Deep learning-based aero-engine residual life prediction method and system

Abstract

The invention provides an aero-engine residual life prediction method and system based on deep learning, and relates to the technical field of engine life prediction. According to the method, a multi-scale convolution feature extraction module (SDMCN module) based on a graph attention mechanism and a GRU module (F-GRU module) fused with the feature attention mechanism are established. Through an SDMCN module, the spatial relevance of the features is fully extracted from the two aspects of the relevance between the feature maps formed under the convolution kernels of the same size and the relevance between the feature maps formed under the convolution kernels of different sizes. And meanwhile, the F-GRU module is used for dynamically adjusting the weights of the input characteristics under different time steps, so that differential updating of the sequence data is realized. By adopting the two parallel branches, extraction of spatial relevance and time sequence dependency relationship between features is realized, so that feature degradation information is captured more comprehensively, a more accurate life degradation model is established, and the accuracy of model prediction is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of engine remaining life prediction, and in particular to a method and system for predicting the remaining life of an aircraft engine based on deep learning. Background Art

[0002] As one of the most important parts of an aircraft, the engine has complex operating conditions and failures are inevitable during long-term operation. Real-time evaluation of the engine's health status and accurate prediction of its remaining useful life (RUL) can effectively reduce unplanned downtime and unnecessary or excessive maintenance operations, and provide a reference for the formulation of subsequent maintenance strategies.

[0003] The performance and service life of aircraft engines are affected by many factors such as flight conditions, operating environment and internal structure. The remaining service life prediction of an engine is to process and analyze the relevant sensor data obtained, and then combine relevant models or machine learning methods to build a mapping model between the operating status data and the remaining service life, so as to predict the service time of the machine from the current operation to the end of its service life. At present, the commonly used methods are mainly divided into two categories: physical model-based methods and data-driven methods. The former mainly establishes a physical model based on the operating mechanism of the equipment to characterize the degradation process, but it is overly dependent on historical monitoring data, and for complex systems, insufficient professional knowledge and interference from uncertain factors will limit the integrity and accuracy of the constructed model. The data-driven method is independent of physical principles. It uses statistical methods or machine learning related algorithms to make direct predictions based on the obtained sensor data. In recent years, with the development of sensor technology, a large amount of degradation data needs to be processed in the life prediction of aircraft engines. Deep learning methods have been widely used due to their excellent data processing and learning capabilities. At present, the relevant methods based on deep learning mainly use network structures such as CNN and LSTM to extract feature degradation information from a large amount of sensor data, capture the complex nonlinear relationship between sensor signal characteristics and remaining life, and thus realize the remaining life prediction of aircraft engines.

[0004] However, existing methods based on deep learning models usually use channel attention mechanisms or spatial attention mechanisms to strengthen the key feature information in different feature maps after convolution and pooling operations, and then use simple splicing or addition operations to fuse features. However, these attention mechanisms are often limited to a single convolution kernel, thus ignoring the influence of the weight matrix in the convolution operation and the correlation between feature maps formed under convolution kernels of different scales. In addition, in terms of capturing temporal features, the feature extraction process of existing methods at different time steps is the same, while ignoring the differences between different features at different time steps. When the spatial correlation and temporal dependency between features are not fully extracted, the prediction effect of the model will be affected to a certain extent. Summary of the invention

[0005] 1. Technical issues to be solved

[0006] In view of the shortcomings of the prior art, the present invention provides a method and system for predicting the remaining life of an aircraft engine based on deep learning, which solves the technical problem that related methods based on deep learning models fail to adequately capture the spatial correlation and temporal dependency of features.

[0007] (II) Technical solution

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0009] In a first aspect, the present invention provides a method for predicting the remaining life of an aircraft engine based on deep learning, comprising:

[0010] Obtain historical engine operation data and in-service engine monitoring data, and perform preprocessing to obtain a data set;

[0011] The data set is labeled according to the operating characteristics of aircraft engines, and the data in the data set is divided into normal operation stage data and life degradation stage data;

[0012] The sliding window method is used to segment the data of adjacent time periods of each engine unit to construct a training sample data set;

[0013] Training a pre-built neural network using a training sample data set to obtain an aircraft engine remaining life prediction model, wherein the aircraft engine remaining life prediction model is used to predict the life of the aircraft engine;

[0014] Among them, the pre-constructed neural network includes a multi-scale convolutional feature extraction module based on a graph attention mechanism, a GRU module fused with a feature attention mechanism, and a RUL prediction module; the multi-scale convolutional feature extraction module based on a graph attention mechanism and the GRU module fused with a feature attention mechanism are operated in parallel, and the outputs of both are input into the RUL prediction module; the multi-scale convolutional feature extraction module based on a graph attention mechanism captures multi-level degradation features through several parallel convolution blocks of different sizes, and uses a graph attention mechanism to regard different filters as nodes, construct multiple different graph structures, and weight each feature graph according to the correlation between different feature graphs; the GRU module fused with a feature attention mechanism dynamically adjusts the weights of input features at different time steps to achieve differential updates of sequence data.

