EHA performance degradation prediction method and system based on PreDyn-ST model

Abstract

The present invention relates to an EHA performance degradation prediction method and system based on the PreDyn-ST model, and proposes a performance degradation prediction method and system for an EHA hydraulic system based on a deep learning method (PreDyn-ST) model. The method of the present invention includes: S1, building an EHA test bench; S2, signal acquisition; S3, obtaining degradation labels; S4, building a PreDyn-ST model; S5, PreDyn-ST model training; S6, obtaining life prediction results predicted by the model. On the other hand, the system of the present invention includes a data acquisition module, a degradation label definition module, a model construction module, a data partitioning module, and a model verification and prediction module. The present invention can visualize the dynamic changes of spatiotemporal characteristics during the degradation process, and interpret these changes in combination with the physical degradation mechanism, thereby enhancing the interpretability of the model and improving the credibility of the model.

Description

Technical Field

[0001] The present invention belongs to the field of EHA hydraulic system performance degradation prediction, and in particular relates to an EHA performance degradation prediction method and system based on a PreDyn-ST model. Background Art

[0002] As the primary power source for flight control, the aircraft hydraulic system provides power for takeoff, maneuvering, landing gear retraction and extension, and braking, making it a critical system closely related to flight safety. Currently, the most widely used system on civil airliners is the traditional centralized hydraulic system, but it still suffers from drawbacks such as high energy loss and low efficiency. High-performance electrohydrostatic actuators (EHAs), with their advantages of small size, light weight, fast response, and high power-to-weight ratio, can replace the defect-prone traditional centralized hydraulic systems with a compact and reliable independent direct drive method. They have already found application as redundant systems on large civil airliners and hold great promise for future applications.

[0003] However, airlines currently record onboard QAR and EICAS hydraulic system data only as independent parameters, which lack a direct relationship to the aircraft hydraulic system's health. Because changes in system health still require indirect analysis, correlation analysis, or damage conversion based on alternating loads, accurate and real-time characterization of the aircraft hydraulic system's health is difficult.

[0004] In practical applications, system degradation processes cause interactions between temporal and spatial characteristics. Simply superimposing spatiotemporal characteristics cannot adapt to these dynamic changes. In particular, the weights of spatiotemporal characteristics must be flexibly adjusted across different degradation stages to effectively reflect the transitions in system states. A key challenge is to develop models that dynamically adapt to these changes in spatiotemporal characteristics, thereby improving the accuracy and robustness of modeling multi-sensor time series data with complex degradation patterns and processes. Summary of the Invention

[0005] In response to the shortcomings of the existing technology, the present invention provides an EHA performance degradation prediction method and system based on the PreDyn-ST model. This method can visualize the dynamic changes of spatiotemporal characteristics during the degradation process and interpret these changes in combination with the physical degradation mechanism, thereby enhancing the interpretability of the model and improving the credibility of the model.

[0006] To achieve the above objectives, the present invention discloses the following technical solutions:

[0007] In a first aspect, the present invention relates to a method for predicting EHA performance degradation based on the PreDyn-ST model, comprising the following steps:

[0008] S1. Build an EHA test bench;

[0009] S2. Signal acquisition: The data acquisition sensor collects the piston rod displacement sensor signal, force sensor signal, flow and pressure signals of the two chambers of the hydraulic servo cylinder, servo motor current signal, and servo motor speed signal;

[0010] S3. Establishing a component function signal set with degradation labels: Obtaining system efficiency based on sensor signal data, using the system efficiency as a degradation label, and establishing a component function signal set with degradation labels;

[0011] S4. Build the PreDyn-ST model: This model is constructed using the SimCLR architecture for contrastive learning, the GCN spatial feature extraction module based on physical priors, and the Transformer temporal feature extraction module. The output of the PreDyn-ST model is used as the system life prediction result. This model includes the following sub-steps:

[0012] S41. Use the SimCLR architecture of contrastive learning to shorten the distance between positive samples and increase the distance between negative samples in the sliding window of the multivariate time series of sensor signal data to generate enhanced data.

