performs adaptive aggregation to effectively extract signal features and reconstruct one-dimensional time series signals; an adaptive fusion learning model is used for state recognition and fault classification;

[0043] For fault classification, a cross entropy loss function is defined. By training the fault diagnosis source domain model based on TimesNet, the optimal parameters of the network are obtained to minimize the error of the loss function. The lower the p1 in the loss function, the better the diagnosis effect:

[0044]

[0045] Among them, ρ(x) represents the output result of Softmax in TimesNet, and its target value is σ(x).

[0046] Furthermore, the implementation process of step (5) is as follows:

[0047] When the target domain PEMFC data is input into the deep transfer learning model, the TimesNet model first trains the shallow structure based on the source domain data to extract shallow features. At this time, the shallow structure of the target domain will be frozen;

[0048] At the same time, the parameters of the trained TimesNet model are shared with the deep structure of the target domain to extract deep features for initialization. At this time, the deep structure parameters will be adjusted to achieve the final classification and recognition of the input PEMFC data;

[0049] After extracting the deep features of the target domain data, the convolutional layer of the deep transfer model operates on its features to obtain signal classification and recognition results;

[0050] The results are input into the fully connected layer Dense layer of the TimesNet model, and the loss function is set in the fully connected layer of the transfer learning model to obtain a model with higher accuracy in fault identification.

[0051] Furthermore, the loss function is the joint maximum mean difference (JMMD) to measure the distribution difference between the source domain and the target domain, and to measure the error between the recognition result and the expected result to control the result accuracy; the JMMD loss function is:

[0052]

[0053] Among them, E P and E Q are the expectations of the source domain P and the target domain Q respectively, Represents the feature map of the source domain data in the Hilbert space, is the feature map of the target domain data in the Hilbert space, |L| represents the number of layers, h1 and h2 represent the activations generated by the source and target domains, and H l Represents the reproducing kernel Hilbert space of the lth layer of the model, embeds the loss function into the transfer learning model, and obtains the model loss function as follows:

[0054] p0=p1+λp JMMD (12)

[0055] Among them, p0 represents the loss function of the entire transfer learning network model, p1 represents the classification loss function of the fault data source domain, and λ represents the trade-off parameter of the JMMD function.

[0056] Furthermore, the different operating states of the PEMFC in step (6) are normal PEMFC, membrane dry and water flooded.

[0057] Beneficial effects: Compared with the prior art, the present invention has the following beneficial effects:

[0058] 1. Aiming at the scarcity of labeled fault sample datasets of PEMFC, the present invention learns the TimesNet model in the source domain dataset, then fine-tunes the model and migrates it to the target domain dataset under the working conditions to be diagnosed, and processes the unlabeled signal data efficiently and accurately, solving the problems of the scarcity of PEMFC fault datasets and the difficulty in obtaining labeled fault data;

[0059] 2. The present invention first defines a cross entropy loss function for the result of source domain fault diagnosis to better train the model. At the same time, a joint maximum mean difference function is set in the transfer learning model to measure the distribution difference between the source domain and the target domain. In the final model loss function, the cross entropy loss function defined in the source domain and the JMMD function used in transfer learning are combined to obtain a model with higher accuracy and stronger applicability for fault identification.

[0060] 3. In view of the large amount of data and high complexity of the collected 26-dimensional fault data set, the present invention uses the UMAP method to reduce the dimensionality of the labeled high-dimensional data in the source domain and the target domain, eliminates the influence of invalid signals on the model accuracy and effectively reduces the input dimension and complexity. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 is a flow chart of the present invention;

[0062] Figure 2 This is a structural diagram of the TimesNet diagnostic model provided by the present invention. DETAILED DESCRIPTION

[0063] The present invention will be further described in detail below in conjunction with the accompanying drawings.

[0064] like Figure 1 As shown, the present invention proposes a proton exchange membrane fuel cell fault diagnosis method based on transfer learning, and the specific steps are as follows:

[0065] Step 1: Construct a high-dimensional dataset in the source domain and a small amount of labeled datasets collected by the current target domain PEMFC, including a 26-dimensional dataset of voltage, current, temperature, concentration, etc. of the cathode and anode collected by sensors, corresponding to different fault states of PEMFC.