[0015] Preferably, the preprocessing includes feature selection and standardization;

[0016] in,

[0017] The feature selection includes: combining a correlation analysis method to perform feature selection on multidimensional variables to obtain variables related to the remaining life of the aircraft engine; the multidimensional variables include relevant sensor data and operating condition parameters;

[0018] The standardization process includes a normalization process.

[0019] Preferably, labeling the data set according to the operating characteristics of the aircraft engine, dividing the data in the data set into normal operating stage data and life degradation stage data, includes:

[0020] The operation phases of aircraft engines are divided by piecewise linear function method. According to its own operation characteristics, the operation cycle of aircraft engines is divided into two phases: normal operation phase and life degradation phase. It is assumed that the engine has a constant RUL value in the normal operation phase:

[0021]

[0022] Among them, y label Indicates the label of the constructed sample data, y label =R early Indicates the normal operation stage, y label = RUL represents the life degradation stage, RUL represents the actual remaining service life of the aircraft engine, R early Indicates the set engine life threshold;

[0023] According to the division standard, the data in the data set are processed and divided into normal operation stage data and life degradation stage data.

[0024] Preferably, the multi-scale convolutional feature extraction module based on the graph attention mechanism includes three parallel convolutional blocks of different sizes and a graph attention mechanism;

[0025] Among them, three parallel convolution blocks of different sizes capture multi-level degraded features, and use the graph attention mechanism to treat the convolution kernels in different convolution blocks as nodes to build multiple different graph structures. According to the correlation between different feature maps, each feature map is weighted;

[0026] Among them, the expression of CNN feature extraction is as follows:

[0027]

[0028] in, and is the weight matrix and bias matrix under the i-th convolution kernel, represents the feature map formed after the convolution operation, and σ(·) represents the activation function;

[0029] The weighting process of the graph attention mechanism is as follows:

[0030]

[0031] Among them, i and j represent nodes in the graph structure, and The feature vector representation of nodes i and j, e ij represents the attention coefficient of node i to node j, represents all adjacent nodes of node i, || represents vector concatenation;

[0032] After obtaining the attention scores of all nodes, the softmax function is used to normalize them, obtain the weights of different nodes, and assign weights to them.

[0033] Preferably, the GRU module integrating the feature attention mechanism is a double-layer GRU network structure, and the feature attention mechanism is introduced after the first GRU, and the feature attention mechanism is combined with the hidden state h of the previous moment in the GRU. t-1 The historical running data retained in the , weights the different input features at the next moment according to their importance, and uses the weighted input variables as the input of the next layer of GRU; the operation process of GRU is as follows:

[0034] r t =σ(W r ·[h t-1 ,x t ]+b r )

[0035]

[0036] z t =σ(W z ·[h t-1 ,x t ]+b z )

[0037]

[0038] Among them, r t represents the output of the reset gate, z t represents the output of the update gate, σ(·) represents the activation function; W r , W h and W z represents the weight matrix; b r 、b h and b z represents the bias matrix; h t Represents the information of the hidden state passed to the next moment.

[0039] Preferably, the RUL prediction module includes a concatenation layer and a fully connected layer, and the two vector matrices are concatenated by the concat function in the concatenation layer.

[0040] In the RUL prediction module, after obtaining the outputs of the SDMCN module and the F-GRU module, the output vectors of the multi-scale convolutional feature extraction module based on the graph attention mechanism and the GRU module with fusion feature attention mechanism are concatenated in matrices through the concat function, and the concatenated vectors are input into the fully connected layer to obtain the engine remaining life prediction result.

[0041] In a second aspect, the present invention provides an aircraft engine remaining life prediction system based on deep learning, comprising:

[0042] A data acquisition module is used to acquire historical engine operation data and in-service engine monitoring data, and perform preprocessing to obtain a data set;

[0043] The data partitioning module is used to label the data set according to the operating characteristics of the aircraft engine, and divide the data in the data set into normal operation stage data and life degradation stage data;

[0044] A training sample construction module is used to segment the data of adjacent time periods of each engine unit using a sliding window method to construct a training sample data set;

[0045] A model training module is used to train a pre-built neural network using a training sample data set to obtain an aircraft engine remaining life prediction model, wherein the aircraft engine remaining life prediction model is used to predict the life of the aircraft engine;

[0046] Among them, the pre-constructed neural network includes a multi-scale convolutional feature extraction module based on a graph attention mechanism, a GRU module fused with a feature attention mechanism, and a RUL prediction module; the multi-scale convolutional feature extraction module based on a graph attention mechanism and the GRU module fused with a feature attention mechanism are operated in parallel, and the outputs of both are input into the RUL prediction module; the multi-scale convolutional feature extraction module based on a graph attention mechanism captures multi-level degradation features through several parallel convolution blocks of different sizes, and uses a graph attention mechanism to regard different filters as nodes, construct multiple different graph structures, and weight each feature graph according to the correlation between different feature graphs; the GRU module fused with a feature attention mechanism dynamically adjusts the weights of input features at different time steps to achieve differential updates of sequence data.