[0013] S42, inputting the enhanced data into a feature extraction module to perform preliminary feature extraction;

[0014] S43, the extracted features are input into the Transformer temporal feature extraction module and the GCN spatial feature extraction module based on physical prior respectively;

[0015] S44. As the degradation stage changes, the PreDyn-ST model adaptively adjusts the weights of the Transformer temporal feature extraction module and the physical prior-based GCN spatial feature extraction module and outputs the system life prediction results;

[0016] S5, PreDyn-ST model training: After dividing the component functional signal set with degradation labels in S3 into a training set, a validation set, and a test set, the PreDyn-ST model is trained and validated, and the model parameters are adjusted to obtain the trained PreDyn-ST model;

[0017] S6. Obtain the life prediction result predicted by the model: The multivariate time series sequence of sensor signal data is collected in real time and input into the PreDyn-ST model trained in S5, and the predicted system life prediction result is output. It is judged whether the system life prediction result is lower than the set threshold, and the performance degradation state of the EHA is determined based on the judgment result.

[0018] Furthermore, in step S4, the SimCLR architecture represents the loss of the entire sample by averaging the losses of all positive sample pairs;

[0019] The loss for a positive pair is defined as:

[0020]

[0021] Among them, sim(z i ,z j ) is z i and z j The cosine similarity between , defined as τ is a temperature parameter; Z is the eigenvector of the positive sample pair; i, j and k are all parameters; 1 [k≠i] is an indicator function that takes 1 when k≠i and 0 otherwise; the denominator is summed over all 2N possible pairs in the batch, excluding positive sample pairs;

[0022] The total loss is calculated by averaging the losses of all positive pairs in the batch:

[0023]

[0024] Furthermore, in step S4, in the graph G=(V,ξ,A) formed by the EHA data in the physical prior-based GCN spatial feature extraction module, V is the number of nodes, i.e., the number of sensors; ξ is the edge set between each pair of connected nodes; is the adjacency matrix showing the spatial relationship between nodes; L = I n -D -1 / 2 AD -1 / 2 is the symmetric normalized graph Laplace matrix, and the diagonal matrix D is calculated based on the adjacency matrix, that is, is the eigenvalue of L;

[0025] The convolution of vertex embedding and filter f is expressed as:

[0026] h=x* g f=U((U T x)⊙(U T f))

[0027] in, is the eigenvector matrix of the Laplace matrix, ⊙ represents the Hadamard product;

[0028] Diagonal matrix g θ , g θ For U T The diagonal matrix representation of f is:

[0029] gθ =diag(U T f)=diag(θ0,θ1,…,θ n-1 )

[0030] Among them, diag is the operation of converting the vector into a diagonal matrix, θ i is each characteristic component after projection into the frequency domain;

[0031] The initial graph convolution formula can be obtained:

[0032] h=x* g f=Ug θ U T x;

[0033] Simplify graph convolution calculation using Chebyshev polynomials:

[0034]

[0035] in, and are the rescaled eigenvalues and Laplace matrices, respectively, is the Chebyshev coefficient, is a Chebyshev polynomial of order k, is an explicitly defined convolution kernel.

[0036] Furthermore, in step S4, in the Transformer temporal feature extraction module:

[0037] The self-attention calculation mechanism is expressed as:

[0038]

[0039] Among them, Q, K, and V are query, key, and value matrices respectively. Then calculate the similarity between each element in the sequence and other elements to determine its attention weight;

[0040] The multi-head attention function is expressed as:

[0041] MultiHead(Q,K,V)=Concat(head1,head2,…,head h )W O

[0042] head i For each attention head (i=1,2,3...k) in the multi-head attention, W o is the output linear transformation matrix;

[0043] Among them, the calculation method of each attention head is:

[0044]

[0045] The formula for preserving the position information of the sequence is:

[0046]

[0047] Among them, pos is the position index, i is the dimension index, d model The dimensions of the model.

