Engine group fault mode recognition method and device based on density clustering-support vector machine and multi-moment prediction weighting and electronic equipment

Abstract

The invention discloses an engine group fault mode identification method and device based on a density clustering-support vector machine and multi-moment prediction weighting and electronic equipment, and the method comprises the steps: carrying out the dimension reduction processing of training engine performance parameters and testing engine performance parameters based on principal component analysis (PCA); training engine low-dimensional performance parameters and testing engine low-dimensional performance parameters are obtained; performing fault mode clustering processing on the low-dimensional performance parameters of the training engines based on a density clustering DBSCAN algorithm in predicting the single-moment fault mode of the engine to obtain fault mode classification labels corresponding to the training engines; establishing a single-moment fault mode classification model based on a support vector machine (SVM), and training the SVM-based single-moment fault mode classification model by using the low-dimensional performance parameters of the training engines and the fault mode classification labels corresponding to the training engines to obtain a trained SVM-based single-moment fault mode classification model; inputting low-dimensional performance parameters of the test engines into the trained SVM-based single-moment fault mode classification model to obtain a single-moment fault mode classification label of each test engine; and obtaining a final fault mode classification label of each test engine based on multi-moment fault mode weighted prediction and the single-moment fault mode classification label of each test engine.

Description

Technical Field

[0001] The present invention relates to the technical field of fault identification, and in particular to a method, device and electronic equipment for identifying engine group fault patterns based on density clustering-support vector machine and multi-moment prediction weighting. Background Art

[0002] Aircraft engines are a key part of aircraft. They usually operate under harsh environmental conditions such as high pressure and high-speed rotation, and their operating profiles and failure results are complex and changeable. Long-term service will lead to performance degradation of components and even the entire aircraft. If the engine health status cannot be evaluated in time and the remaining life of the engine cannot be accurately predicted in advance, the reliability and safety of the aircraft will be affected.

[0003] Since the operating profile and failure mode of aircraft engines are interconnected, the engine will experience a variety of different operating conditions before a failure mode occurs, and the combination of different operating conditions will cause the engine degradation path and failure mode to change. At the same time, the operating conditions and failure modes have a great influence on the degradation path analysis and life prediction errors. Identifying the engine operating conditions is conducive to improving the accuracy and applicability of the prediction model. Therefore, the problem of difficulty in identifying operating conditions and failure modes under complex operating conditions is addressed. Summary of the invention

[0004] The present invention provides a method, device and electronic equipment for identifying engine group fault patterns based on density clustering-support vector machine and multi-moment prediction weighting, so as to solve the technical problem of difficulty in identifying operating conditions and fault patterns under complex operating conditions.

[0005] The embodiment of the present invention provides a method for identifying engine group fault patterns based on density clustering-support vector machine and multi-time prediction weighting, comprising:

[0006] Based on principal component analysis PCA, the training engine performance parameters and the test engine performance parameters are respectively reduced in dimension to obtain the training engine low-dimensional performance parameters and the test engine low-dimensional performance parameters;

[0007] In predicting the single-moment fault mode of the engine, the low-dimensional performance parameters of the training engine are clustered based on the density clustering DBSCAN algorithm to obtain the fault mode classification label corresponding to each training engine;

[0008] Establishing a single-moment fault mode classification model based on a support vector machine (SVM), and training the single-moment fault mode classification model based on SVM using the low-dimensional performance parameters of the training engine and the fault mode classification labels corresponding to each training engine, to obtain a trained single-moment fault mode classification model based on SVM;

[0009] By inputting the low-dimensional performance parameters of the test engine into the trained SVM-based single-moment failure mode classification model, a single-moment failure mode classification label of each test engine is obtained;

[0010] Based on the multi-moment fault mode weighted prediction and the single-moment fault mode classification label of each test engine, a final fault mode classification label of each test engine is obtained.

[0011] The embodiment of the present invention further provides an engine group fault mode recognition device based on density clustering-support vector machine and multi-time prediction weighting, comprising:

[0012] A parameter dimension reduction module is used to perform dimension reduction processing on the training engine performance parameters and the test engine performance parameters based on principal component analysis PCA to obtain low-dimensional performance parameters of the training engine and low-dimensional performance parameters of the test engine;

[0013] A fault mode classification module is used to perform fault mode clustering processing on the low-dimensional performance parameters of the training engine based on the density clustering DBSCAN algorithm in predicting the single-moment fault mode of the engine, and obtain a fault mode classification label corresponding to each training engine;

[0014] A model training module, used to establish a single-moment fault mode classification model based on a support vector machine (SVM), and train the single-moment fault mode classification model based on the SVM using the low-dimensional performance parameters of the training engine and the fault mode classification labels corresponding to each training engine, to obtain a trained single-moment fault mode classification model based on the SVM;

[0015] The fault mode recognition module is used to obtain the single-moment fault mode classification label of each test engine by inputting the low-dimensional performance parameters of the test engine into the trained SVM-based single-moment fault mode classification model; and obtain the final fault mode classification label of each test engine based on the weighted prediction of multi-moment fault modes and the single-moment fault mode classification label of each test engine.

[0016] An embodiment of the present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor; when the computer program is executed by the processor, the steps of the engine group fault mode recognition method based on density clustering-support vector machine and multi-moment prediction weighting described in any one of claims 1 to 8 are implemented.

[0017] The beneficial effect of the present invention is that sensitive parameters related to engine degradation are extracted from multidimensional monitoring data, and a mode combining metric learning and clustering algorithm is adopted to separate operating conditions and fault modes in steps, thereby ensuring an accurate interpretation of the engine operating status. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a flow chart of a method for identifying engine group fault patterns based on density clustering-support vector machine and multi-time prediction weighting provided by the present invention;

[0019] Figure 2 It is the technical roadmap of the present invention for predicting the life of aircraft engines under complex operating conditions based on metric learning;

[0020] Figure 3 It is a flow chart of a method for adaptively identifying engine operating conditions by combining clustering algorithm with metric learning;

[0021] Figure 4 It is a flow chart of the method for equivalent transformation of variable working condition data;

[0022] Figure 5 It is a curve diagram representing the degradation of variable working conditions;

[0023] Figure 6 It is a flow chart of a fault mode identification method based on variable weight prediction;

[0024] Figure 7 It is a flow chart for constructing a single-moment fault mode classification model;

[0025] Figure 8 This is the structure diagram of the LSTMCNN_AE network;

[0026] Fig. 9 This is the structural details of the encoder and decoder in the LSTMCNN_AE network;

[0027] Fig.10 This is the engine timing degradation feature extraction flow chart based on LSTMCNN_AE;

[0028] Fig.11 This is a schematic diagram of the LSTMCNN_AE model input sample generation process;

[0029] Fig.12 It is a flow chart of engine health assessment for multiple fault modes and variable operating conditions based on NCA metric learning;

[0030] Fig.13 It is a schematic diagram of the Siamese network structure;

[0031] Fig.14 It is a structural diagram of the SN-GRU network model;

[0032] Fig.15 It is a schematic diagram of the SN-GRU network structure;

[0033] Fig.16It is a flowchart of engine life prediction under multiple fault modes based on SN-GRU. DETAILED DESCRIPTION

[0034] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. In the subsequent description, the use of suffixes such as "module", "component" or "unit" used to represent elements is only to facilitate the description of the present invention and has no specific meaning in itself. Therefore, "module", "component" or "unit" can be used in a mixed manner.

[0035] Figure 1 The present invention provides a flow chart of a method for identifying engine group fault patterns based on density clustering-support vector machine and multi-time prediction weighting, such as Figure 1 As shown, it includes: S101: based on principal component analysis PCA, dimensionality reduction processing is performed on the training engine performance parameters and the test engine performance parameters respectively to obtain low-dimensional performance parameters of the training engine and low-dimensional performance parameters of the test engine; S102: in predicting the single-moment fault mode of the engine, the low-dimensional performance parameters of the training engine are clustered based on the density clustering DBSCAN algorithm to obtain the fault mode classification labels corresponding to each training engine; S103: a single-moment fault mode classification model based on a support vector machine SVM is established, and the single-moment fault mode classification model based on SVM is trained using the low-dimensional performance parameters of the training engine and the fault mode classification labels corresponding to each training engine to obtain a trained single-moment fault mode classification model based on SVM; S104: the single-moment fault mode classification labels of each test engine are obtained by inputting the low-dimensional performance parameters of the test engine into the trained single-moment fault mode classification model based on SVM; S105: based on the weighted prediction of multi-moment fault modes and the single-moment fault mode classification labels of each test engine, the final fault mode classification labels of each test engine are obtained.

[0036] In an embodiment of the present invention, the method of obtaining the final failure mode classification label of each test engine based on the weighted prediction of multi-moment failure modes and the single-moment failure mode classification label of each test engine includes: obtaining the prediction result of the failure mode of each test engine at a single moment according to the trained SVM-based single-moment failure mode classification model; performing weighted prediction using the failure state of each test engine at a single moment and the comprehensive multi-moment failure state to obtain the weighted prediction result of each test engine under different failure modes; and obtaining the final failure mode classification label of each test engine using the weighted prediction result of each test engine under different failure modes.

[0037] In an embodiment of the present invention, according to the trained SVM-based single-moment fault mode classification model, obtaining the prediction results of each test engine under the fault mode at a single moment includes:

[0038]

[0039] In an embodiment of the present invention, the weighted prediction is performed using the fault state of each test engine at a single moment and the comprehensive fault state at multiple moments to obtain the weighted prediction results of each test engine under different fault modes, including:

[0040]

[0041] Among them, m represents the fault mode; j represents the test engine; τ represents the recent weighting coefficient of the recognition proportion of recent data; λ represents the comprehensive weighting coefficient of the number of flight cycles considered comprehensively; k represents the value coefficient affecting the weight of the recent and long-term, and represents the flight cycle at the most recent moment; represents the predicted state of the test engine j under fault mode m at the moment farthest from t; represents the predicted state of the test engine j under fault mode m at time tk, It represents the prediction result of engine j under fault mode m obtained by weighted prediction.