[0047] Preferably, labeling the data set according to the operating characteristics of the aircraft engine, dividing the data in the data set into normal operating stage data and life degradation stage data, includes:

[0048] The operation phases of aircraft engines are divided by piecewise linear function method. According to its own operation characteristics, the operation cycle of aircraft engines is divided into two phases: normal operation phase and life degradation phase. It is assumed that the engine has a constant RUL value in the normal operation phase:

[0049]

[0050] Among them, y label Indicates the label of the constructed sample data, y label =R early Indicates the normal operation stage, y label = RUL represents the life degradation stage, RUL represents the actual remaining service life of the aircraft engine, R early Indicates the set engine life threshold;

[0051] According to the division standard, the data in the data set are processed and divided into normal operation stage data and life degradation stage data.

[0052] In a third aspect, the present invention provides a computer-readable storage medium storing a computer program for predicting the remaining life of an aircraft engine based on deep learning, wherein the computer program enables a computer to execute the method for predicting the remaining life of an aircraft engine based on deep learning as described above.

[0053] In a fourth aspect, the present invention provides an electronic device, comprising:

[0054] One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the programs include methods for executing the deep learning-based aircraft engine remaining life prediction method as described above.

[0055] (III) Beneficial effects

[0056] The present invention provides a method and system for predicting the remaining life of an aircraft engine based on deep learning. Compared with the prior art, it has the following beneficial effects:

[0057] In view of the problem that the spatial correlation between features in the existing methods is not sufficiently extracted, the present invention establishes a multi-scale convolution feature extraction module based on the graph attention mechanism and a GRU module that integrates the feature attention mechanism. Through the multi-scale feature extraction module, the spatial correlation of features is fully extracted from two angles: the correlation between feature graphs formed under the same size convolution kernel (internal similarity) and the correlation between feature graphs formed under different size convolution kernels (external similarity). At the same time, the F-GRU module is used to dynamically adjust the weights of input features at different time steps to achieve differential updates of sequence data. These two parallel branches are used to realize the extraction of spatial correlation and temporal dependency between features, thereby more comprehensively capturing feature degradation information, establishing a more accurate life degradation model, and improving the accuracy of model prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] 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 some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0059] Figure 1 The block diagram of the remaining life prediction method of aircraft engines based on deep learning;

[0060] Figure 2 This is a specific flow chart of the remaining life prediction method of aircraft engines based on deep learning;

[0061] Figure 3 A schematic diagram of a segmentation process for segmenting data of adjacent time periods of each engine unit using a sliding window method;

[0062] Figure 4 This is a schematic diagram of the structure of the aircraft engine remaining life prediction model;

[0063] Figure 5This is a schematic diagram of the structure of the multi-scale convolutional feature extraction module based on the graph attention mechanism;

[0064] Figure 6 This is a schematic diagram of the structure of the GRU module that integrates the feature attention mechanism;

[0065] Figure 7a to Figure 7d These are all comparison charts of prediction effects. Figure 7a The predicted and true values ​​of the engine unit #76 on the four data subsets are: Figure 7b The predicted and true values ​​of the engine unit #64 on the four data subsets are: Figure 7c The predicted and true values ​​of the engine unit #99 on the four data subsets are: Figure 7d These are the predicted and true values ​​for the engine unit #47 on the four data subsets. DETAILED DESCRIPTION

[0066] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are clearly and completely described. Obviously, the described embodiments are 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.

[0067] The embodiment of the present application provides a method and system for predicting the remaining life of an aircraft engine based on deep learning, which solves the technical problem of insufficient capture of the spatial correlation between different feature graphs and the temporal dependency of input features in related methods based on deep learning models. The system simultaneously pays attention to the correlation between feature graphs formed under convolution kernels of the same size and feature graphs formed under convolution kernels of different sizes, as well as the dynamic update of input feature weights at different time steps. It captures feature degradation information more comprehensively from the perspectives of time and space, and achieves more accurate life prediction.