[0048] Furthermore, in said S1, the EHA test bench constructed includes an active part and a load part of the EHA drive, wherein the active part includes a servo motor, a gear pump, a servo hydraulic cylinder and a plurality of data acquisition sensors;

[0049] The load part adopts an opposing cylinder structure including a motor pump, a relief valve and multiple one-way valves.

[0050] On the other hand, the present invention relates to a system for predicting EHA performance degradation based on the PreDyn-ST model, which includes: a data acquisition module, a degradation label definition module, a model construction module, a data partitioning module, and a model verification and prediction module:

[0051] Data acquisition module: collects piston rod displacement sensor signals, force sensor signals used to display load size, flow and pressure signals of the two chambers of the hydraulic servo cylinder, servo motor current signals, and servo motor speed signals through sensors on the EHA test bench;

[0052] Degradation label definition module: organizes the signals collected in the EHA test bench and outputs them as system efficiency as degradation labels;

[0053] Model building module: build PreDyn-ST model;

[0054] Data partitioning module: divides the data in the collected EHA dataset into training set, validation set, and test set;

[0055] Model verification and prediction module: adjusts model parameters, trains and verifies the extracted feature labels with the PreDyn-ST model, and performs time series prediction to obtain performance indicator results of the model prediction.

[0056] Compared with the prior art, the present invention has the following beneficial effects:

[0057] (1) This paper addresses the temporal dependence and spatial structural changes in multi-sensor time series (MTS) data caused by different stages of the degradation process and proposes a method to capture the changes in spatiotemporal characteristics during the degradation process using dynamic weights. This method can visualize the dynamic changes in spatiotemporal characteristics during the degradation process and interpret these changes in conjunction with the physical degradation mechanism, thereby enhancing the interpretability and credibility of the model.

[0058] (2) This paper proposes a PreDyn-ST method based on a pre-training strategy. First, the contrastive learning method is used to perform data enhancement on the sliding window of the time series sequence. Then, the GCN framework is used to construct the spatial feature module in the downstream task, and the Transformer is used to construct the temporal feature module. Finally, dynamic weights are used to adaptively adjust the spatiotemporal ratio according to the changes in the degradation process to achieve degradation prediction.

[0059] (3) The present invention simulates the working conditions of the aircraft hydraulic system by using an electrostatic hydraulic actuator (EHA) performance degradation test bench, conducts accelerated degradation tests, and obtains degradation data of the EHA system. Based on the proposed method, these degradation data are effectively predicted, demonstrating the applicability and accuracy of the method under actual working conditions. In addition, the generalization ability of the model is verified on the C-MAPSS dataset. The results show that the model not only performs well in the EHA system, but also has high accuracy and robustness in degradation prediction tasks in different fields. This experiment further demonstrates the model's potential for wide application in a variety of complex systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 Flowchart of the EHA performance degradation prediction method based on the PreDyn-ST model of the present invention;

[0061] Figure 2 This is a schematic diagram of the EHA test bench of the present invention;

[0062] Figure 3 Schematic diagram of the comparative learning model structure for processing MTS data in the present invention;

[0063] Figure 4 Schematic diagram of the structure of the GCN spatial feature extraction module based on physical priors of the present invention;

[0064] Figure 5 This is a schematic diagram of the structure of the Transformer temporal feature extraction module of the present invention;

[0065] Figure 6 This is a schematic diagram of the PreDyn-ST framework flow of the present invention;

[0066] Figure 7Schematic diagram of the overall framework for predicting EHA performance degradation according to the present invention;

[0067] Figure 8 Schematic diagram of feature distribution before and after EHA data pre-training of the present invention;

[0068] Figure 9 This is a comparison chart of the predicted and actual EHA efficiency values in one day of the experiment of the present invention;

[0069] Figure 10 This is a comparison chart of the actual RUL and predicted RUL of a single engine in the C-MAPSS test set of the present invention;

[0070] Figure 11 Schematic diagram of the EHA data training and validation loss curve of the present invention;

[0071] Figure 12 Schematic diagram of the overall CSI curve of the C-MAPSS training data set of the present invention;

[0072] Figure 13 This is the experimental CSI curve and dynamic weight change diagram of the EHA dataset within one day of the present invention. DETAILED DESCRIPTION

[0073] The exemplary embodiments, features, and aspects of the present invention will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise indicated.