[0042] In an embodiment of the present invention, the method of obtaining the final failure mode classification label of each test engine by using the weighted prediction results of each test engine under different failure modes includes:

[0043]

[0044] Among them, Y j represents the final failure mode classification label of test engine j.

[0045] In an embodiment of the present invention, before the training engine performance parameters and the test engine performance parameters are subjected to dimensionality reduction processing based on principal component analysis PCA, the method further includes: screening out the performance parameters of the engine that are sensitive to decay under variable operating conditions; extracting engine data under different operating conditions based on the individual engine operating condition division results to obtain decay-sensitive performance parameters under each operating condition; normalizing the decay-sensitive performance parameters under each operating condition using a normalization method, and reconstructing the normalized decay-sensitive performance parameters under each operating condition according to the flight cycle sequence of the engine to obtain decay-sensitive performance parameters under fused multiple operating conditions; and dividing the decay-sensitive performance parameters under fused multiple operating conditions into training engine performance parameters and test engine performance parameters.

[0046] In an embodiment of the present invention, screening out the performance parameters of the engine that are sensitive to degradation under variable operating conditions also includes: obtaining multidimensional operating parameters of the training engine under different operating conditions; using a K-Means clustering algorithm to preliminarily identify the operating condition category of the training engine based on the obtained multidimensional operating parameters, and obtaining the cluster center of each operating condition; using a multidimensional scaling analysis MDS algorithm to scale the multidimensional operating parameters of the test engine and the cluster center of the corresponding operating condition to one dimension, and using the one-dimensional operating condition cluster center as the operating condition baseline; and adaptively identifying the operating condition corresponding to each test engine in each flight cycle based on the principle of being closest to the operating condition baseline.

[0047] In an embodiment of the present invention, the operating condition corresponding to each test engine in each flight cycle is adaptively identified based on the principle of being closest to the operating condition baseline, including: by measuring the distance between the operating parameters of the test engine at a single moment and each operating condition baseline, selecting the operating condition with the closest distance as the operating condition to which the test engine belongs.

[0048] The present invention also provides an engine group fault pattern recognition device based on density clustering-support vector machine and multi-time prediction weighting, including: a parameter dimension reduction module, which is used to perform dimension reduction processing on the training engine performance parameters and the test engine performance parameters based on principal component analysis PCA, respectively, to obtain the training engine low-dimensional performance parameters and the test engine low-dimensional performance parameters; a fault pattern classification module, which is used to perform fault pattern clustering processing on the low-dimensional performance parameters of the training engine based on the density clustering DBSCAN algorithm in predicting the single-time fault mode of the engine, to obtain the fault pattern classification label corresponding to each training engine; a model training module, which is used to establish a fault pattern classification label based on the support vector machine SV A single-moment fault mode classification model based on SVM is prepared, and the single-moment fault mode classification model based on SVM is trained by using the low-dimensional performance parameters of the training engine and the fault mode classification labels corresponding to each training engine to obtain a trained single-moment fault mode classification model based on SVM; a fault mode recognition module is used to obtain a single-moment fault mode classification label of each test engine by inputting the low-dimensional performance parameters of the test engine into the trained single-moment fault mode classification model based on SVM; and a final fault mode classification label of each test engine is obtained based on the weighted prediction of multi-moment fault modes and the single-moment fault mode classification labels of each test engine.

[0049] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor; when the computer program is executed by the processor, the steps of the engine group fault pattern recognition method based on density clustering-support vector machine and multi-moment prediction weighting are implemented.

[0050] There are many technical bottlenecks that need to be solved in the life prediction of aircraft engines under variable operating conditions and multiple fault modes: difficulty in identifying operating conditions and fault modes under complex operating conditions, difficulty in extracting time series degradation features under variable operating conditions, difficulty in quantifying engine degradation trends under variable operating conditions, and decreased accuracy of engine life prediction under multiple fault modes. In response to the above problems, a life prediction method is proposed. Please refer to the overall life prediction process and technical route. Figure 2 , specifically includes three parts: engine group fault mode recognition method based on density clustering-support vector machine and multi-time prediction weighting, variable operating condition engine health assessment based on improved autoencoder and metric learning, and multi-fault mode engine life prediction based on time series distribution metric and domain generalization.

[0051] 1. Engine group fault pattern recognition method based on density clustering-support vector machine and multi-time prediction weighting

[0052] In view of the difficulty in identifying operating conditions and fault modes under complex operating conditions, the present invention starts from the two perspectives of identification order and identification method, and formulates an operating condition analysis process from individual engines to engine groups. In terms of order, the flight conditions during the operation monitoring of a single engine are first identified, and then the failure fault modes of the engine group are divided. In terms of method, since the operating condition is a single-moment identification of the engine flight cycle, the combination of clustering method and metric learning can identify the category of operating parameters at a specific moment, which provides ideas for the division of operating conditions. The performance degradation of the engine is a gradual process. For test engines that may be in the early stages of degradation, their fault characteristics are not obvious, and it is difficult to accurately distinguish them through monitoring parameters at a single moment. Therefore, the fault mode is the identification of multiple moments of the evolution trend. For fault mode recognition, different degradation trajectories can be identified through density clustering methods, while the weighted fusion method provides new ideas for multi-moment fault mode discrimination.

[0053] 1.1 Engine operating condition classification based on metric learning and clustering

[0054] In the identification of engine operating conditions, it is necessary to cluster the multidimensional operating parameters to obtain the operating condition classification results. In order to accurately determine the operating condition label at a single moment, the present invention proposes an improved clustering method to identify the engine operating condition, that is, to introduce the unsupervised metric learning MDS algorithm into the K-Means clustering method. The core of MDS is to use high-dimensional data to calculate the distribution of data in low dimensions, that is, to reconstruct the low-dimensional coordinates of the data, so as to efficiently measure the real distance between the data. The MDS algorithm can project the multidimensional operating parameters into a low-dimensional space while keeping the relative position unchanged. The test engine can automatically identify and classify it into the nearest operating condition category, thereby adaptively realizing the engine's single-moment operating condition category division. The MDS algorithm can be used to effectively calculate the relative distance between the high-dimensional operating condition data of the test set and the cluster center, and overcome the problem of inconsistent Euclidean distance scales, realize the test engine operating condition category division, and solve the problem of inaccurate clustering of the test set operating conditions.

[0055] In the engine operating condition identification, the multi-dimensional operating parameters of the training engine are used as the data basis, and the K-Means clustering algorithm is used to preliminarily identify the training engine operating condition categories, and obtain the cluster center of each operating condition. Then, the MDS algorithm is used to scale the test engine operating parameters and the operating condition cluster center to one dimension, and the operating condition corresponding to each flight cycle of the test engine is adaptively identified based on the principle of the closest distance to the operating condition baseline. The specific process of adaptive identification of engine operating conditions based on the combination of metric learning and clustering is as follows: Figure 3 shown.

[0056] In short, the method of introducing the MDS algorithm into the K-Means clustering algorithm to adaptively realize the classification of the engine's single-time operating condition category includes the following steps: S111, obtaining the multidimensional operating parameters of the training engine under different operating conditions; S112, using the K-Means clustering algorithm to preliminarily identify the operating condition category of the training engine according to the multidimensional operating parameters obtained in step S111, and obtaining the cluster center of each operating condition; S113, using the MDS algorithm to scale the multidimensional operating parameters of the test engine and the cluster center of the corresponding operating condition to one dimension; S114, adaptively identifying the operating condition corresponding to the test engine in each flight cycle based on the principle of being closest to the operating condition baseline.

[0057] The pseudo code for adaptive recognition of engine operating conditions based on metric learning and clustering is as follows:

[0058]

[0059]

[0060] The process of adaptive recognition of engine operating conditions based on the combination of metric learning and clustering is as follows:

[0061] (101) Engine operating parameter extraction

[0062] The data of aircraft engines under complex operating conditions include operating parameters and gas path parameters. The operating parameter data is extracted as the data basis for engine operating condition identification. The operating parameters of the engine are constantly changing, indicating that the operating conditions of the engine are constantly changing during operation. The combination of operating parameters brings different operating conditions to the aircraft. When the values ​​of the three operating parameters are basically the same and within a very small fluctuation range, it can be indicated that the engine operating conditions are the same. The operating conditions of aircraft engines usually change randomly, and it is impossible to find their changing patterns, which also brings certain difficulties to the subsequent engine health assessment under variable conditions.

[0063] (102) K-Means-based training engine cluster center determination and operating condition label division

[0064] The divided training engine operating parameters are used as the multi-dimensional input of K-Means clustering. According to the number of aviation engine operating condition categories k, k operating condition parameter combination points are randomly selected as the initial cluster centers. In the training K-Means clustering model, the number of cluster centers and the maximum number of iterations for each training are set. After the training is completed, the model returns the optimal cluster center and outputs the operating condition label corresponding to each training engine flight cycle and the final cluster center result.

[0065] (103) Adaptive identification of test engine operating conditions based on MDS metrics

[0066] The operating parameters of the test engine are merged with the operating condition clustering center, and the multidimensional data is scaled to one dimension using the multidimensional scaling MDS algorithm. The one-dimensional operating condition center is used as the baseline. The operating data after single-time scaling can automatically identify the baseline operating condition with the smallest distance, thereby adaptively selecting the operating condition and obtaining the operating condition of the test engine in each flight cycle.