[0068] The technical solution in the embodiment of the present application is to solve the above technical problems, and the overall idea is as follows:

[0069] Existing deep learning-based methods mainly use network structures such as CNN, LSTM, and CNN-BiGRU to extract feature degradation information from a large amount of sensor data and capture the complex nonlinear relationship between sensor signal characteristics and remaining life, thereby realizing the remaining life prediction of aircraft engines. However, the existing technology has the following defects:

[0070] (1) When using CNN networks for feature extraction, a single-scale convolution kernel is often unable to fully obtain feature information. In addition, after performing convolution and pooling operations, existing model methods usually use channel attention mechanisms or spatial attention mechanisms to strengthen the key feature information in different feature maps, and then use simple splicing or addition operations to perform feature fusion. However, these attention mechanisms are limited to a single convolution kernel, thus ignoring the influence of the weight matrix in the convolution operation and the correlation between features of different scales. When the spatial correlation between features is not fully extracted, the prediction effect of the model will be affected to a certain extent.

[0071] (2) Traditional methods focus on the temporal dependency of sensor data when using the Gated Recurrent Unit (GRU) model to learn time series data, that is, different weights are assigned to features at different time steps to highlight the importance of data at different time steps in the RUL prediction process. The feature update process of GRU is indifferent across the entire data sequence, that is, all features at each time step are processed in the same way. However, in actual situations, different feature vectors in each time step play different roles in the RUL prediction process, especially in the critical stage of engine life degradation. Therefore, if all features at different time periods are processed in the same way, it will affect the capture of key feature degradation information, thereby affecting the accuracy of model prediction.

[0072] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0073] The present invention provides a method for predicting the remaining life of an aircraft engine based on deep learning. Figure 1 As shown, the method includes:

[0074] S1. Obtain historical engine operation data and in-service engine monitoring data, and perform preprocessing to obtain a data set;

[0075] S2. Label the data set according to the operating characteristics of the aircraft engine, and divide the data in the data set into normal operation stage data and life degradation stage data;

[0076] S3, using a sliding window method to segment the data of adjacent time periods of each engine unit to construct a training sample data set;

[0077] S4, training a pre-built neural network using a training sample data set to obtain an aircraft engine remaining life prediction model, and predicting the aircraft engine using the aircraft engine remaining life prediction model to obtain a prediction result;

[0078] The pre-built neural network includes a multi-scale convolution feature extraction module based on the graph attention mechanism, a GRU module fused with the feature attention mechanism, and a RUL prediction module. The multi-scale convolution feature extraction module based on the graph attention mechanism and the GRU module fused with the feature attention mechanism are in parallel, and the outputs of both are input into the RUL prediction module; the multi-scale convolution feature extraction module based on the graph attention mechanism captures multi-level degradation features through several parallel convolution blocks of different sizes, and uses the graph attention mechanism to treat different filters as nodes, construct multiple different graph structures, and weight each feature graph according to the correlation between different feature graphs; the GRU module fused with the feature attention mechanism dynamically adjusts the weights of the input features at different time steps to achieve differential updates of sequence data.

[0079] The embodiment of the present invention firstly addresses the problem of insufficient extraction of spatial correlation between features in existing methods, and establishes a multi-scale convolution feature extraction module based on the graph attention mechanism, which fully extracts the spatial correlation of features from two perspectives: the correlation between feature graphs formed under the same size convolution kernel (internal similarity) and the correlation between feature graphs formed under different size convolution kernels (external similarity). Secondly, in order to address the shortcomings of existing methods in capturing temporal dependencies of features, the feature attention mechanism is integrated with GRU to achieve differentiated updates of input features at different time steps. Through two parallel branches, feature degradation information is captured more comprehensively, thereby improving the accuracy of prediction of the aircraft engine remaining life prediction model.

[0080] The following is combined with Figure 2 The flowchart shown describes the individual steps in detail:

[0081] In step S1, historical engine operation data and in-service engine monitoring data are obtained and preprocessed to obtain a data set. The specific implementation process is as follows:

[0082] Historical engine operation data and in-service engine monitoring data include relevant sensor data and operating parameters. Preprocessing mainly includes feature selection and standardization. Specifically, it includes:

[0083] Combined with the correlation analysis method, feature selection is performed on the obtained relevant sensor data and multi-dimensional variables such as operating parameters to obtain variables related to the remaining life of aircraft engines. Variables related to the remaining life of aircraft engines include operating parameters of engine operation, high and low pressure compressor temperature parameters, fan speed, etc. The "minimum-maximum" normalization method is used to standardize the selected variables, and the formula is as follows:

[0084]

[0085] Among them, xi For each sensor value, X max and X min are the maximum and minimum values ​​in each column of sensor variables, respectively, i ' is the corresponding normalized variable value.