[0074] On the one hand, the present invention provides an EHA performance degradation prediction method based on the PreDyn-ST model, such as Figures 1-13 As shown in FIG, the EHA performance degradation prediction method based on the PreDyn-ST model includes the following steps:

[0075] S1. Build an EHA test bench.

[0076] S2. Signal acquisition: The data acquisition sensor is used to collect the piston rod displacement sensor signal, force sensor signal, flow and pressure signals of the two chambers of the hydraulic servo cylinder, servo motor current signal and servo motor speed signal.

[0077] S3. Obtain degradation labels: Obtain corresponding system efficiency according to component function signals, use the system efficiency as a degradation label, and establish a component function signal set with degradation labels.

[0078] In this embodiment, the system efficiency is the efficiency of the EHA hydraulic system motor pump, which is stable at 25%-30% under normal operating conditions. If the system degrades, the efficiency will decrease. The efficiency of the EHA hydraulic system motor pump can be calculated by extracting and calculating from the component function signal data.

[0079] S4. Construct PreDyn-ST model: Use the SimCLR architecture of contrastive learning to construct the PreDyn-ST model based on the physical prior-based GCN spatial feature extraction module and the Transformer temporal feature extraction module, and use the output degradation label as the warning value.

[0080] Among them, the GCN spatial feature extraction module based on physical priors and the construction of the adjacency matrix are combined with the similarity between sensor signal nodes and the physical connection information of each component in the EHA system.

[0081] S41. Use the SimCLR architecture of contrastive learning to shorten the distance between positive samples and increase the distance between negative samples in the sliding window of the multivariate time series of sensor signals to generate enhanced data.

[0082] S42: Input the generated enhanced data into the feature extraction layer module for preliminary feature extraction.

[0083] S43. The extracted features are respectively input into the Transformer temporal feature extraction module and the GCN spatial feature extraction module based on physical prior.

[0084] S44. As the degradation stage changes, changes in sensor signal correlation significantly impact the GCN graph's ability to convey spatial information. By observing the sensor correlation CSI values, higher CSI values indicate that the connections between sensors increase the weight of the spatial module. This adaptive adjustment of the weights of the temporal and spatial modules yields a system lifespan prediction result.

[0085] S5, data division: divide the data collected in S2 into training set, validation set, and test set.

[0086] S6. Obtain the performance indicator results of the model prediction: adjust the model parameters, train and verify the extracted feature labels with the PreDyn-ST model, and perform time series prediction to obtain the performance indicator results of the model prediction and determine whether it is lower than the degraded label.

[0087] The SimCLR architecture of contrastive learning in S4 uses a time window input method, where the input data is a window; a window includes all sensor signals and a specified number of time steps. Contrastive learning can enhance each time series window sample x in the dataset twice using random transformations to generate two related time series windows. and Then, the encoder network f(·) is used to extract feature representations from the enhanced time series window and generate feature vectors and Finally, the feature vector is passed to the projection head g(·), g(·). Positive samples are the time steps corresponding to the two time windows; otherwise, they are negative samples.

[0088] In a second aspect, the present invention provides a system for predicting EHA performance degradation based on the PreDyn-ST model, which includes: a data acquisition module, a degradation label definition module, a model construction module, a data partitioning module, and a model verification and prediction module:

[0089] Data acquisition module: The sensors of the EHA test bench collect the piston rod displacement sensor signal, force sensor signal (used to display the load size), flow and pressure signals of the two chambers of the hydraulic servo cylinder, servo motor current signal and servo motor speed signal.