[0067] 1.2 Engine data fusion based on equivalent transformation of operating conditions

[0068] Aircraft engine gas path parameters can serve as an important basis for health assessment and life prediction, but the data of gas path parameters fluctuate up and down under the influence of operating conditions, making it difficult to characterize the true degradation trend of the engine. Usually among aircraft engine gas path parameters, not all gas path parameters are useful for studying the engine status, and some parameters provide constant or discrete values ​​throughout the life cycle of the engine. In order to restore the true degradation trend of the engine under variable operating conditions, it is necessary to unify the performance parameters under different operating conditions to a comparable parameter standard. The present invention proposes a method for equivalent transformation of variable operating condition engine data, which mainly consists of four parts: screening of decay performance parameters, decomposition of multi-operating condition time series data, standardization of performance parameters of each operating condition, and reconstruction of performance parameters. The process of equivalent transformation of variable operating condition data is as follows: Figure 4shown.

[0069] (1001) Screening of decay-sensitive gas path parameters under variable operating conditions

[0070] In the screening of degradation performance parameters, by drawing the engine life curve under different working conditions, the gas path parameters that are constant and have no obvious degradation trend are initially excluded, so as to preliminarily screen out the performance parameters that have obvious degradation trend with working conditions, small fluctuation, and are more sensitive to engine degradation, and form a Figure 4 The performance parameter sequence under variable operating conditions shown in .

[0071] (1002) Multi-operating condition time series data decomposition

[0072] In the decomposition of multi-condition time series data, based on the results of the division of individual engine operating conditions, the engine data under different conditions are extracted to obtain the decay-sensitive performance parameters under each condition, thereby realizing the extraction of feature data under variable conditions. Based on the condition identification label based on the improved clustering method, the engine time series data is decomposed based on the condition by matching the engine flight cycle with the condition. At this time, the various gas path parameters of the engine can be divided into time-discontinuous data under different conditions, but under the same condition, the gas path parameters show a relatively uniform degradation trend, and the fluctuation is smaller than before the data decomposition, thus laying the foundation for parameter standardization and reconstruction.

[0073] (1003) Standardization of performance parameters for each operating condition

[0074] Aircraft engines face frequent changes in operating conditions during operation. Under the same operating conditions, the degradation parameters of engine performance usually show a gradual change trend with small fluctuations. When the operating conditions change frequently, the degradation trend is difficult to show.

[0075] To achieve the goal of parameter unification and degradation trend integration, two operations need to be taken: first, for engine parameters, convert them into unified indicators that can reflect degradation trends, scale the data under different working conditions, and unify them into the standard space; second, for degradation trends, form the standardized data under different working conditions into a curve that can clearly characterize the degradation of variable working conditions, such as Figure 5 shown.

[0076] The normalization method is used to normalize the degradation sensitivity performance parameters under different working conditions, so as to achieve the parameter normalization of different working conditions. i At the moment, the decay sensitivity performance parameter is x i , the corresponding working condition is m i , its state parameter can be expressed as (t i ,x i ,m i),i=1,2,..,n. The engine operating conditions include k types, and its operating condition category set can be expressed as M={M 1 ,M 2 ,...,M k}, therefore, the total set of performance parameters under each working condition can be expressed as {X} (K) ={x i |m i ∈M}.

[0077] Z-score normalization establishes a standardized index by obtaining the mean and standard deviation of the data. This method can transform the original data into data with a mean of 0 and a variance of 1. The mean and standard deviation of the parameters under different working conditions can be expressed as and k , then the data normalization formula under working condition k is:

[0078]

[0079] The z-score method uses the mean and standard deviation as the normalization benchmark and has less impact on local fluctuations and noise. Given that aircraft engine parameters usually have greater noise interference, it can more effectively deal with this problem.

[0080] (1004) Gas path performance parameter reconstruction

[0081] Finally, according to the flight cycle sequence of the engine, the normalized performance data is reconstructed to merge the normalized characteristic parameters under different operating conditions and reconstruct the degradation time series integrating multiple operating conditions to characterize the degradation of the engine under variable operating conditions. The reconstructed parameter data can be expressed as:

[0082] X'={x 1 ',x' 2 ,...,x' n} (6)

[0083] Among them, X' is the aerodynamic performance degradation parameter of the engine under the reconstructed variable working condition, x t ' is the N-dimensional performance parameter under flight cycle t, t=1,2,…,n.

[0084] 1.3 Engine Fault Pattern Recognition Based on Classification and Variable Weight Prediction

[0085] In fault mode recognition, it is necessary to divide the fault mode according to the degradation path of the engine. Considering that the engine parameters have certain volatility, K-Means does not have the inclusiveness of noise data, and for trajectory clustering, the similarity mean has no practical meaning, which will cause trouble for the subsequent test set data performance degradation trajectory recognition and classification. The density-based clustering algorithm is not affected by the up and down fluctuations of parameters and is suitable for fault mode recognition. Therefore, the present invention designs a weighted fault mode discrimination method based on density clustering-support vector machine (DBSCAN-SVM) and multi-time prediction, identifies the engine fault mode through the density clustering method, and adopts SVM to discriminate the single-time fault state classification of the test unit, and finally weightedly considers the multi-time fault state to discriminate the test unit fault mode.

[0086] In the fault mode recognition method based on variable weight prediction, PCA dimensionality reduction is first performed based on the screened gas path performance degradation parameters to initially obtain low-dimensional features for clustering of accurate fault modes for training the engine; then, a single-moment fault mode classification model based on SVM is established on the basis of density clustering, and a fault mode weighted prediction method is designed to complete the fault mode recognition of the test engine. The engine fault mode recognition based on variable weight prediction is mainly divided into two parts, namely the establishment of a single-moment fault mode classification model and multi-moment fault mode weighted prediction. The main process is as follows: Figure 6 shown.

[0087] The pseudo code of engine failure mode recognition based on variable weight prediction is as follows:

[0088]

[0089]

[0090] 301) Constructing a single-moment fault mode classification model

[0091] The construction of the single-moment fault mode classification model is mainly divided into three parts: parameter dimension reduction based on principal component analysis, degradation trajectory clustering based on DBSCAN, and single-moment fault mode classification model construction based on SVM. Figure 7 shown.

[0092] (301) Parameter Dimensionality Reduction Based on Principal Component Analysis

[0093] After the equivalent transformation of the working conditions, the gas path performance parameters are still multidimensional, and there may be correlation between the parameters, which makes the trend of the failure mode difficult and complex. If the performance parameters are analyzed separately, the efficiency will be greatly reduced, and the problem will be viewed in isolation rather than comprehensively. Therefore, considering the correlation between the performance parameters, the PCA method in unsupervised metric learning is used for dimensionality reduction, which can obtain unrelated low-dimensional parameter information without losing the original parameter information.

[0094] PCA is a nonparametric dimensionality reduction technique that aims to transform numerous variables in a high-dimensional dataset into fewer new variables while retaining the key information of the data. Its core principle is to linearly transform the data in unrelated directions by calculating the eigenvectors of the covariance matrix. These new dimensions are sorted by their contribution to the total variance to identify the most important dimensions that retain important information of the data. This helps to reduce the dimensionality of the data while maintaining the key structural characteristics of the data.

[0095] (302) Clustering of Degraded Trajectories Based on DBSCAN

[0096] The training engine monitors the data from healthy to decayed. Considering that the degradation characteristics are often not obvious in the early stage of engine operation, the late decay data is selected to identify its fault mode category. After extracting the low-dimensional gas path parameter characteristics of the engine by PCA method, the DBSCAN method is used to divide the late gas path parameter characteristics of the training engine, and the corresponding fault mode of each training engine is obtained.

[0097] After the fault mode clustering based on the DBSCAN algorithm, assuming that there are M types of fault modes, the characteristic matrix of the mth type of fault after clustering is:

[0098]

[0099] Among them, Z m N m ×l matrix, N m is the number of characteristic samples of the mth type of fault mode, and l is the dimension of the fault feature. m The corresponding failure mode classification label can be expressed as Y m =[mm … m] T .

[0100] (303) Construction of single moment fault mode classification model based on SVM

[0101] The characteristic matrix of each type of fault mode is used as the input of the fault mode classifier, and the corresponding fault mode label is used as the output of the classifier to train the fault mode classification model. Unlike neural networks that require a large amount of data for training, SVM, as a classic classification algorithm, can achieve excellent classification results with a small number of samples. Since the sample size of aircraft engine fault modes is small, the present invention uses SVM to construct a single-moment fault mode classification model to establish a foundation for testing engine fault mode classification.

[0102] SVM is a supervised learning classification algorithm, and its principle is based on finding a hyperplane with the largest margin to separate data points of different categories. The margin refers to the distance from the data point closest to the hyperplane to the plane, and the support vector is the data point with the closest distance. The present invention designs a fault mode classification model based on SVM. If the training engine sample is X={(x 1 ,Y 1 ),(x 2 ,Y 2 ),…,(x N ,Y N )}, the failure mode label is Y k ∈{1,2,…,M′},k=1,2,…,N, then the optimization problem of the SVM model of different types of fault modes can be expressed as:

[0103]

[0104] Among them, φ(x γ ) is the mapping function from input engine data to category labels, is the loss function of the model, and the penalty coefficient C of the hyperparameters and the hyperplane normal vector ω are optimized by the model. ij , hyperplane intercept b ij , thus obtaining the hyperplane partition of the i-th fault mode and the j-th fault mode. For the test sample x test , a single SVM model belongs to the category The judgment is:

[0105]

[0106] Among them, if If the value is 1, it means that the test sample is in the i-th failure mode, otherwise it is in the j-th failure mode.

[0107] 302) Multi-time Fault Mode Weighted Prediction

[0108] Since the performance degradation of the engine is a gradual process, the fault characteristics of the test engine that has not completely degraded may not be significant enough, and it is difficult to accurately identify it through the monitoring parameters at a single moment. Therefore, a weighted prediction method is introduced to determine the final fault mode of the engine by comprehensively considering the fault mode characteristics at multiple moments. In the process of fault mode identification, the dynamic changes in the engine degradation process are more comprehensively considered, which makes up for the defects caused by the fault mode classification at a single moment.