[0086] The standardized variables related to the remaining life of aircraft engines form a data set, which includes a training set and a test set. The training set is obtained after preprocessing the historical engine operation data. The test set is obtained after preprocessing the in-service engine monitoring data. The training set is used for model training and parameter adjustment, and the test set is used to verify the effectiveness of the trained model.

[0087] In step S2, the data set is labeled according to the operating characteristics of the aircraft engine, and the data in the data set is divided into normal operation stage data and life degradation stage data. The specific implementation process is as follows:

[0088] The operation phases of aircraft engines are divided by piecewise linear function method. According to its own operation characteristics, the operation cycle of aircraft engines is divided into two phases: normal operation phase and life degradation phase. It is assumed that the engine has a constant RUL value in the normal operation phase:

[0089]

[0090] Among them, y label represents the label of the constructed sample data, RUL represents the actual remaining useful life of the aircraft engine, and R early Indicates the set engine life threshold.

[0091] According to this classification standard, the data in the data set are processed and divided into normal operation stage data and life degradation stage data.

[0092] The purpose of dividing the data in the dataset into normal operation stage data and life degradation stage data is to better perform prediction processing. If the data is not divided, it is equivalent to accurately predicting the data at each moment. After the division, the predicted label is equivalent to a piecewise linear degradation.

[0093] In step S3, the sliding window method is used to segment the data of adjacent time periods of each engine unit to construct a training sample data set. The specific implementation process is as follows:

[0094] Specific segmentation methods include Figure 3As shown, the time series features between single independent data are not obvious, so here the data of each engine is processed by sliding window, and the data in a certain interval is packaged as one data, the sliding step is 1, W represents the sliding window size, and the segmented data is used as the training sample data set.

[0095] In step S4, the pre-built neural network is trained by the training sample data set to obtain an aircraft engine remaining life prediction model, and the aircraft engine remaining life prediction model is used to predict the life of the aircraft engine. The specific implementation process is as follows:

[0096] The structure of the pre-built neural network in the embodiment of the present invention (the structure of the trained aircraft engine remaining life prediction model is consistent with it, at least the parameters of the model are different) is as follows: Figure 4 As shown in Figure 1, it includes two parallel multi-scale convolutional feature extraction modules based on graph attention mechanism (SDMCN modules), a GRU module fused with feature attention mechanism (F-GRU module) and a RUL prediction module. Figure 5 As shown, the GRU module integrating the feature attention mechanism is as follows Figure 6 As shown in the figure, the SDMCN module and the F-GRU module are run in parallel, and the outputs of both are input into the RUL prediction module.

[0097] like Figure 5 As shown, the multi-scale convolution feature extraction module based on the graph attention mechanism captures multi-level degradation features through several (three are selected in the embodiment of the present invention) parallel convolution blocks of different sizes, and uses the graph attention mechanism to regard different filters as nodes (i.e., feature maps formed by feature convolution operations with different weights under different convolution kernels and the same convolution kernel), construct multiple different graph structures, and weight each feature map according to the correlation between different feature maps. Among them, the expression of CNN feature extraction is as follows:

[0098]

[0099] in, and is the weight matrix and bias matrix under the i-th convolution kernel, represents the feature map formed after the convolution operation, and σ(·) represents the activation function.

[0100] The weighting process of GAT (graph attention mechanism) is as follows

[0101]

[0102] Among them, i and j represent nodes in the graph structure (each convolution kernel is regarded as a node in the graph structure), and The feature vector representation of nodes i and j, e ij represents the attention coefficient of node i to node j, Represents all the adjacent nodes of node i. || represents vector concatenation. After obtaining the attention scores of all nodes, the softmax function is used to normalize them, obtain the weights of different nodes, and assign weights to them.

[0103] like Figure 6 As shown in the figure, the GRU module integrating the feature attention mechanism is a two-layer GRU network structure. The feature attention mechanism is introduced after the first GRU. With the help of the feature attention mechanism, the hidden state h of the previous moment in the GRU is combined. t-1 The retained historical running data is used to weight different input features at the next moment according to their importance, and then the weighted input variables are used as the input of the next layer of GRU. The operation process of GRU is as follows:

[0104] r t =σ(W r ·[h t-1 ,x t ]+b r )

[0105]

[0106] z t =σ(W z ·[h t-1 ,x t ]+b z )

[0107]

[0108] Among them, r t represents the output of the reset gate, z t represents the output of the update gate, σ(·) represents the activation function; W r , W h and W z represents the weight matrix; b r 、b h and b z represents the bias matrix; h t Represents the information of the hidden state passed to the next moment.

[0109] In the RUL prediction module, after obtaining the outputs of the SDMCN module and the F-GRU module, the two vector matrices are concatenated through the concat function. Then they are input into the fully connected layer to obtain the engine remaining life prediction result RUL pre .