[0090] Degradation label definition module: organizes the signals collected in the EHA test bench and outputs them as system efficiency as degradation labels.

[0091] Model building module: builds the PreDyn-ST model.

[0092] Data partitioning module: divides the data in the collected EHA dataset into training set, validation set, and test set.

[0093] Model verification and prediction module: adjusts model parameters, trains and verifies the extracted feature labels with the PreDyn-ST model, and performs time series prediction to obtain performance indicator results of the model prediction.

[0094] Specifically, the data collection methods include:

[0095] The EHA performance degradation test bench is divided into two parts, namely the active part of the EHA drive and the load part. The active part includes a servo motor, a gear pump, a servo hydraulic cylinder and multiple data acquisition sensors.

[0096] The load part adopts a top-to-bottom cylinder structure, including a motor pump, a relief valve and multiple one-way valves. The working process of EHA is that the servo motor drives the high-speed gear pump to convert electrical energy into hydraulic energy. The pump pushes the hydraulic oil into the piston chamber of the hydraulic servo cylinder and generates thrust to drive the piston movement. Figure 2shown.

[0097] When the control system issues a command, the servo motor adjusts the pump's output flow and pressure according to the desired direction and speed of movement, thereby controlling the movement of the piston. A relief valve is used in the load section to regulate system pressure to achieve load control. Sensor signals are collected by a data acquisition card combined with the developed data acquisition software.

[0098] The experiment collected signals from eight sensors. Figure 8 The data collected in the previous ten days are shown, including the piston rod displacement sensor signal, the force sensor signal used to display the load size, the flow and pressure signals of the two chambers of the hydraulic servo cylinder, the servo motor current signal, and the servo motor speed signal.

[0099] During the test, a sinusoidal waveform was used for waveform control. The EHA operated at a reciprocating frequency of 1 Hz and a piston stroke of 30 cm. The data sampling frequency was 1000 Hz. The test was conducted for 3 hours per day for 84 days, comprehensively recording the performance of the equipment throughout its life cycle.

[0100] In step S3, the system efficiency is used as a degradation label, including:

[0101] Since system efficiency is an important indicator to measure the degree of system degradation, system efficiency is used as a degradation label. If the system efficiency is lower than a certain threshold, it indicates that the system is faulty.

[0102] The system efficiency was calculated from the raw data using a custom Python program. To match the training data, the average system efficiency was calculated every 10 cycles.

[0103] Furthermore, the method of constructing the PreDyn-ST model includes:

[0104] The PreDyn-ST model includes the SimCLR architecture for contrastive learning, a GCN spatial feature extraction module based on physical priors, and a Transformer temporal feature extraction module.

[0105] A physical prior-based GCN spatial feature extraction module is proposed, in which the construction of the adjacency matrix is not only based on the similarity between nodes (sensor signals), but also incorporates the physical connection information of each component in the EHA system.

[0106] The contrastive learning of the SimCLR model represents the loss of the entire sample by averaging the losses of all positive sample pairs in a batch.

[0107] The loss for a positive pair is defined as:

[0108]

[0109] Among them, sim(z i ,z j ) is z i and z j The cosine similarity between , defined as τ is a temperature parameter; 1 [k≠i] is an indicator function that takes 1 when k≠i and 0 otherwise; the denominator is summed over all 2N possible pairs in the batch, excluding positive sample pairs.

[0110] Among them, sim(z i ,z j ) is z i and z j The cosine similarity between , defined as τ is a temperature parameter; 1 [k≠i] is an indicator function that takes 1 when k≠i and 0 otherwise; the denominator is summed over all 2N possible pairs in the batch, excluding positive sample pairs.

[0111] The total loss is calculated by averaging the losses of all positive pairs in the batch:

[0112]

[0113] By minimizing this loss, the model can learn feature representations that are insensitive to the data augmentation process. This representation remains consistent under different data augmentation transformations (such as rotation, scaling, adding noise, etc.), thereby improving the robustness and generalization ability of the model and being able to more stably cope with diverse input data, such as Figure 3 shown.