[0109] According to the SVM fault mode classification model, the fault state of the test engine j at a single moment can be expressed as Its state under fault mode m (m=1,2,…,M) can be calculated as:

[0110]

[0111] Afterwards, weighted prediction is performed based on the comprehensive multi-time fault status, and the weighted prediction results of the test engine j under different fault modes can be calculated as:

[0112]

[0113] The present invention introduces the recent weighting coefficient τ (0 < τ < 1) and the comprehensive weighting coefficient λ (λ, t) to analyze the engine degradation trajectory, where τ represents the recognition weight of recent data and λ represents the number of flight cycles considered comprehensively. The final engine failure mode can be calculated as The failure mode with the highest probability is selected as the final failure mode category of the engine.

[0114] The calculation method of τ is: take a number between (0,1) as the weight according to the recent data requirements. In this case, 0.7 is taken as the recent weight coefficient.

[0115] The calculation method of λ is: take 70% of the flight cycles of the jth engine.

[0116] The following is an example of the process of engine group fault pattern recognition based on density clustering-support vector machine and multi-moment prediction weighting, combined with a specific case.

[0117] A. Dataset Introduction

[0118] The present invention uses an engine simulation data set provided by a company, which is generated by C-MAPSS (Commercial Modular Aero-Propulsion System Simulation) simulation software. The model generates engine performance degradation data for subsequent analysis by simulating the gradual degradation process of five key components, namely, the fan, low-pressure compressor, high-pressure compressor, high-pressure turbine and low-pressure turbine, under different operating conditions and failure modes.

[0119] Based on C-MAPSS simulation, 4 data sets were obtained. Due to the influence of fault modes and operating conditions on sensor data, the complexity of data sets 1 to 4 continued to increase. The situation of each data set is shown in Table 1 below. Since the present invention is mainly aimed at the situation under variable engine conditions and multiple failure modes, the fourth data set FD004 is selected. This data set includes 249 training engine data and 248 test engine data. Each engine operates under 6 different operating conditions, and the final failure mode can be divided into 2 types. The failure modes include fan degradation and high-pressure compressor degradation, but the degradation path is not informed, and each engine finally degrades to only one failure mode, and there is no situation where two failure modes occur at the same time.

[0120] The engine has two failure modes: HPC degradation and fan degradation, but the corresponding degradation paths are not marked.

[0121] Table 1 C-MAPSS dataset details

[0122]

[0123] There are four main reasons for choosing this dataset. The first is that the dataset is authoritative, and the data provided by NASA is more reliable and accurate. The second is that the dataset is typical. The monitoring data in the dataset is a degradation signal mixed with invalid signals and noise in a certain fault degradation mode, which shows that it is challenging to make accurate assessments and predictions. The third is scalability. After studying this dataset, the research can be expanded to more complex engines or other objects, such as the PHM08 challenge dataset, N-CMAPPS, etc. The fourth is comparability. Many studies are currently focused on this dataset, so it is easier to compare.

[0124] B. Engine operating condition classification based on metric learning and clustering

[0125] B1) Extraction of aircraft engine operating parameters

[0126] In the FD004 data set, the sensor monitoring data includes 3 operating parameters and 21 gas path parameters. The 3 operating parameters need to be extracted as the data basis for engine operating condition identification. According to the changes in the operating parameters of training engine No. 1, training engine No. 2, test engine No. 1, and test engine No. 2, it can be seen that the operating parameters of the same engine are in a constant change process, and the operating parameters of different engines vary greatly.

[0127] B2) Determination of cluster centers of training engines and division of operating condition labels

[0128] The three-dimensional training engine operating parameters are used as the input of K-Means clustering. Since the engine samples have 6 operating conditions, the clustering category k is set to 6, and the maximum number of iterations of model training is set to 300. The K-Means clustering model is trained to obtain the engine operating condition cluster center and each flight cycle cluster label. Among them, the operating condition label records the operating condition of the flight cycle. By comparing the operating condition labels, the flight altitude, Mach number and throttle lever solver angle range of the engine at that moment can be determined.

[0129] In the aero-engine operating condition clustering results and cluster centers, the six points of the operating condition clustering results represent the center points of the six operating condition categories, and the three coordinate axes represent the three operating condition parameters of flight altitude, Mach number, and throttle lever resolver angle, respectively. The six categories represent the six different operating conditions of the aero-engine. Table 2 shows the cluster center coordinates and cluster radius of each operating condition. The operating condition cluster center is the basis for the test engine operating condition identification based on the MDS algorithm.

[0130] Table 2 Flight condition cluster centers and cluster radius

[0131]

[0132] After identifying the operating conditions of the training engine, the operating condition label corresponding to each cycle is output. For example, the operating condition label corresponding to the first operating condition is 1, and the operating condition label corresponding to the sixth operating condition is 6.

[0133] B3) Adaptive identification of test engine operating conditions based on MDS metrics

[0134] The MDS metric learning method is used to scale the test engine operating parameters and operating condition centers into one-dimensional data, and the distance d between the single-time operating data and each operating condition center is measured. j , adaptively select the closest distance as the working condition.

[0135] C. Engine data fusion based on equivalent transformation of operating conditions

[0136] C1) Screening of decay-sensitive gas path parameters under variable operating conditions

[0137] 21 gas path parameters in FD004 are selected as the data basis for health assessment and life prediction. Therefore, engine data fusion based on equivalent transformation of working conditions is carried out for the 21 gas path parameters. Table 3 below shows the specific description and symbolic representation of the 21 gas path parameters in C-MAPSS data.

[0138] Table 3 Chinese description and symbolic representation of gas path parameters

[0139]

[0140] In the change trend of the original 21 gas path parameters of the No. 1 training engine, the original gas path parameter data changes disorderly, and it is difficult to find its degradation law from the engine gas path performance parameters without dividing the working conditions. Therefore, it is necessary to screen the degradation-sensitive gas path parameters that can accurately characterize the engine degradation state, so as to complete the subsequent evaluation and prediction work more efficiently and accurately.

[0141] Since the five gas path parameters T2, P2, farB, Nf_dmd, and PCNfR_dmd do not change with time under the same working conditions, and the degradation trends of the five gas path parameters T24, P15, epr, W31, and W32 are chaotic and not obvious, 10 gas path parameters that are constant under various working conditions and insensitive to degradation can be preliminarily excluded, and the remaining 11 gas path parameters, namely T30, T50, P30, Nf, NC, Ps30, phi, NRf, NRc, BPR, and htBleed, are selected as indicator parameters for further evaluation and prediction.

[0142] C2) Decomposition of multi-operating condition time series data

[0143] After screening out the degradation-sensitive performance parameters of aircraft engines, the degradation trends of the degradation-sensitive performance parameters under 6 independent working conditions can be extracted according to the working condition division results. Under the same working condition, the change trends of various gas path parameters are generally consistent, but under different working conditions, the degradation range of the same parameter varies greatly. Therefore, it is of great significance to decompose and reconstruct the data based on the working condition to restore the original degradation trend of the gas path parameters.

[0144] C3) Standardization of performance parameters under various working conditions

[0145] After decomposing the multi-condition time series data, the performance parameters of each condition are standardized. Regarding the normalization method, taking the No. 1 training engine as an example, the applicability of the two normalization methods for the standardization of the performance parameters of each engine condition is verified. Both the linear normalization and z-score normalization methods can remove the interference of variable conditions to a certain extent and integrate the degradation trend of the gas path parameters under each condition. By comparing the normalization results of parameters such as Nf and NRf in the two figures, it can be seen that the linear normalization method is easily affected by local outliers, and the performance of the z-score normalization method is more stable, which is completely consistent with the previous theoretical analysis.

[0146] C4) Gas path performance parameter reconstruction

[0147] The standardized gas path performance parameters of each operating condition are merged to reconstruct the degradation time series integrating multiple operating conditions. The engine data fusion method based on equivalent transformation of operating conditions can achieve the effect of removing the interference of variable operating conditions and restoring the trend of gas path performance parameters.

[0148] D. Engine Fault Pattern Recognition Based on Classification and Variable Weight Prediction

[0149] (D1) Parameter Dimensionality Reduction Based on Principal Component Analysis

[0150] In predicting the single-moment fault mode of the engine, the parameter dimension reduction based on principal component analysis is first performed to provide preliminary low-dimensional features for the clustering of gas path parameter data. The PCA method is used to reduce the dimension of the 11 gas path parameter working condition fusion data obtained above. Based on the proportion of parameter-explainable characteristic information based on the PCA method, it can be seen that the first principal component and the second principal component account for 96.2% of the total information, which can represent the degradation information of the engine gas path parameters. Therefore, the first principal component "PCA1" and the second principal component "PCA2" are selected as the subsequent fault mode analysis data.

[0151] (D2) Degenerate clustering based on DBSCAN

[0152] The first principal component and the second principal component are used as the basis for clustering the degradation trajectory data, and two types of degradation trends can be preliminarily identified from the data distribution, which is consistent with the two types of engine failure modes described in the data set.

[0153] Since the characteristics of the engine's initial failure mode are not obvious and there are overlapping feature points, it is difficult to further divide the engine failure modes. Therefore, the late degradation data is selected to determine the failure mode category. The training engine degradation corresponding to the last 30% flight cycle and the last 20% flight cycle are respectively intercepted. The degradation data in the late degradation period can more clearly determine the failure mode without data overlap. Therefore, the last 20% degradation data is intercepted for failure mode division.

[0154] With the clustering radius e as 20 and the minimum number of regions MinPts as 1000, the DBSCAN clustering method is used to divide the degradation modes of the above training engines, so as to obtain the fault mode classification labels of each training engine.