[0066] The obtained labeled high-dimensional dataset is denoted as S s :

[0067] S s ={(x n,i ,y n,i ),x n,i ∈A n ,y n,i ∈B n}(1)

[0068] Among them, A n Represents a labeled dataset S s The working signal data sample set of the fuel cell, x n,i Represents the working signal data sample set A n The i-th working signal data sample in B n Represents a labeled dataset S s The health status label set of the fuel cell in y n,i Represents the working signal data sample x n,i The corresponding health status label.

[0069] Step 2: Use a large amount of high-dimensional PEMFC data and a small amount of labeled data collected from the current target domain PEMFC as input to the Uniform Manifold Approximation and Projection algorithm (UMAP) to reduce the dimensionality of the high-dimensional data set and remove the influence of redundant information.

[0070] The PEMFC high-dimensional data set is reduced in dimension using UMAP, which is based on the theoretical framework of Riemannian geometry and algebraic topology. It can retain the characteristics of the original data to the greatest extent and reduce the characteristic dimension. The steps of UMAP are as follows:

[0071] For the input data set {x1,…,x1,…,x n} for each x i , γ is a given hyperparameter, define θ i and δ i :

[0072]

[0073] Among them, θ i The choice of must ensure that there is at least one data point with an edge weight of 1 with x i Connected, δ i is the length scale parameter, x n represents the number of samples in the data set, d(x i ,x j ) represents the sample point x i and its neighboring point x j The distance between.

[0074] Defining a directed weighted graph use The symmetric property of defines an undirected weighted graph Z. Let C be the weighted adjacency matrix of Z, and we can get a symmetric matrix D:

[0075]

[0076] Among them, the undirected weighted neighborhood graph Z is defined using the adjacency matrix D. is the Hadamard product.

[0077] UMAP applies gravitational and repulsive forces along the boundaries and vertices to evolve a point set {f i The equivalent weighted graph H constructed by}, i = 1...N. The cross entropy metric is used to calculate the difference between the weighted neighborhood graphs Z and H, so that the topological structure of the source data captured by H and Z can be matched, thereby obtaining a low-dimensional representation of the overall topology of the data.

[0078] Step 3: Divide the data set and build the time series basic model TimesNet diagnostic framework.

[0079] The dataset is divided into training set and test set, the first 80% is the training set and the last 20% is the test set. TimesNet consists of stacked time blocks TimesBlock. The input sequence is embedded in the layer to obtain deep features. The construction steps include:

[0080] For the time block of layer l, the input is Then, 2D convolution is used to extract the two-dimensional temporal changes:

[0081]

[0082] The original one-dimensional time series data X is converted into 1D Fold according to the following formula:

[0083]

[0084] in, is the 2D tensor after the i-th transformation, Padding(X 1D ) pads the end of the sequence with zeros to align it so that the sequence length can be i divisible, Reshape the one-dimensional sequence data after zero padding. i Indicates the corresponding X 1D The frequency, P i For X 1D cycle.

[0085] The specific process of the time block is as follows:

[0086] Convert one dimension into two dimensions: First, the one-dimensional time series features of the input The cycles are extracted and converted into a two-dimensional tensor to represent the two-dimensional temporal changes.

[0087] Extracting two-dimensional temporal change representation: For two-dimensional tensors, due to their two-dimensional locality, this study used the Inception model to extract information, namely:

[0088]

[0089] Transform two dimensions to one dimension: For the extracted temporal features, transform them back to one-dimensional space for information aggregation:

[0090]

[0091] In the formula, Indicates that Padding(X 1D) operation to remove the added 0.

[0092] Adaptive Fusion: Representing One Dimension The final output is obtained by weighted summing according to the corresponding frequency:

[0093]

[0094] in, Indicates the corresponding X 1D The magnitude of , Softmax() represents the Softmax classifier, Represents the output after the Softmax classifier.