[0114] The GCN spatial feature extraction module based on physical prior is mainly used to capture the spatial structural characteristics of the data, and adjust the influence of spatial characteristics in degradation prediction through a dynamic weight method, thereby improving the analysis accuracy of degradation data.

[0115] The GCN spatial feature extraction module based on physical priors includes the graph G = (V, ξ, A) formed by EHA data: V is the number of nodes, i.e., the number of sensors; ξ is the set of edges between each pair of connected nodes; is the adjacency matrix showing the spatial relationship between nodes; L = I n -D -1 / 2 AD -1 / 2 is the symmetric normalized graph Laplace matrix, and the diagonal matrix D is calculated based on the adjacency matrix, that is, is the eigenvalue of L.

[0116] (1) The convolution of vertex embedding and filter f is expressed as:

[0117] h=x* g f=U((U T x)⊙(U T f))

[0118] in, is the eigenvector matrix of the Laplace matrix, and ⊙ represents the Hadamard product.

[0119] (2) Diagonal matrix g θ , g θ For U T The diagonal matrix representation of f is:

[0120] Among them, diag is the operation of converting the vector into a diagonal matrix, θ i is each characteristic component after being projected into the frequency domain.

[0121] (3) The initial graph convolution formula can be obtained:

[0122] h=x* g f=Ug θ U T x.

[0123] (4) Use Chebyshev polynomials to simplify graph convolution calculations:

[0124]

[0125] in, and are the rescaled eigenvalues and Laplace matrices, respectively, is the Chebyshev coefficient, is a Chebyshev polynomial of order k, is an explicitly defined convolution kernel.

[0126] GCN is mainly used to capture the spatial structure characteristics of data and adjust the influence of spatial characteristics in degradation prediction through dynamic weighting method, thereby improving the analysis accuracy of degradation data, such as Figure 4 shown.

[0127] The Transformer temporal feature extraction module includes: (1) self-attention calculation mechanism, (2) multi-head attention function, and (3) formula for preserving the position information of the sequence.

[0128] Transformer is used to focus on the temporal characteristics of the data. In this process, multi-head attention and position encoding mechanisms are used simultaneously, and a dynamic weight method is used to adjust the impact of degradation temporal characteristics in degradation prediction.

[0129] (1) Self-attention calculation mechanism:

[0130]

[0131] Among them, Q, K, and V are query, key, and value matrices respectively. The similarity between each element in the sequence and other elements is calculated to determine its attention weight.

[0132] (2) The mathematical representation of the multi-head attention function is:

[0133] MultiHead(Q,K,V)=Concat(head1,head2,...,head h )W O

[0134] Among them, the calculation method of each attention head is:

[0135]

[0136] (3) The formula for retaining the position information of the sequence is:

[0137]

[0138] Among them, pos is the position index, i is the dimension index, d model The dimensions of the model.

[0139] Transformer is used to focus on the temporal characteristics of the data. In this process, multi-head attention and position encoding mechanisms are used simultaneously, and the dynamic weight method is used to adjust the impact of degradation time characteristics in degradation prediction, such as Figure 5 shown.

[0140] The constructed PreDyn-ST framework process is shown as follows: Figure 6 shown.

[0141] The constructed PreDyn-ST model is used to predict the actual RUL value at the failure point of four C-MAPSS test sets and the comparison results of the predicted RUL value show that the proposed model performs well on the four C-MAPSS test data sets and has good prediction effects, such as Figure 10 shown.

[0142] The constructed PreDyn-ST model has good fitting ability and can accurately predict the changes in EHA system efficiency within a day and in the long term, such as Figure 9 shown.