[0155] (D3) Construction of single-moment fault mode classification model based on SVM

[0156] Taking the PCA degradation features of the training engine as input and the corresponding flight cycle failure mode labels as output, the SVM binary classification model is trained to complete the establishment of the single-moment failure mode classification model, and lay the foundation for the model of multi-moment weighted prediction of the subsequent test engine. Table 4 shows the model parameters.

[0157] Table 4 Model parameters

[0158]

[0159] (D4) Multi-time failure mode weighted prediction

[0160] The single-moment failure mode of the test engine is classified using the trained failure mode classifier.

[0161] Since the engine only experiences one failure mode from operation to completion, the weighted failure mode prediction method is used to predict the final failure mode of the engine. The recent weight coefficient τ is set to 0.7, and the comprehensive consideration quantity λ is the number of predicted failure modes of the last 70% of the engine.

[0162] In summary, the present invention analyzes the complex operating conditions of aircraft engines and integrates the metric learning method with the clustering method to establish an engine operating condition division based on the combination of metric learning and clustering, an engine data fusion based on operating condition equivalent transformation, and an engine fault pattern recognition method based on classification and edge weight prediction, forming a complete process for separation and division of engine variable operating conditions and multiple fault modes.

[0163] After completing the engine operating condition division, engine data fusion under variable conditions, and engine fault mode identification, the present invention also includes: variable condition engine health assessment based on improved autoencoder and metric learning and multi-fault mode engine life prediction based on metric learning and domain generalization, which are specifically as follows:

[0164] 2. Engine Health Assessment under Variable Operating Conditions Based on Improved Autoencoder and Metric Learning

[0165] The variable operating condition engine health assessment method comprises: constructing a long short-term memory convolutional autoencoder LSTMCNN_AE feature extraction model, training the LSTMCNN_AE feature extraction model using engine training set data to obtain a trained LSTMCNN_AE feature extraction model; inputting engine test set data into the trained LSTMCNN_AE feature extraction model to obtain low-dimensional time series degradation feature data; constructing and training an NCA metric learning model under each fault mode, and mapping the low-dimensional time series degradation feature data using the trained NCA metric learning model under each fault mode to obtain mapping feature data; and performing engine health assessment processing based on an optimized Mahalanobis distance feature matrix and the mapping feature data.

[0166] The LSTMCNN_AE feature extraction model is trained using engine training set data to obtain a trained LSTMCNN_AE feature extraction model, including: preprocessing multidimensional engine parameter data under different working conditions using a sliding window of set length and step size, and dividing the multidimensional engine parameter data into training samples and test samples according to a sliding window method; using the training samples as model input and output, and reconstructing the input sequence through the LSTMCNN_AE feature extraction model; capturing feature information based on the training data set, determining model parameters of the feature extraction model, and optimizing the model parameters through a residual learning method to obtain a trained LSTMCNN_AE feature extraction model.

[0167] Constructing and training the NCA metric learning model under each fault mode includes: dividing the low-dimensional timing degradation feature data into timing degradation feature data under different fault modes according to the identified engine fault mode label; under each fault mode, dividing the timing degradation feature data into healthy set feature data and degraded set feature data, and marking the corresponding healthy set state label and degraded set state label respectively; constructing the NCA metric learning model under each fault mode, and taking the healthy set features and degraded set features under each fault mode as the model input, and taking the state label corresponding to the feature as the model output for training, so as to obtain the trained NCA metric learning model and the optimized Mahalanobis distance feature matrix under each fault mode.

[0168] The engine health assessment processing based on the optimized Mahalanobis distance feature matrix and the mapping feature data includes: calculating the distance between the healthy space and the degraded space of each operating condition of the engine based on the optimized Mahalanobis distance feature matrix and the mapping feature data; normalizing the distance under each operating condition by a linear normalization method to obtain the health assessment index of the engine under each operating condition; reconstructing the health assessment index of the engine under each operating condition into a health assessment curve under a time series condition based on the rearrangement of the flight cycle; traversing the assessment under all fault modes to form a health assessment result under each fault mode.

[0169] In the engine health assessment under multiple fault modes and variable operating conditions, the present invention proposes a new autoencoder feature extraction method, introduces the metric learning method into health assessment, adopts the neighbor component analysis (NCA) algorithm, measures the difference between the degradation characteristics and the initial health characteristics under different operating conditions through neighbor category division and Mahalanobis distance transformation, and then uses the operating condition transformation idea to obtain the health assessment value under variable operating conditions, thereby completing the degradation trend characterization of individual engines.

[0170] 2.1 Introduction to the Principle of NCA Algorithm

[0171] The KNN method is a supervised nonparametric machine learning method that selects the K nearest neighbors of a sample and classifies the sample into the class that appears most frequently among the neighbors. Assume that the input sample is {x 1 ,x 2 ,…,x n}, and its corresponding category label is c 1 ,c 2 ,…,c n For the sample labels to be learned, we need to find a distance measure that optimizes the nearest neighbor classification. For the Mahalanobis distance that can be learned in metric learning, its transformation matrix Q = A T A is a symmetric semi-positive definite matrix, then the Mahalanobis distance between two samples can be expressed as:

[0172]

[0173] Among them, the semi-positive matrix Q is a learnable parameter, called a metric. The goal of metric learning is to optimize the matrix Q through some constraints to learn a distance metric. When calculating the classification error by the leave-one-out method, a differentiable softmax function is introduced because the error function is not continuous. Therefore, the nearest neighbor distribution of the sample is defined as:

[0174]

[0175] Among them, p ij Represents data point x i In the random neighbor, choose another data point x instead j The probability of the corresponding category. The probability of the sample point selecting the correct classification is:

[0176]

[0177] The objective function of optimization is to maximize the number of correctly classified points, so the optimization objective can be expressed as:

[0178]

[0179] 2.2 Engine timing degradation feature extraction based on LSTMCNN_AE

[0180] The present invention proposes a new autoencoder feature extraction method, namely, long short-term memory convolutional autoencoder (LSTMCNN_AE), which is used to generate low-dimensional and low-noise engine time series feature information, providing a data basis for variable operating condition engine health assessment.

[0181] 21) Construction of LSTMCNN_AE feature extraction network structure

[0182] In order to construct a feature extraction model for aircraft engines with time series and high noise, the present invention proposes a feature extraction method based on the LSTMCNN_AE algorithm, whose network structure is as follows: Figure 8 As shown in the figure, LSTM and convolution units are embedded in this specific network to capture sequence information while reducing feature dimensionality and learning engine degradation features. The LSTM unit in LSTMCNN_AE is used to capture sequence information from multi-sensor time series data. Convolution and deconvolution units are further embedded after the LSTM unit to filter noise and extract features corresponding to engine degradation. Afterwards, residual learning is used to reduce the difficulty of training and improve the feature learning performance of LSTMCNN_AE.

[0183] LSTMCNN_AE consists of two parts: encoder and decoder, the details of which are as follows Fig. 9As shown. Taking the multi-dimensional decay-sensitive gas path parameters after the working condition transformation as input, the encoder composed of LSTM and convolution units is used to encode the time series input and extract effective features from the original signal. The decoder composed of LSTM and deconvolution units is used to decode the learned features and reconstruct the input data. LSTMCNN_AE mainly includes the following unit modules:

[0184] (21) LSTM encoding unit

[0185] The LSTM unit in the encoder is used to learn the temporal information from the input signal. LSTM consists of three gating units, namely the input gate, the forget gate, and the output gate. The special architecture of LSTM ensures that the model can avoid the gradient vanishing problem and accurately capture the long-term correlation of temporal information.

[0186] In LSTM, for each time point t, the update process of the hidden state ht can be described as follows:

[0187] i t =σ(W i x t +V i h t-1 +b i )

[0188] f t =σ(W f x t +V f h t-1 +b f )

[0189] O t =σ(W o x t +V o h t-1 +b o )

[0190] c t =f t ⊙c t-1 +i t ⊙tanh(W c x t +W c h t-1 +b c )

[0191] h t =o t ⊙tanh(c t ) (16)

[0192] Among them, i t , f t , Ot , c t They are the input gate, forget gate, output gate and storage unit, W and V are weight matrices, b is the bias vector, σ is the activation function, and ⊙ represents the convolution unit.

[0193] (22) Convolutional layer

[0194] The feature h generated by LSTM is still noisy and high-dimensional, and cannot effectively represent the engine health status. Therefore, the output h is input to the convolutional layer for further dimensionality reduction and feature learning. The feature F learned by the convolutional layer is as follows:

[0195]

[0196] Where * represents the convolution operation, w is the convolution kernel, b is the bias, and j is the number of channels.

[0197] (23) Deconvolution layer

[0198] The learned features are then passed to the decoder for further decoding. The decoder part consists of LSTM units and deconvolution layers to generate the reconstruction vector As shown in the figure, the deconvolution operation can transform the features into the original shape. The deconvolution operation is the opposite of the convolution operation:

[0199]

[0200] in, represents the deconvolution operation, is the deconvolution kernel, is the deviation, and i is the number of channels.

[0201] (24) LSTM decoding unit

[0202] LSTM units in the decoder are used to capture temporal information from the features generated by the previous layer. Output of the deconvolution layer Input to the LSTM decoding unit. The output of the LSTM can be calculated as follows:

[0203]

[0204] (25) Residual Learning Block

[0205] Residual networks are usually used to solve the problem that the training gradient disappears as the network deepens. Using residual learning can improve the feature learning performance of LSTMCNN_AE. The output of the residual learning block can be expressed as follows:

[0206]

[0207] (26) Fully connected layer

[0208] In order to ensure that the input data has the same shape, the fully connected layer is set on the top layer of LSTMCNN_AE. The final output of the deep network can be obtained by the following formula:

[0209]

[0210] 22) Engine timing degradation feature extraction process based on LSTMCNN_AE

[0211] The feature extraction based on LSTMCNN_AE is divided into offline LSTMCNN_AE modeling and online degradation feature extraction.