[0095] Step 4: Use the reduced high-dimensional PEMFC data as the source domain of the TimesNet model and pre-train it to obtain a trained TimesNet pre-diagnosis model, including:

[0096] The TimesNet model is used to perform Fourier transform on PEMFC data, expand the analysis of time series signals to two-dimensional space, reconstruct one-dimensional data into two-dimensional tensors, and thus obtain two-dimensional changes in time. Before selection, the harmonic information in the input data is obtained by Fourier transform, including amplitude, frequency and cycle length.

[0097] According to the selected frequency and cycle length, the Padding layer is used to zero-expand the time series signal along the time dimension and reconstruct the one-dimensional time series signal into multiple two-dimensional tensors.

[0098] TimesBlock based on TimesNet captures various time changes of k different reconstruction tensors and performs adaptive aggregation to effectively extract signal features and reconstruct one-dimensional time series signals. An adaptive fusion learning model is used for state recognition and fault classification.

[0099] For fault classification, a cross entropy loss function is defined. A fault diagnosis source domain model based on TimesNet is established for training. The optimal parameters of the network are obtained by testing the diagnosis model, minimizing the error of the loss function, and obtaining a pre-diagnosis model. The lower the p1 in the loss function, the better the diagnosis effect. The p1 formula is:

[0100]

[0101] Among them, ρ(x) represents the output result of Softmax in TimesNet, and its target value is σ(x).

[0102] Step 5: Use the small amount of labeled data of the target domain collected by the current PEMFC to extract UMAP features, and then divide the labeled data of the target domain into the training set and the test set. Then fine-tune the parameters of the TimesNet model through transfer learning. The constructed transfer learning mainly includes the input layer, convolution layer, fully connected layer and output layer. The migration process includes the following steps:

[0103] When the target domain PEMFC data is input into the deep transfer learning model, the TimesNet model first trains the shallow structure based on the source domain data to extract shallow features. At this time, the shallow structure Dropout layer and Norm Layer of the target domain will be frozen.

[0104] At the same time, the parameters of the trained TimesNet model are shared with the deep structure of the target domain to extract deep feature initialization. At this time, the deep structure parameters will be adjusted to achieve the final classification and recognition of the input PEMFC data.

[0105] After extracting the deep features of the target domain data, the convolutional layer of the deep transfer model operates on its features to obtain signal classification and recognition results.

[0106] The result is input into the fully connected layer Dense layer of the TimesNet model, and the loss function is set in the fully connected layer of the transfer learning model. Specifically, JMMD is used to measure the distribution difference between the source domain and the target domain, and the error between the recognition result and the expected result is measured to control the result accuracy. The JMMD loss function is:

[0107]

[0108] Among them, E P and E Q are the expectations of the source domain P and the target domain Q respectively, Represents the feature map of the source domain data in the Hilbert space, is the feature map of the target domain data in the Hilbert space, |L| represents the number of layers, h1 and h2 represent the activations generated by the source and target domains, and H l Represents the reproducing kernel Hilbert space of the lth layer of the model. The loss function of the above formula is embedded into the transfer learning model. Combined with the loss function of the source domain diagnosis model, the model loss function can be finally obtained as:

[0109] p0=p1+λp JMMD (12)

[0110] Among them, p0 represents the loss function of the entire transfer learning network model, p1 represents the classification loss function of the fault data source domain, and λ represents the trade-off parameter of the JMMD function.

[0111] By setting the loss function and fine-tuning the diagnostic network model, we can finally obtain a model that can identify faults with high accuracy.

[0112] Step 6: For the unlabeled data of the fuel cell to be diagnosed, the same sensor working signal acquisition method as the labeled data set is adopted. The PEMFC data set collected by the current sensor is input into the trained TimesNet diagnostic model for classification, and the three working states of PEMFC normal, membrane dry and flooded can be obtained.

[0113] The above embodiments are only for illustrating the technical concept and features of the present invention, and their purpose is to enable people familiar with the technology to understand the content of the present invention and implement it accordingly, and they cannot be used to limit the protection scope of the present invention. Any equivalent transformation or modification made according to the spirit of the present invention should be included in the protection scope of the present invention.