[0143] In this embodiment, the training, validation, and testing of the model include:

[0144] In the constructed PreDyn-ST model, for the pre-training model, set n_length to 50, n_h id to 512, projection_d im to 64, temperature to 0.5, num_levels to 2, lr to 1.5e-4, epochs to 200, and batch_size to 100.

[0145] The feature points processed by contrastive learning have a wider distribution range and a larger distance between feature points, which is conducive to distinguishing between feature points. Figure 8 shown.

[0146] After the contrast learning preprocessing, the training and validation loss curves of the data drop rapidly, and only a small number of epochs need to be trained to converge quickly, such as Figure 11 shown.

[0147] For the overall CSI curve of the C-MAPSS training data set, such as Figure 12 shown.

[0148] After visualizing the CSI value, the proportion of the time module and the space module is adaptively adjusted, such as Figure 13 shown.

[0149] For the prediction task, set nfeat to 16, nh id to 128, GCN num_levels to 2, num_node to 14, Transformer num_levels to 2, idden_d im to 8, num_windows to 5, window_sample to 50, batch_size to 200, epochs to 100, and lr to 1.5e-4;

[0150] In this example, to verify the superiority of the combination, different model variants were evaluated. The experiments were divided into the following configurations: GCN model, Transformer model, pre-trained GCN model, pre-trained Transformer model, dynamic weight GCN-Transformer temporal feature extraction module, and the proposed pre-trained dynamic weight GCN-Transformer temporal feature extraction module (PreDyn-ST). The results are shown in Table 1.

[0151] Table 1

[0152]

[0153] The results show that both pre-training and dynamic weights improve the performance of the model, and the proposed PreDyn-ST method has the best prediction effect.

[0154] The embodiments described above are merely descriptions of preferred implementations of the present invention and are not intended to limit the scope of the present invention. Without departing from the spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should fall within the scope of protection determined by the claims of the present invention.

Claims

1. A method for predicting EHA performance degradation based on the PreDyn-ST model, characterized in that: It includes the following steps: S1. Build an EHA test bench. The EHA test bench includes the active part and the load part of the EHA drive. The active part includes a servo motor, a gear pump, a servo hydraulic cylinder, and multiple data acquisition sensors. The load part adopts a top-to-top cylinder structure, and includes a motor pump, a relief valve and multiple one-way valves; S2. Signal acquisition: The data acquisition sensor collects the piston rod displacement sensor signal, force sensor signal, flow and pressure signals of the two chambers of the hydraulic servo cylinder, servo motor current signal, and servo motor speed signal; S3. Establishing a component function signal set with degradation labels: Obtaining system efficiency based on sensor signal data, using the system efficiency as a degradation label, and establishing a component function signal set with degradation labels; S4. Build the PreDyn-ST model: This model is constructed using the SimCLR architecture for contrastive learning, the GCN spatial feature extraction module based on physical priors, and the Transformer temporal feature extraction module. The output of the PreDyn-ST model is used as the system life prediction result. This model includes the following sub-steps: S41. Use the SimCLR architecture of contrastive learning to shorten the distance between positive samples and increase the distance between negative samples in the sliding window of the multivariate time series of sensor signal data to generate enhanced data. S42, inputting the enhanced data into a feature extraction module to perform preliminary feature extraction; S43, the extracted features are input into the Transformer temporal feature extraction module and the GCN spatial feature extraction module based on physical prior respectively; S44. As the degradation stage changes, the PreDyn-ST model adaptively adjusts the weights of the Transformer temporal feature extraction module and the physical prior-based GCN spatial feature extraction module and outputs the system life prediction results. By observing the sensor correlation CSI value, an increase in the CSI value indicates that the connection between sensors will increase the weight of the spatial module. S5, PreDyn-ST model training: After dividing the component functional signal set with degradation labels in S3 into a training set, a validation set, and a test set, the PreDyn-ST model is trained and validated, and the model parameters are adjusted to obtain the trained PreDyn-ST model; S6. Obtain the life prediction result predicted by the model: The multivariate time series sequence of sensor signal data is collected in real time and input into the PreDyn-ST model trained in S5, and the predicted system life prediction result is output. It is judged whether the system life prediction result is lower than the set threshold, and the performance degradation state of the EHA is determined based on the judgment result.