[0212] In offline LSTMCNN_AE modeling, the training engine gas path parameters are used to train the model. When the degradation data is input into the model, the gas path parameter data of the original training engine is reconstructed by setting the model structure and adjusting the parameters. Assuming that the multidimensional time series Contains all the data of training unit i from the beginning to failure, then use X i To train the model, the reconstruction error can be expressed as The optimal model is trained by minimizing the reconstruction error.

[0213] In the online degradation feature extraction, all the data of the training engine and all the data of the test engine are used as input. At this time, the model input is The output is The corresponding degradation features are the reconstructed features learned by the LSTMCNN_AE encoder. That is, extracting the engine timing degradation characteristics.

[0214] The engine timing degradation feature extraction process based on LSMTCNN_AE is as follows Fig.10 As shown, including:

[0215] (221) Offline LSTMCNN_AE modeling

[0216] The offline LSTMCNN_AE modeling phase consists of three parts:

[0217] 201. Determine the training set and test set of the model. The gas path data of the training engine is selected as the training set of the model, and all the data of the training engine and the test engine are selected as the test set. Considering that the aerospace engine data has a strong time series, the sliding window method is used to preprocess the multidimensional gas path parameters.

[0218] In data preprocessing, the sliding window is L and the step size is d, sliding along the multidimensional gas path parameters to generate model input data. The sample generation process is as follows: Fig.11 shown.

[0219] The preprocessed model training set is The length of the two-dimensional gas path parameter data is L×K (sliding window length×number of gas path parameters). The model test set is X test ={X trian_all ,X test_all},in, They respectively represent the two-dimensional gas path parameter data of all training engines and test engines obtained by sliding window method.

[0220] 202. Determine the input and output of the model. When training the model, the input and output sequences are the same, both of which are training set data X train , reconstruct the input sequence through the LSTMCNN_AE model.

[0221] 203. Train the LSTMCNN_AE feature extraction model. Capture feature information based on the training data set, determine the model parameters such as the number of model layers, number of nodes, learning rate, batch size, number of iterations, and optimize the model parameters through the residual learning method to obtain the optimal feature extraction model.

[0222] (222) Online degradation feature extraction

[0223] Determine the input for feature extraction. When obtaining degradation features, the input is the test set data X test ={X trian_all ,X test_all}, thereby obtaining low-dimensional degraded features through the constructed encoder.

[0224] Extract engine degradation features. Input the test set data into the trained LSTMCNN_AE model to obtain the low-dimensional data output by the encoder, which is the extracted low-dimensional degradation features. Establish a data foundation for subsequent health assessments.

[0225] 2.3 Engine health assessment under multiple fault modes and variable operating conditions based on NCA algorithm

[0226] The present invention uses the NCA algorithm to divide the health and fault states of the training and test engines, and constructs a health assessment model for each operating condition based on the idea of ​​operating condition transformation, measures the differences between health and degradation under each operating condition, and constructs a health index through a distance value. The health index can reflect the health status of the engine sample under the flight cycle. Afterwards, the health index is reconstructed based on the flight cycle as the transformation benchmark. Therefore, the steps of engine health assessment under multiple fault modes and variable operating conditions are divided into: division and mapping of health and degradation sets based on the NCA model, construction of health indicators for each operating condition based on the optimization matrix, and fusion of variable operating condition health states based on operating condition transformation. The specific process is as follows: Fig.12 shown.

[0227] The pseudo code of variable operating condition engine health assessment based on NCA algorithm is as follows:

[0228]

[0229] The variable operating condition health assessment process based on NCA metric learning is mainly divided into three parts, which will be introduced in turn below.

[0230] 201) Partitioning and mapping of healthy and degraded sets based on NCA model

[0231] According to the identified engine failure mode labels, the extracted time series features are divided into features under different failure modes Each fault mode corresponds to an NCA metric learning model. The following takes the construction of the NCA metric learning model under the i-th fault mode as an example to illustrate.

[0232] Under the i-th fault mode, the NCA metric learning model is supervisedly trained with the healthy set and the degraded set of the training engine degradation characteristics. Then the test engine degradation characteristics are used as the input of the NCA algorithm to divide the test samples into the healthy set and the degraded set.

[0233] (2011) Healthy set and degraded set state label setting

[0234] In the actual operation of the engine, its life does not decrease linearly with the degradation process, but after running for a period of time and reaching the life limit, the remaining life gradually decreases. Therefore, it can be considered that the initial degradation of the engine can be ignored, the remaining life is a constant value, and the remaining life decreases linearly after reaching the critical value.

[0235] The healthy set and the degraded set are divided according to the degradation characteristics of the training engine. According to the piecewise linear degradation principle, the healthy state characteristics of the training engine are regarded as the original input of the healthy set of the NCA model, and the engine degradation state characteristics are regarded as the original input of the degradation set, and the healthy and fault labels are used as the model output. The degradation characteristics of the training engine can be expressed as X train ={X 1 ,X 2 ,...X n_train}, where X n =X ij , i is the engine flight cycle, j is the degraded feature dimension. The first 10% of the engine features are taken as the healthy set, and the last 90% of the features are taken as the degraded set. Then the healthy set H train and degenerate set D train It can be expressed as:

[0236] H train ={H 1 ,H 2 ,...H n_H} (twenty two)

[0237] D train ={D 1 ,D 2 ,...D n_D}(twenty three)

[0238] Among them, H train is the health characteristic corresponding to each flight cycle, D train is the fault feature corresponding to each flight cycle, H i and D i is the dimension reduction feature after LSTMCNN_AE processing,

[0239] Based on the division of healthy set and degraded set, the labels are set. The state label can be expressed as in is the status label corresponding to the health status, is the state label corresponding to the degradation state, and each engine degradation feature corresponds to a state label. Therefore, the state labels corresponding to the healthy set and the degradation set can be expressed as:

[0240]

[0241] (2012) NCA metric learning model training

[0242] In the training of NCA metric learning model, the core is to enable the model to effectively separate the healthy and degraded state features of the engine through training, and obtain a well-learned Mahalanobis distance matrix, so that the healthy and degraded features are sufficiently separated and the same features are relatively aggregated, and lay a stable and efficient foundation for subsequent distance calculation. input ={H train ,D train} as model input, the state label corresponding to the feature As the model output, by setting the maximum number of model iterations max_iter and optimizing the NCA algorithm parameter random_state, the healthy and degraded states of the engine are effectively divided and identified, and the learned optimized Mahalanobis distance matrix Q is obtained.

[0243] (2013) Adaptive mapping of engine degradation characteristics

[0244] In the adaptive mapping of degradation features, the core is to adaptively map the input features to a new space that matches the feature state according to the NCA metric learning model, thereby reducing the aliasing of health and fault features caused by data fluctuations or operating condition changes, making the metric calculation between health and degradation more stable and robust, and the distance representation more accurate. train={X 1 ,X 2 ,...X n_train} and test engine x test ={x 1 ,x 2 ,...x n_test} features for feature mapping, the one-dimensional mapping features of the engine can be expressed as:

[0245] F train ={F 1 ,F 2 ,...F n_train}(26)

[0246] f test ={f 1 ,f 2 ,...f n_test}(27)

[0247] Among them, each engine mapping feature can be expressed as a set of healthy mapping features and degraded feature mappings F 1 ={H train1 ,D train1}, f 1 ={H test1 ,D test1}.

[0248] 202) Construction of health indicators for different working conditions based on optimization matrix

[0249] The core of the construction of working condition health index is to divide the mapping features based on the operating conditions, and construct a health assessment scheme under different working conditions to describe the degree of degradation of the engine under this flight cycle. Unlike the traditional distance measurement method, the traditional distance measurement requires manual setting of the measurement data and measurement length each time, and there are differences in different measurement spaces. The method based on NCA metric learning can use the learned optimal distance matrix for universal measurement, reduce the uncertainty of the measurement method and improve its robustness.

[0250] (2021) Design of measurement scheme for different working conditions

[0251] Considering that all engines are initially in a healthy state, but there may be slight differences between them, the method of measuring the distance between the degraded set and the healthy set consisting of all engines has poor stability and is not suitable for aircraft engines with individual differences. Therefore, the measurement based on individual engines is adopted. The difference between the degraded state and the healthy state is measured based on the covariance matrix of learning under the same working condition, and the engine health status index value (Confidence Value, CV) under different working conditions is constructed. The larger the distance value, the higher the degree of degradation, thereby characterizing the health status of the engine under this working condition.

[0252] (2022) Construction of health indicators for different working conditions

[0253] Taking the i-th test engine as an example, its mapping feature can be expressed as f i ={H i ,D i}, according to the working condition labels obtained in the previous section, the mapping features are divided into healthy and degraded features under different working conditions, which can be expressed as:

[0254]

[0255] Where k is the number of operating conditions, and are the healthy mapping characteristics and the degraded mapping characteristics under the engine operating condition m.

[0256] Under each operating condition, the distance d between the fault state feature and the first healthy state feature is calculated based on the covariance matrix Q obtained by optimization learning. The calculation formula is as follows:

[0257]

[0258] The calculated distance set under the mth working condition is shown in the following formula. This distance can characterize the difference between the current state and the healthy state of the engine under this working condition:

[0259]

[0260] (2023) Construction of health assessment index based on normalized distance of different working conditions

[0261] In order to unify the health indicators into a consistent health assessment indicator measurement, the calculated distance differences need to be normalized. In constructing health indicators, CV = 0 usually represents a healthy state, and CV = 1 represents a complete failure state. Since the calculation standards for each operating condition are different, each operating condition is independently standardized. The linear normalization method meets the unified standard of 0-1, so the linear normalization method is selected to normalize the distance of each operating condition to obtain the engine health assessment index. Under the mth (1≤m≤k) operating condition, the maximum distance value among all engine samples is The minimum distance value is Under this condition, the standard distance value is calculated as shown in the following formula:

[0262]

[0263] Among them, CV m is the normalized health assessment index under working condition m, d m is the distance value under working condition m.