[0110] out con =[out conv ,out gru ]

[0111] RUL pre =LeakyReLU(W out con +b)

[0112] The model is trained using the training set, and the grid search method is used to optimize the parameters to determine the best parameter set. The effectiveness of the trained model is verified through the test set to train the remaining life prediction model of aircraft engines.

[0113] The effectiveness of the embodiment of the present invention is verified by simulation experiments below:

[0114] The dataset C-MAPSS selected in this simulation experiment is developed by NASA using commercial modular simulation software in the MATLAB environment. It simulates the entire degradation process data of a turbofan engine from operation to failure. It consists of four data subsets FD001-FD004, each with 26 columns of data (engine ID, current number of operating cycles, 3 operating settings, and 21 columns of sensor signal monitoring data).

[0115] Step 1: Draw the curves of each variable in the training set changing with the service life of the aircraft engine and combine correlation analysis and other methods to select 17 columns of variable data as the input of the model (operating condition 1, operating condition 2, sensor 2, 3, 4, 6, 7, 8, 9, 11, 12, 13, 14, 15, 17, 20, 21). Then use the "min-max" normalization method to normalize each column of variables.

[0116] Step 2: Segment the life prediction labels in the training set and the test set. early =120.

[0117] Step 3: Analyze the training sets in the four data subsets in C-MAPSS respectively, and select the appropriate time window size W for the training set according to the minimum number of cycles in the corresponding test set. 1 , W 2 , W 3 , W 4 , the step size is set to 1, and N×W i The sample input of (i=1,2,3,4) has the corresponding predicted label y t+W-1 The test set is processed in the same way, but unlike the training set, the test sample only uses the last sliding window data of each engine unit.

[0118] X t=[x 1 ,x 2 ,......,x N ]

[0119]

[0120] Among them, X t and X t' They represent the original input data and the preprocessed input data sequence at the tth time step, N represents the feature dimension, and T represents the length of the time window.

[0121] Step 4: Select RMSE and Score as the evaluation indicators of the model prediction effect. RMSE is used to measure the gap between the model prediction value and the true value, and Score reflects the penalty value of the model for different prediction situations (advance prediction or delayed prediction). The principle is as follows:

[0122]

[0123] Where N is the total number of samples, is the predicted value of engine life, is the actual value of engine life, d i Represents the difference between the predicted value and the true value.

[0124] Step 5: Use the training data processed in step 3 as the input data of the model. Select three different convolution kernel sizes (3, 5, 7) to build the remaining life prediction model and optimize the parameters. This verification process determines the optimal parameter set based on four different data subsets and performs fine-tuning. Some hyperparameter values ​​are shown in Table 1:

[0125] Table 1 Some hyperparameter values

[0126]

[0127] Step 6: Put the four test subsets into the model trained in step 5 for verification, and obtain the model's predicted value of the remaining service life of each engine after random stop, and compare it with the true label. After multiple independent repeated experiments, obtain the RMSE and Score mean on the four test sets and compare them with the prediction effect of the SOTA method to analyze the effectiveness of the method proposed in the present invention.

[0128] Step 7: In order to more intuitively demonstrate the prediction effect of the model, a comparison chart of the predicted values ​​and the actual values ​​of the engine units #76, #64, #99 and #47 on the four data subsets is drawn for visual analysis, as shown in the figure below: Figure 7a to Figure 7d shown.

[0129] The embodiment of the present invention further provides an aircraft engine remaining life prediction system based on deep learning, comprising:

[0130] A data acquisition module is used to acquire historical engine operation data and in-service engine monitoring data, and perform preprocessing to obtain a data set;

[0131] The data partitioning module is used to label the data set according to the operating characteristics of the aircraft engine, and divide the data in the data set into normal operation stage data and life degradation stage data;

[0132] A training sample construction module is used to segment the data of adjacent time periods of each engine unit using a sliding window method to construct a training sample data set;

[0133] A model training module is used to train a pre-built neural network using a training sample data set to obtain an aircraft engine remaining life prediction model, wherein the aircraft engine remaining life prediction model is used to predict the life of the aircraft engine;

[0134] The pre-built neural network includes a multi-scale convolution feature extraction module based on the graph attention mechanism, a GRU module fused with the feature attention mechanism, and a RUL prediction module. The multi-scale convolution feature extraction module based on the graph attention mechanism and the GRU module fused with the feature attention mechanism are in parallel, and the outputs of both are input into the RUL prediction module; the multi-scale convolution feature extraction module based on the graph attention mechanism captures multi-level degradation features through several parallel convolution blocks of different sizes, and uses the graph attention mechanism to treat different filters as nodes, construct multiple different graph structures, and weight each feature graph according to the correlation between different feature graphs; the GRU module fused with the feature attention mechanism dynamically adjusts the weights of the input features at different time steps to achieve differential updates of sequence data.