2. The EHA performance degradation prediction method based on the PreDyn-ST model according to claim 1, characterized in that: In step S4, the SimCLR architecture represents the loss of the entire sample by averaging the losses of all positive sample pairs; The loss for a positive pair is defined as: Among them, sim(z i ,z j ) is z i and z j The cosine similarity between , defined as τ is a temperature parameter; Z is the eigenvector of the positive sample pair; i, j and k are all parameters; 1 [k≠i] is an indicator function that takes 1 when k≠i and 0 otherwise; the denominator is summed over all 2N possible pairs in the batch, excluding positive sample pairs; The total loss is calculated by averaging the losses of all positive pairs in the batch:

3. The EHA performance degradation prediction method based on the PreDyn-ST model according to claim 1, characterized in that: In step S4, the graph G=(V,ξ,A) formed by the EHA data in the physical prior-based GCN spatial feature extraction module is: V is the number of nodes, that is, the number of sensors; ξ is the edge set between each pair of connected nodes; is the adjacency matrix showing the spatial relationship between nodes; L = I n -D -1 / 2 AD -1 / 2 is the symmetric normalized graph Laplace matrix, and the diagonal matrix D is calculated based on the adjacency matrix, that is, is the eigenvalue of L; The convolution of vertex embedding and filter f is expressed as: h=x* g f=U((U T x)⊙(U T f)) in, is the eigenvector matrix of the Laplace matrix, ⊙ represents the Hadamard product; Diagonal matrix g θ , g θ For U T The diagonal matrix representation of f is: g θ =diag(U T f)=diag(θ0,θ1,...,θ n-1 ) Among them, diag is the operation of converting the vector into a diagonal matrix, θ i is each characteristic component after projection into the frequency domain; The initial graph convolution formula can be obtained: h=x* g f=Ug θ U T x; Simplify graph convolution calculation using Chebyshev polynomials: in, and are the rescaled eigenvalues and Laplace matrices, respectively, is the Chebyshev coefficient, is a Chebyshev polynomial of order k, is an explicitly defined convolution kernel.

4. The EHA performance degradation prediction method based on the PreDyn-ST model according to claim 1, characterized in that: In step S4, in the Transformer temporal feature extraction module: The self-attention calculation mechanism is expressed as: Among them, Q, K, and V are query, key, and value matrices respectively. Then calculate the similarity between each element in the sequence and other elements to determine its attention weight; The multi-head attention function is expressed as: MultiHead(Q,K,V)=Concat(head1,head2,...,head h )W O head i is each attention head in the multi-head attention, where i = 1, 2, 3...h, W o is the output linear transformation matrix; Among them, the calculation method of each attention head is: head i =Attention(QW i Q ,KW i K ,VW i V ); The formula for preserving the position information of the sequence is: Among them, pos is the position index, i is the dimension index, d model The dimensions of the model.

5. A system for the EHA performance degradation prediction method based on the PreDyn-ST model according to any one of claims 1 to 4, characterized in that: It includes data acquisition module, degradation label definition module, model construction module, data partitioning module and model verification and prediction module: Data acquisition module: collects piston rod displacement sensor signals, force sensor signals used to display load size, flow and pressure signals of the two chambers of the hydraulic servo cylinder, servo motor current signals, and servo motor speed signals through sensors on the EHA test bench; Degradation label definition module: organizes the signals collected in the EHA test bench and outputs them as system efficiency as degradation labels; Model building module: build PreDyn-ST model; Data partitioning module: divides the data in the collected EHA dataset into training set, validation set and test set; Model verification and prediction module: adjusts model parameters, trains and verifies the extracted feature labels with the PreDyn-ST model, and performs time series prediction to obtain performance indicator results of the model prediction.

Images