[0264] 203) Fusion of health status based on operating condition transformation

[0265] After obtaining the health indicators of each operating condition, with the help of operating condition transformation thinking, we carried out research on the generation of health indicators based on the flight cycle as the standard, so as to obtain the health status assessment curve of each engine.

[0266] (2031) Reconstruction of health indicators under variable working conditions

[0267] After constructing the health indicators for each working condition, the health evaluation indicator set for the training engine and the test engine under each working condition can be obtained. Formula (33) is the set of health indicators for the test engine i under each working condition:

[0268]

[0269] Based on the idea of ​​operating condition transformation, the CV indicators are rearranged based on the flight cycle to reconstruct the health assessment curve of the engine under timing conditions. This curve can quantitatively reflect the changes in the health degradation of the engine from a specific numerical value, and lay a data foundation for the subsequent remaining life prediction under multiple fault modes.

[0270] (2032) Generation of health assessment results under multiple failure modes and variable operating conditions

[0271] Traverse the evaluation under all failure modes to form the health evaluation results under each failure mode. and test engines Generate a set of variable condition health assessments under multiple fault modes:

[0272]

[0273] (2033) Evaluation of health assessment results

[0274] This paper proposes two evaluation indicators to quantify the results of the health assessment method, and compares the proposed method with other mainstream health assessment methods to prove the effectiveness of the health assessment method proposed in this paper.

[0275] CV curve trend indicator Trend

[0276] The CV degradation curve generally shows a monotonic trend, which can characterize the engine degradation trend. For training engines, if the degradation trend is obvious, it is consistent with the operation of the training engine from healthy to completely failed. This paper proposes the Trend index to quantify the degradation trend of the CV curve, which is the sum of the increase or decrease of the CV value in each flight cycle. The larger the index, the more obvious the degradation trend. The specific calculation formula is as follows:

[0277]

[0278] in, is the health index of the jth engine in the ith flight cycle under fault mode m, len is the running time of the engine, n m is the number of engines under fault mode m, k is the number of fault modes, and n is the total number of engines.

[0279] CV curve volatility indicator Fluc

[0280] The CV degradation curve is relatively smooth and has low volatility, which indicates that the health assessment process is relatively stable and the selected method is appropriate. This paper proposes the Fluc index to quantify the volatility of the CV curve, which is the sum of the absolute values ​​of the original CV value of each engine and the smoothed CV value. The smaller the index, the smaller the volatility of the CV curve. The specific calculation formula is as follows:

[0281]

[0282] in, and are the original calculated health index and smoothed health index of the jth engine in the ith flight cycle under fault mode m, len is the running time of the engine, n m is the number of engines under fault mode m, k is the number of fault modes, and n is the total number of engines.

[0283] 3. Multi-failure mode engine life prediction based on metric learning and domain generalization

[0284] After determining the health status trend of the engine under variable working conditions, it is necessary to establish a suitable life prediction model under multiple fault modes based on this. In the present invention, a combination strategy of the classic deep metric learning Siamese network and the recurrent neural network GRU is selected to perform life prediction based on the engine health assessment results obtained above under different fault modes.

[0285] A method for predicting the life of an engine with multiple fault modes comprises: obtaining health assessment timing curves of a training engine under different fault modes, and selecting the health assessment timing curves of the training engine under two fault modes; constructing an SN-GRU model consisting of two Siamese networks and one GRU network, and training the SN-GRU model using the health assessment timing curves of the training engine under the two fault modes to obtain a trained SN-GRU model; and performing life prediction processing on a test engine based on the trained SN-GRU model.

[0286] The SN-GRU model is trained using the health assessment timing curves of the training engine under the two fault modes to obtain a trained SN-GRU model, including: obtaining health indicator samples under the first fault mode and health indicator samples under the second fault mode by respectively performing sliding window cutting processing on the health assessment timing curves of the training engine under the two fault modes; obtaining the remaining life corresponding to the health indicator samples under the first fault mode and the remaining life corresponding to the health indicator samples under the second fault mode; in each round of iteration, the health indicator samples under the first fault mode and the health indicator samples under the second fault mode are respectively used as inputs of the Siamese network, and the remaining life corresponding to the health indicator samples under the first fault mode and the remaining life corresponding to the health indicator samples under the second fault mode are used as outputs of the GRU prediction network, and the hyperparameters of the Siamese network and the GRU prediction network are updated by the gradient descent algorithm to obtain a trained SN-GRU model.

[0287] The life prediction process of the test engine based on the trained SN-GRU model includes: obtaining health indicator samples of the test engine under k failure modes The health indicator samples are predicted by the Siamese network and the GRU prediction network in the trained SN-GRU model. After processing, the direct predicted RUL of the test engine is obtained; the formula is:

[0288]

[0289] in, is the RUL directly estimated based on the SN-GRU model, G is the Siamese network in the SN-GRU model, and P is the GRU prediction network in the SN-GRU model.

[0290] The life prediction process of the test engine based on the trained SN-GRU model further includes: obtaining health indicator samples of the test engine under k failure modes The second health indicator sample and its corresponding remaining life span (CV j ,RUL j ); Based on the trained SN-GRU model, according to the difference between the health indicator sample and the second health indicator sample in the Siamese network, an indirect predicted RUL of the test engine is obtained.

[0291] The life prediction processing of the test engine based on the trained SN-GRU model further includes: calculating the predicted RUL of each test engine and its last flight cycle cycle k Add them together to get the predicted life L of the engine tested under k failure modesk , the formula is:

[0292] L k =RUL k +cycle k

[0293] Siamese neural network is a classic method in deep metric learning. Siamese network consists of two embedded networks with shared weights, such as Fig.13 As shown. Among them, for the input sample (X i , X j ), train the Siamese network by minimizing the contrastive loss function:

[0294]

[0295] Among them, if the sample pair (X i , X j ) belong to the same category and have a value of 0, then Y ij is a label with value 1; otherwise And α is the minimum margin between pairs of samples of different categories.

[0296] The present invention focuses on the distance measurement capability of Siamese network, embeds the Siamese network structure into the RUL prediction model, applies the Siamese network to learn the differences between health indicators, and inputs the GRU network to perform mapping learning between indicator differences and RUL differences.

[0297] SN-GRU Remaining Life Prediction Model under Multiple Fault Modes

[0298] 31) Construction of SN-GRU multi-fault mode remaining life prediction model

[0299] (31) SN-GRU model and training target design

[0300] When it comes to life prediction, the usual practice is to first perform RUL prediction and then calculate the life of the equipment based on the RUL. Therefore, the SN-GRU model is constructed based on the engine health assessment results under the above-mentioned aircraft engine variable operating condition multi-fault mode and the corresponding RUL. The structure of the network model is as follows: Fig.14 shown.

[0301] The SN-GRU model adopts a structure in which Siamese and GRU networks are connected. The Siamese network is a time series health indicator measurement network, and the GRU network is a RUL prediction network. Among them, G and P are the mapping functions of the Siamese embedding network and the prediction network, respectively. By introducing a multi-task learning scheme, the training of the SN-GRU model has two main purposes: first, by inputting the degradation curve CV of different time periods into the Siamese network, the network can effectively calculate and learn their differences; second, the degradation curve and its difference can be mapped to its RUL and RUL difference through the GRU prediction network, so that its mapping relationship can be learned from the network and the difference problem of inconsistent health indicator degradation caused by different failure modes can be reduced.

[0302] According to the network settings, θ G ,θ P are the network hyperparameters of G and P respectively. The first training goal of the proposed network is to minimize the individual prediction loss, namely:

[0303]

[0304] Here, two networks are trained simultaneously to learn the health indicator CV i and remaining useful life RUL i The mapping relationship between them.

[0305] At the same time, the SN-GRU model is able to learn the nonlinear relationship between health indicator differences and RUL differences, namely:

[0306] P(z i -z j )=RUL i -RUL j (40)

[0307] Therefore, by learning the differences between the health assessment indicators corresponding to RUL, the differences between RULs can be further estimated, thereby reducing the differences in CV curves caused by multiple failure modes and improving the generalization ability of the prediction model. i ,CV j ) and RUL to (RUL i ,RUL j ), the SN-GRU is trained by optimizing the loss function of formula (41) to satisfy the condition in formula (40). The regularization term helps prevent overfitting. By combining the loss functions of formula (39) and formula (41), the overall training objective shown in formula (42) is obtained, where ω is a balancing parameter.

[0308]

[0309] (32) SN-GRU network structure design

[0310] The SN-GRU network consists of two shared embedding networks and a life prediction network. For the embedding network, the CNN architecture is used, which can perform better than other architectures for the RUL prediction task within a reasonable training time. In the CNN architecture, 1-D convolution is used to process the health assessment sequence, through 2 convolutional layers, 1 flat layer and 1 fully connected layer, and the corresponding dimensions and convolution kernels are designed. In the GRU prediction network, 1 GRU layer, 2 dropout layers and 2 fully connected layers are designed. Fig.15 Design diagram of SN-GRU network structure.

[0311] 32) Life prediction process under multiple fault modes based on SN-GRU model

[0312] The present invention introduces Siamese network into RUL prediction problem, establishes SN-GRU prediction model, and constructs engine RUL prediction model suitable for multiple fault modes by designing the corresponding relationship of "distribution difference-remaining life difference". The life prediction process of engine under multiple fault modes based on SN-GRU is as follows Fig.16 shown.