Claims

1. A proton exchange membrane fuel cell fault diagnosis method based on transfer learning, characterized in that: The following steps are involved: (1) Construct a high-dimensional PEMFC dataset in the source domain and a labeled PEMFC dataset in the current target domain, corresponding to different fault states of PEMFC; (2) The source domain high-dimensional PEMFC data and the current target domain PEMFC data are used as the input of the uniform manifold approximation and projection algorithm UMAP to reduce the dimensionality of the high-dimensional data set and remove the influence of redundant information; (3) Divide the data set and build a TimesNet model diagnostic framework; (4) The high-dimensional PEMFC data after dimensionality reduction is used as the source domain of the TimesNet model for pre-training; (5) Using a small amount of labeled data from the current target domain PEMFC, the parameters of the TimesNet model are fine-tuned through transfer learning to obtain the final diagnostic model; (6) For the unlabeled data of the fuel cell to be diagnosed, the same sensor working signal acquisition method as the labeled data set is adopted. The PEMFC data set collected by the current sensor is input into the TimesNet diagnosis model for classification to obtain the different working states of the PEMFC.

2. According to the method for proton exchange membrane fuel cell fault diagnosis based on transfer learning described in claim 1, it is characterized in that: The source domain high-dimensional PEMFC data in step (1) includes the voltage, current, temperature, and concentration of the cathode and anode of the proton exchange membrane fuel cell.

3. According to the method for proton exchange membrane fuel cell fault diagnosis based on transfer learning described in claim 1, it is characterized in that: The source domain high-dimensional PEMFC dataset in step (1) is S s : S s ={(x n,i ,and n,i ),x n,i ∈A n ,and n,i ∈B n }(1) Among them, A n Represents a labeled dataset S s The working signal data sample set of the fuel cell, x n,i Represents the working signal data sample set A n The i-th working signal data sample in B n Represents a labeled dataset S s The health status label set of the fuel cell in y n,i Represents the working signal data sample x n,i The corresponding health status label.

4. According to the method for proton exchange membrane fuel cell fault diagnosis based on transfer learning described in claim 1, it is characterized in that: The implementation process of step (2) is as follows: For the input data set {x1,…,x1,…,x n } for each x i , γ is a given hyperparameter, define θ i and δ i : Among them, θ i The choice of must ensure that there is at least one data point with an edge weight of 1 with x i Connected, δ i is the length scale parameter, x n represents the number of samples in the data set, d(x i ,x j ) represents the sample point x i and its neighboring point x j The distance between Defining a directed weighted graph use The symmetric property of defines an undirected weighted graph Z; let B be the weighted adjacency matrix of Z, and we get a symmetric matrix D: Among them, the undirected weighted neighborhood graph Z is defined using the adjacency matrix D. is the Hadamard product; UMAP applies gravitational and repulsive forces along the boundaries and vertices to evolve a point set {f i The cross entropy metric is used to calculate the difference between the weighted neighborhood graphs Z and H, so that the topological structure of the source data captured by H and Z matches, thereby obtaining a low-dimensional representation of the overall topology of the data.

5. According to the method for proton exchange membrane fuel cell fault diagnosis based on transfer learning described in claim 1, it is characterized in that: The implementation process of step (3) is as follows: The dataset is divided into training set and test set, the first 80% is the training set and the last 20% is the test set; TimesNet consists of stacked TimesBlocks, and the input sequence is embedded in the layer to obtain deep features. For the time block of the lth layer, the input is Then, 2D convolution is used to extract the two-dimensional temporal changes: The original one-dimensional time series data X is converted into 1D Fold according to the following formula: In the formula, is the 2D tensor after the i-th transformation, Padding(X 1D ) pads the end of the sequence with zeros to align it so that the sequence length can be i Divisible by Reshape the one-dimensional sequence data after zero padding. i Indicates the corresponding X 1D The frequency, P i For the corresponding X 1D cycle.

