157 results about "Kernel principal component analysis" patented technology

The present disclosure provides a fuel cell fault diagnosis method and system. The method includes: determining key parameters for temporal feature and spatial feature extractions according to the amount of information contained in all sensor parameters in a fuel cell to be diagnosed; obtaining a target intrinsic mode function by performing complementary ensemble empirical mode decomposition on a temporal feature matrix; obtaining a high-dimensional mapping vector by processing spatial feature data using a kernel principal component analysis; and obtaining a spatial feature to be synchronized by processing the high-dimensional mapping vector according to a preset confidence interval, obtaining a temporal feature to be synchronized by processing a target decomposition result according to a lumped fuzzy entropy operation, fusing the spatial feature to be synchronized and the temporal feature to be synchronized, and obtaining a fault diagnosis result by inputting a synchronous spatial-temporal feature into a preset diagnosis model.

The invention provides a lightning protection system effectiveness evaluation method and system based on multi-dimensional research and judgment, and relates to the technical field of lightning protection, and the method comprises the steps: collecting system index data through a bidirectional feature extraction network, employing a separable convolution layer with an attention mechanism and multi-scale Fourier transform to extract features, and carrying out the analysis of the features; an index transfer function is constructed in combination with a causal reasoning network, evaluation grade division is performed by adopting kernel principal component analysis and density clustering, and system parameters are optimized through a hierarchical reinforcement learning framework, so that accurate evaluation and dynamic optimization of the state of the lightning protection system can be realized, and the reliability and the protection effect of the system are improved.

A method, system, and readable storage medium for fault line selection in distribution networks is provided. The method includes: obtaining the zero-sequence current of each feeder and the zero-sequence voltage of the busbar within a preset time window after a fault occurs; using these to process the feeder's short-time window zero-sequence instantaneous power curve cluster in the distribution network through KPCA (Kernel Principal Component Analysis) for dimensionality reduction, determining the principal component scores; and performing BIRCH (Balanced Iterative Reducing and Clustering using Hierarchies) clustering based on these scores to identify whether a feeder is faulted. This clustering process allows for precise and rapid identification of the faulted feeder, even when the current is small, improving detection accuracy. This solves the problem of quickly identifying the faulted feeder in a small current grounding distribution network during single-phase grounding faults.

The invention relates to the technical field of ship working condition recognition, in particular to a multi-working-condition recognition method, system and device for an all-electric ship and a medium, and the method comprises the steps: obtaining the historical operation data of the all-electric ship, carrying out the feature extraction and noise reduction, and obtaining a noise reduction data set of each sample; preliminarily clustering the noise-reduced propulsion load and the first-order derivative of the propulsion load into a plurality of basic working conditions, and adding a unique basic working condition label for the noise-reduced data set; judging whether the absolute value of the first-order derivative of the propulsion load of each sample after noise reduction is higher than a preset threshold value or not, summarizing noise reduction data groups corresponding to all samples with positive results into a high-fluctuation data set, and summarizing the propulsion load, the first-order derivative of the propulsion load and the basic working condition labels corresponding to other samples into a general data set; and using a kernel principal component analysis algorithm to extract main features of data in the high-fluctuation data set and the general data set, inputting the main features into the pre-trained working condition subdivision model, and outputting a specific working condition category. The working condition identification precision and real-time performance of the all-electric ship can be improved.

The invention provides a photovoltaic output prediction method and a distributed optical storage transformer area active / reactive support capability optimization method, and belongs to the technical field of power system automation. Comprising the following steps: constructing a prediction model based on meteorological information, extracting multi-scale features of meteorological data, reducing dimensions through kernel principal component analysis, predicting photovoltaic power through a long-short-term memory network, quantifying the uncertainty of the photovoltaic power, and forming a prediction interval. Based on a photovoltaic power prediction result, a robust nonlinear programming model is established, the sum of absolute values of active / reactive power transmitted to a main power grid by a light storage area is maximized as a target, and linear and nonlinear constraints such as energy storage operation, power balance, equipment capacity and power factors are considered at the same time. The robustness under the photovoltaic output uncertainty is ensured through a budget uncertainty set; the model is solved by adopting a sequential quadratic programming algorithm. According to the method, the photovoltaic power prediction precision is effectively improved, and organic combination of high-precision prediction and robust nonlinear optimization is realized.

The invention discloses an elevator fault prediction method and system based on the big data technology, and the method comprises the steps: collecting and preprocessing elevator multi-source data, and generating a standardized data set; performing kernel function mapping and kernel principal component analysis dimensionality reduction to obtain a dimensionality-reduced feature sequence; the sequence is sent into a gating Transform in a segmented mode, and a time sequence modeling result is output; identifying a fault type based on a time sequence modeling result and predicting a future fault probability; the risk threshold is compared, the fault risk is judged, and early warning information is generated; and sending a judgment result and early warning information to an operation and maintenance end to assist in maintenance decision making. According to the method, efficient prediction and intelligent early warning of elevator faults are achieved by fusing kernel principal component analysis and gating Transform, and the operation and maintenance response efficiency and the equipment operation safety are improved.

The invention provides a typhoon rainstorm debris flow susceptibility evaluation method based on an ensemble learning algorithm, and the method comprises the steps: selecting an impact factor for a research region, building an evaluation index system, and obtaining related data according to an index demand; then extracting factor data by using ArcGIS and preprocessing the factor data, screening irrelevant characteristic factors by using a factor correlation analysis method, quantitatively measuring the colinearity among multivariate factors by using a multi-colinearity analysis method and eliminating the correlation among the factors by using a KPCA (Kernel Principal Component Analysis) method; then performing oversampling on debris flow occurrence samples by using an SMOTE algorithm; then optimizing parameters of the CatBoost regression model through an integrated optimization algorithm based on WOA, ISO, CSA and IGA optimization models; k-fold cross validation is carried out through Skleen to evaluate the stability of the model, and an optimal model is identified; and finally, drawing a debris flow susceptibility map by adopting the optimal model, and analyzing the influence of rainfall data in different time ranges on debris flow susceptibility prediction accuracy.