[0313] The pseudo code for model training of engine life prediction under multiple fault modes based on SN-GRU is as follows:

[0314]

[0315] By designing the corresponding relationship between "distribution difference-remaining life difference", learning the nonlinear relationship between the time series distribution difference and the remaining life difference between the health assessment indicators, and reducing the gap between multiple fault modes through "difference" learning, the prediction model is applicable to multiple fault mode situations. The model training steps for engine life prediction under multiple fault modes based on SN-GRU mainly include three parts:

[0316] (301) Input design of SN-GRU life prediction model under multiple fault modes

[0317] The engine CV results obtained under different fault modes are used as the input of the SN-GRU model. Since the trained SN-GRU model is applicable to multiple fault modes, the CV indicators under all fault modes are used as the input of the model training.

[0318] The present invention selects X in the training engine health index sequence 1 =X 2 ={1,2,...,|CV|}, and use sliding window random sampling and As the input of training in each iteration, the shared knowledge under the time series is maximized. After quantifying the similarity of the sequence, if the prediction model can map the CV data under random sampling to the corresponding RUL, the generalization ability of the prediction model will be stronger.

[0319] (302) Output design of SN-GRU life prediction model under multiple fault modes

[0320] The current RUL value is calculated based on the flight cycle of the training engine, and the corresponding RUL is obtained based on the set prediction model input sample, which are respectively and Then, the mapping relationship between CV sequence and sequence difference and RUL sequence and RUL difference can be learned by training the SN-GRU model.

[0321] (303) SN-GRU model training

[0322] In each iteration, and As the input of the Siamese network, its corresponding and As the output of the GRU prediction network. After that, through the gradient descent algorithm, and according to the loss function designed in the previous stage Update hyperparameter θ G ,θ P , and obtain the trained SN-GRU model, which has strong generalization ability and can handle the life prediction problem under failure mode.

[0323] 33) Comprehensive lifespan estimation method based on SN-GRU

[0324] The present invention designs a life estimation method combining "direct + indirect", which can combine all training samples for estimation, thereby achieving robust and accurate prediction of engine life and improving the generalization of the prediction model under multiple fault modes.

[0325] For a given test engine health indicator Two RUL prediction methods are proposed.

[0326] (331) Direct RUL estimation

[0327] The input health indicators are processed through the embedding network and GRU prediction network in Siamese to directly predict the RUL, as shown in the following formula:

[0328]

[0329] Will Defined as model-based RUL, F and G are the embedding network and prediction network in SN-GRU, respectively.

[0330] (332) Indirect RUL estimation

[0331] In addition to direct estimation, the RUL of the test engine can also be inferred based on the difference between the test sample and other samples in the Siamese network. According to the SN-GRU prediction model structure, if (CV j ,RUL j ) and CV i , then RUL can be calculated j +P(G(CV i )-G(CV j )) to estimate RUL i Here, (CV j ,RUL j ) is considered as the estimated CV i To increase the accuracy of the RUL prediction of the test set, as many estimates as the number of available training samples for each test sample can be obtained and combined to produce an ensemble effect that reduces the variance of the estimates. The indirect RUL estimation formula based on the reference is as follows:

[0332]

[0333] Among them, is defined as the indirectly estimated RUL, and |D| is the total number of estimated references.

[0334] After completing the direct and indirect RUL estimation, the estimated data is fused to obtain the final RUL prediction result. The fusion is shown in the following formula:

[0335]

[0336] Among them, α and β are fusion parameters respectively.

[0337] Finally, the predicted RUL of each test engine and its final flight cycle are added together to obtain the final predicted life of the test engine. The calculation formula is as follows:

[0338] L k =RUL k +cycle k (46)

[0339] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the present invention is not limited thereby. Any modification, equivalent substitution and improvement made by those skilled in the art without departing from the scope and essence of the present invention shall be within the scope of the present invention.

Claims

1. A method for identifying engine group fault patterns based on density clustering-support vector machine and multi-time prediction weighting, characterized in that: include: Based on principal component analysis PCA, the training engine performance parameters and the test engine performance parameters are respectively reduced in dimension to obtain the training engine low-dimensional performance parameters and the test engine low-dimensional performance parameters; In predicting the single-moment fault mode of the engine, the low-dimensional performance parameters of the training engine are clustered based on the density clustering DBSCAN algorithm to obtain the fault mode classification label corresponding to each training engine; Establishing a single-moment fault mode classification model based on a support vector machine (SVM), and training the single-moment fault mode classification model based on SVM using the low-dimensional performance parameters of the training engine and the fault mode classification labels corresponding to each training engine, to obtain a trained single-moment fault mode classification model based on SVM; By inputting the low-dimensional performance parameters of the test engine into the trained SVM-based single-moment failure mode classification model, a single-moment failure mode classification label of each test engine is obtained; Based on the multi-moment fault mode weighted prediction and the single-moment fault mode classification label of each test engine, a final fault mode classification label of each test engine is obtained.

2. The method according to claim 1, characterized in that The method of obtaining the final failure mode classification label of each test engine based on the weighted prediction of the multi-time failure mode and the single-time failure mode classification label of each test engine comprises: According to the trained SVM-based single-moment fault mode classification model, the prediction results of each test engine under the fault mode at a single moment are obtained; The weighted prediction is performed using the fault state of each test engine at a single moment and the comprehensive fault state at multiple moments to obtain the weighted prediction results of each test engine under different fault modes; The weighted prediction results of each test engine under different failure modes are used to obtain a final failure mode classification label of each test engine.

3. The method according to claim 2, characterized in that According to the trained SVM-based single-moment fault mode classification model, the prediction results of each test engine under the fault mode at a single moment are obtained, including: 。 4. The method according to claim 3, characterized in that The weighted prediction results of each test engine under different fault modes obtained by using the fault state of each test engine at a single moment and the comprehensive fault state at multiple moments include: ； Wherein, m represents the failure mode; j represents the test engine; Indicates the recent weighting coefficient of the recognition proportion of recent data; λ indicates the comprehensive weighting coefficient of the number of flight cycles considered comprehensively; k indicates the value coefficient affecting the weight of the recent and long-term, indicating the flight cycle at the most recent moment; represents the predicted state of the test engine j under fault mode m at the time farthest from t; represents the predicted state of the test engine j under fault mode m at time tk, It represents the prediction result of engine j under fault mode m obtained by weighted prediction.

5. The method according to claim 4, characterized in that The method of using the weighted prediction results of each test engine under different failure modes to obtain the final failure mode classification label of each test engine includes: ； in, represents the final failure mode classification label of test engine j.

6. The method according to claim 1, characterized in that Before the dimension reduction processing of the training engine performance parameters and the test engine performance parameters is performed based on the principal component analysis PCA, it also includes: Screen out the performance parameters of the engine that are sensitive to decay under variable operating conditions; Based on the results of the individual engine operating condition classification, the engine data under different operating conditions are extracted to obtain the degradation sensitivity performance parameters under each operating condition; The normalization method is used to normalize the decay sensitivity performance parameters under each working condition, and the normalized decay sensitivity performance parameters under each working condition are reconstructed according to the flight cycle sequence of the engine to obtain the decay sensitivity performance parameters under multiple working conditions. The degradation-sensitive performance parameters under the fusion of multiple working conditions are divided into training engine performance parameters and test engine performance parameters.

7. The method according to claim 6, characterized in that The performance parameters that are sensitive to engine degradation under variable operating conditions include: Obtain multi-dimensional operating parameters of the training engine under different working conditions; Based on the obtained multi-dimensional operating parameters, the K-Means clustering algorithm is used to preliminarily identify the operating condition category of the training engine and obtain the cluster center of each operating condition; The multidimensional operating parameters of the test engine and the cluster centers of the corresponding working conditions are scaled to one dimension using the multidimensional scaling analysis (MDS) algorithm, and the cluster center of the one-dimensional working condition is used as the working condition baseline. Based on the principle of being closest to the operating condition baseline, the operating condition corresponding to each test engine in each flight cycle is adaptively identified.

8. The method according to claim 6, characterized in that Based on the principle of being closest to the operating condition baseline, the operating conditions corresponding to each test engine in each flight cycle are adaptively identified, including: By measuring the distance between the operating parameters of the test engine at a single moment and the baseline of each working condition, the working condition with the closest distance is selected as the operating condition of the test engine.

9. An engine group fault pattern recognition device based on density clustering-support vector machine and multi-time prediction weighting, characterized in that: include: A parameter dimension reduction module is used to perform dimension reduction processing on the training engine performance parameters and the test engine performance parameters based on principal component analysis PCA to obtain low-dimensional performance parameters of the training engine and low-dimensional performance parameters of the test engine; A fault mode classification module is used to perform fault mode clustering processing on the low-dimensional performance parameters of the training engine based on the density clustering DBSCAN algorithm in predicting the single-moment fault mode of the engine, and obtain a fault mode classification label corresponding to each training engine; A model training module, used to establish a single-moment fault mode classification model based on a support vector machine (SVM), and train the single-moment fault mode classification model based on the SVM using the low-dimensional performance parameters of the training engine and the fault mode classification labels corresponding to each training engine, to obtain a trained single-moment fault mode classification model based on the SVM; A fault mode recognition module is used to obtain a single-moment fault mode classification label of each test engine by inputting the low-dimensional performance parameters of the test engine into the trained SVM-based single-moment fault mode classification model; Based on the multi-moment fault mode weighted prediction and the single-moment fault mode classification label of each test engine, a final fault mode classification label of each test engine is obtained.

10. An electronic device, characterized in that: It comprises a memory, a processor and a computer program stored in the memory and executable on the processor; when the computer program is executed by the processor, the steps of the engine group fault pattern recognition method based on density clustering-support vector machine and multi-moment prediction weighting described in any one of claims 1 to 8 are implemented.

Images