[0135] It can be understood that the data center energy system security risk assessment system provided by the embodiment of the present invention corresponds to the above-mentioned data center energy system security risk assessment method. The explanations, examples, beneficial effects and other parts of its relevant contents can refer to the corresponding contents in the data center energy system security risk assessment method and will not be repeated here.

[0136] An embodiment of the present invention also provides a computer-readable storage medium storing a computer program for data center energy system security risk assessment, wherein the computer program enables a computer to execute the data center energy system security risk assessment method as described above.

[0137] An embodiment of the present invention also provides an electronic device, comprising: one or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the programs include a method for executing the data center energy system security risk assessment method as described above.

[0138] In summary, compared with the prior art, the present invention has the following beneficial effects:

[0139] In order to solve the problem of insufficient extraction of spatial correlation between features in existing methods, the embodiments of the present invention establish a multi-scale convolution feature extraction module based on a graph attention mechanism and a GRU module fused with a feature attention mechanism. Through the multi-scale feature extraction module, the spatial correlation of features is fully extracted from two perspectives: the correlation between feature graphs formed under convolution kernels of the same size (internal similarity) and the correlation between feature graphs formed under convolution kernels of different sizes (external similarity). At the same time, the GRU module fused with the feature attention mechanism is used to dynamically adjust the weights of input features at different time steps to achieve differential updates of sequence data. These two parallel branches are used to realize the extraction of spatial correlation and temporal dependency between features, thereby more comprehensively capturing feature degradation information, establishing a more accurate life degradation model, and improving the accuracy of model prediction.

[0140] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0141] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting the remaining life of an aircraft engine based on deep learning, characterized in that: include: Obtain historical engine operation data and in-service engine monitoring data, and perform preprocessing to obtain a data set; The data set is labeled according to the operating characteristics of aircraft engines, and the data in the data set is divided into normal operation stage data and life degradation stage data; The sliding window method is used to segment the data of adjacent time periods of each engine unit to construct a training sample data set; Training a pre-built neural network using a training sample data set to obtain an aircraft engine remaining life prediction model, wherein the aircraft engine remaining life prediction model is used to predict the life of the aircraft engine; Among them, the pre-constructed neural network includes a multi-scale convolutional feature extraction module based on a graph attention mechanism, a GRU module fused with a feature attention mechanism, and a RUL prediction module. The multi-scale convolutional feature extraction module based on a graph attention mechanism and the GRU module fused with a feature attention mechanism are operated in parallel, and the outputs of both are input into the RUL prediction module; the multi-scale convolutional feature extraction module based on the graph attention mechanism captures multi-level degradation features through several parallel convolution blocks of different sizes, and uses the graph attention mechanism to regard different filters as nodes, construct multiple different graph structures, and weight each feature graph according to the correlation between different feature graphs; the GRU module fused with the feature attention mechanism dynamically adjusts the weights of the input features at different time steps to achieve differential updating of sequence data.

2. The method for predicting the remaining life of an aircraft engine based on deep learning according to claim 1, characterized in that: The preprocessing includes feature selection and standardization; in, The feature selection includes: combining a correlation analysis method to perform feature selection on multidimensional variables to obtain variables related to the remaining life of the aircraft engine; the multidimensional variables include relevant sensor data and operating condition parameters; The standardization process includes a normalization process.

3. The method for predicting the remaining life of an aircraft engine based on deep learning according to claim 1, characterized in that: The data set is labeled according to the operating characteristics of the aircraft engine, and the data in the data set is divided into normal operating stage data and life degradation stage data, including: The operation phases of aircraft engines are divided by piecewise linear function method. According to its own operation characteristics, the operation cycle of aircraft engines is divided into two phases: normal operation phase and life degradation phase. It is assumed that the engine has a constant RUL value in the normal operation phase: Among them, y label Indicates the label of the constructed sample data, y label =R early Indicates the normal operation stage, y label = RUL represents the life degradation stage, RUL represents the actual remaining service life of the aircraft engine, R early Indicates the set engine life threshold; According to the division standard, the data in the data set are processed and divided into normal operation stage data and life degradation stage data.