6. According to the method for proton exchange membrane fuel cell fault diagnosis based on transfer learning as described in claim 1, it is characterized in that: The specific process of the time block is as follows: Convert one dimension into two dimensions: First, the input one-dimensional time series feature Extract the period and convert it into a two-dimensional tensor to represent the two-dimensional time series changes; Extracting two-dimensional temporal change representation: For two-dimensional tensors, due to their two-dimensional locality, the Inception model is used to extract information, namely: Transform two dimensions to one dimension: For the extracted temporal features, transform them back to one-dimensional space for information aggregation: In the formula, Trunc(Reshape1, Indicates that Padding(X 1D ) The 0 added by the operation is removed; Adaptive Fusion: Representing One Dimension The final output is obtained by weighted summing according to the corresponding frequency: in, Indicates the corresponding X 1D The magnitude of , Softmax() represents the Softmax classifier, Represents the output after the Softmax classifier.

7. According to the method for proton exchange membrane fuel cell fault diagnosis based on transfer learning as described in claim 1, it is characterized in that: The implementation process of step (4) is as follows: The TimesNet model is used to perform Fourier transform on PEMFC data, expand the analysis of time series signals to two-dimensional space, reconstruct one-dimensional data into two-dimensional tensors, and thus obtain two-dimensional changes in time. Before selection, the harmonic information in the input data is obtained by Fourier transform, including amplitude, frequency and cycle length; According to the selected frequency and cycle length, the Padding layer is used to zero-expand the time series signal along the time dimension, and the one-dimensional time series signal is reconstructed into multiple two-dimensional tensors; TimesBlock based on TimesNet captures various time changes of k different reconstruction tensors and performs adaptive aggregation to effectively extract signal features and reconstruct one-dimensional time series signals; an adaptive fusion learning model is used for state recognition and fault classification; For fault classification, a cross entropy loss function is defined. By training the fault diagnosis source domain model based on TimesNet, the optimal parameters of the network are obtained to minimize the error of the loss function. The lower the p1 in the loss function, the better the diagnosis effect: Among them, ρ(x) represents the output result of Softmax in TimesNet, and its target value is σ(x).

8. According to the method for proton exchange membrane fuel cell fault diagnosis based on transfer learning as described in claim 1, it is characterized in that: The implementation process of step (5) is as follows: When the target domain PEMFC data is input into the deep transfer learning model, the TimesNet model first trains the shallow structure based on the source domain data to extract shallow features. At this time, the shallow structure of the target domain will be frozen; At the same time, the parameters of the trained TimesNet model are shared with the deep structure of the target domain to extract deep features for initialization. At this time, the deep structure parameters will be adjusted to achieve the final classification and recognition of the input PEMFC data; After extracting the deep features of the target domain data, the convolutional layer of the deep transfer model operates on its features to obtain signal classification and recognition results; The results are input into the fully connected layer Dense layer of the TimesNet model, and the loss function is set in the fully connected layer of the transfer learning model to obtain a model with higher accuracy in fault identification.

9. A proton exchange membrane fuel cell fault diagnosis method based on transfer learning according to claim 1, characterized in that: The loss function is the joint maximum mean difference (JMMD) to measure the distribution difference between the source domain and the target domain, and to measure the error between the recognition result and the expected result to control the result accuracy; the JMMD loss function is: Among them, E P and E Q are the expectations of the source domain P and the target domain Q, respectively. Represents the feature map of the source domain data in the Hilbert space, is the feature map of the target domain data in the Hilbert space, |L| represents the number of layers, h1 and h2 represent the activations generated by the source and target domains, and H l Represents the reproducing kernel Hilbert space of the lth layer of the model, embeds the loss function into the transfer learning model, and obtains the model loss function as follows: p0=p1+λp JMMD (12) Where p0 represents the loss function of the entire transfer learning network model, p1 represents the classification loss function of the fault data source domain, and λ represents the trade-off parameter of the JMMD function.

10. A proton exchange membrane fuel cell fault diagnosis method based on transfer learning according to claim 1, characterized in that: The different working states of the PEMFC in step (6) are normal PEMFC, membrane dry and water flooded.

Citation Information

Patent Citations

  • Fault diagnosis method and system for proton exchange membrane fuel cell integrated system

    CN116187195A

  • Proton exchange membrane fuel cell system fault diagnosis method based on PSO-GWO-DELM

    CN117276600A

  • Display device and display panel

    KR1020240142153A