4. The method for predicting the remaining life of an aircraft engine based on deep learning according to any one of claims 1 to 3, characterized in that: The multi-scale convolutional feature extraction module based on the graph attention mechanism includes three parallel convolution blocks of different sizes and a graph attention mechanism; Among them, three parallel convolution blocks of different sizes capture multi-level degraded features, and use the graph attention mechanism to treat the convolution kernels in different convolution blocks as nodes to build multiple different graph structures. According to the correlation between different feature maps, each feature map is weighted; Among them, the expression of CNN feature extraction is as follows: in, and is the weight matrix and bias matrix under the i-th convolution kernel, represents the feature map formed after the convolution operation, and σ(·) represents the activation function; The weighting process of the graph attention mechanism is as follows: Among them, i and j represent nodes in the graph structure, and The feature vector representation of nodes i and j, e ij represents the attention coefficient of node i to node j, represents all adjacent nodes of node i, || represents vector concatenation; After obtaining the attention scores of all nodes, the softmax function is used to normalize them, obtain the weights of different nodes, and assign weights to them.

5. The method for predicting the remaining life of an aircraft engine based on deep learning according to any one of claims 1 to 3, characterized in that: The GRU module integrating the feature attention mechanism is a two-layer GRU network structure. The feature attention mechanism is introduced after the first GRU. The feature attention mechanism is combined with the hidden state h of the previous moment in the GRU. t-1 The historical running data retained in the , weights the different input features at the next moment according to their importance, and uses the weighted input variables as the input of the next layer of GRU; the operation process of GRU is as follows: r t =σ(W r ·[h t-1 ,x t ]+b r ) z t =σ(W z ·[h t-1 ,x t ]+b z ) Among them, r t represents the output of the reset gate, z t represents the output of the update gate, σ(·) represents the activation function; W r , W h and W z represents the weight matrix; b r , b h and b z represents the bias matrix; h t Represents the information of the hidden state passed to the next moment.

6. The method for predicting the remaining life of an aircraft engine based on deep learning according to any one of claims 1 to 3, characterized in that: The RUL prediction module includes a concatenation layer and a fully connected layer. The concat function in the concatenation layer concatenates two vector matrices. In the RUL prediction module, after obtaining the outputs of the SDMCN module and the F-GRU module, the output vectors of the multi-scale convolutional feature extraction module based on the graph attention mechanism and the GRU module with fusion feature attention mechanism are concatenated in matrices through the concat function, and the concatenated vectors are input into the fully connected layer to obtain the engine remaining life prediction result.

7. A deep learning-based aircraft engine remaining life prediction system, characterized in that: include: A data acquisition module is used to acquire historical engine operation data and in-service engine monitoring data, and perform preprocessing to obtain a data set; The data partitioning module is used to label the data set according to the operating characteristics of the aircraft engine, and divide the data in the data set into normal operation stage data and life degradation stage data; A training sample construction module is used to segment the data of adjacent time periods of each engine unit using a sliding window method to construct a training sample data set; A model training module is used to train a pre-built neural network using a training sample data set to obtain an aircraft engine remaining life prediction model, wherein the aircraft engine remaining life prediction model is used to predict the life of the aircraft engine; Among them, the pre-constructed neural network includes a multi-scale convolutional feature extraction module based on a graph attention mechanism, a GRU module fused with a feature attention mechanism, and a RUL prediction module; the multi-scale convolutional feature extraction module based on a graph attention mechanism and the GRU module fused with a feature attention mechanism are operated in parallel, and the outputs of both are input into the RUL prediction module; the multi-scale convolutional feature extraction module based on a graph attention mechanism captures multi-level degradation features through several parallel convolution blocks of different sizes, and uses a graph attention mechanism to regard different filters as nodes, construct multiple different graph structures, and weight each feature graph according to the correlation between different feature graphs; the GRU module fused with a feature attention mechanism dynamically adjusts the weights of input features at different time steps to achieve differential updates of sequence data.

8. The aircraft engine remaining life prediction system based on deep learning according to claim 7, characterized in that: The data set is labeled according to the operating characteristics of the aircraft engine, and the data in the data set is divided into normal operating stage data and life degradation stage data, including: The operation phases of aircraft engines are divided by piecewise linear function method. According to its own operation characteristics, the operation cycle of aircraft engines is divided into two phases: normal operation phase and life degradation phase. It is assumed that the engine has a constant RUL value in the normal operation phase: Among them, y label Indicates the label of the constructed sample data, y label =R early Indicates the normal operation stage, y label = RUL represents the life degradation stage, RUL represents the actual remaining service life of the aircraft engine, R early Indicates the set engine life threshold; According to the division standard, the data in the data set are processed and divided into normal operation stage data and life degradation stage data.

9. A computer-readable storage medium, characterized in that: It stores a computer program for predicting the remaining life of an aircraft engine based on deep learning, wherein the computer program enables a computer to execute the method for predicting the remaining life of an aircraft engine based on deep learning as described in any one of claims 1 to 6.

10. An electronic device, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the programs include a method for executing the deep learning-based aircraft engine remaining life prediction method as described in any one of claims 1 to 6.

Images