According to the plateau area load prediction method and system based on the signal decomposition and the neural network, an original signal is decomposed into a plurality of intrinsic mode components with physical significance by adopting completely adaptive noise set empirical mode decomposition, mode aliasing is suppressed, and multi-scale features are extracted to effectively suppress load demand oscillation; the problem of non-stationarity of the load of the service area is solved; then, K-means clustering grouping is carried out on the components, similar modes are combined to reduce calculation redundancy, and the problems of heterogeneity and local feature redundancy in complex time series data are effectively solved; performing nonlinear dimension reduction processing on the grouped reconstructed signals by adopting kernel principal component analysis, eliminating noise interference and extracting key features, thereby effectively solving the multiple nonlinear problem; and finally, inputting the dimensionality-reduced features into a long-short-term memory network modeling time sequence dependency relationship, and realizing high-precision prediction through adaptive weighted integration of component prediction results.

The invention relates to the technical field of laser frequency stabilization control, and discloses a multi-mode laser frequency stabilization error feedback correction system driven by machine learning. The system comprises a multi-modal data acquisition module for acquiring various data to generate a multi-modal time sequence data set; the error feature extraction module is used for extracting an error feature tensor by using a kernel principal component analysis algorithm; the dynamic compensation modeling module is used for constructing a support vector regression model to generate a dynamic compensation strategy matrix; and the feedback control optimization module is used for designing a self-adaptive model prediction control framework to generate a closed-loop correction instruction sequence. In addition, a self-adaptive correction execution module, an error traceability analysis module and an abnormal mode recognition model are further arranged. Through multi-modal data acquisition and analysis and intelligent modeling and control, high-precision laser frequency stabilization is realized, the system can effectively adapt to a complex environment, the stability and reliability of the system are improved, and the system has a wide application prospect in the fields of laser processing, optical communication and the like.

The invention discloses a short-term power load prediction method, system and device based on a VAE-BiLSTM hybrid neural network and Bayesian optimization, and a medium. The method comprises the following steps: preprocessing obtained load data related to a power system and feature data influencing a load; performing feature dimension reduction on the processed data by using kernel principal component analysis; performing hyper-parameter optimization on the network structures of the variational auto-encoder and the bidirectional long-short-term memory network by using a Bayesian optimization method; training the dimensionality-reduced data containing the data principal component by using a variational auto-encoder with an optimal hyper-parameter; inputting a coding layer containing data potential representation in the trained variational auto-encoder network structure into the bidirectional long-short-term memory network model with the optimal hyper-parameter for load prediction to obtain a short-term power load prediction result; performing accuracy evaluation on the prediction result; according to the method, reasonable selection of time sequence correlation and hyper-parameters can be fully considered in power load prediction, and the accuracy of power load prediction is improved.

The invention relates to the technical field of metal grinding machining, in particular to a workpiece grinding management method, system and equipment, and the method comprises the following steps: acquiring workpiece information and grinding machining information; a multi-scale management model is established according to the workpiece information and the grinding machining information, and a management threshold value is set in the multi-scale management model; the multi-scale management model obtains a plurality of machining parameters in the grinding machining information according to a set time interval, then the machining parameters serve as initial features, the initial features are fused to obtain management features, through kernel principal component analysis feature fusion and fuzzy control, the abrasion state of the grinding wheel can be dynamically recognized, a nonlinear compensation strategy is generated, and the accuracy of the grinding wheel is improved. Specifically, when principal components extracted through kernel principal component analysis show that the grinding wheel enters an accelerated wear stage, the fuzzy controller can automatically adjust the compensation intensity according to the error change rate, and compensation deviation caused by linear hypothesis in a traditional method is avoided.

The invention relates to the technical field of photovoltaic prediction of a power system, in particular to a photovoltaic power short-term prediction method, device and equipment based on multi-level reverse error correction and a medium, and the method comprises the steps: obtaining original data, and carrying out the data interpolation and data selection; variational mode decomposition is used to decompose the selected data, and kernel principal component analysis is carried out to reduce dimensions; dividing the data after dimension reduction into a plurality of sub-data sets with the same size and a test set as input data, selecting a plurality of training algorithms, constructing a prediction model based on model stacking Stacking, and inputting the input data into the prediction model for training; performing prediction by using the trained prediction model, and evaluating a prediction result; according to the method, historical data or environmental factors are analyzed, photovoltaic stations with similar characteristics or prediction results are clustered, photovoltaic stations of different clusters are predicted according to the clustering results, and a prediction model is subjected to reverse correction.

The invention relates to the technical field of power system fault monitoring, and discloses a measurement switch fault identification and early warning system, which comprises a signal acquisition unit, a feature analysis unit, a fault judgment unit and an early warning trigger unit. The signal acquisition unit acquires a potential fluctuation sequence and an exciting current pulse sequence through a contact voltage sensor and a coil current transformer; the feature analysis unit extracts time-frequency domain and statistical domain feature groups by means of wavelet transform and moment function analysis; the fault judgment unit generates a fault judgment vector by adopting kernel principal component analysis fusion features; and the early warning triggering unit triggers four-level early warning by using dynamically updated grading threshold values (including historical reference values and online dynamic values). According to the system, through multi-modal feature fusion, dynamic threshold adjustment and a grading early warning strategy, accurate identification and grading early warning of measurement switch faults are achieved, the fault identification accuracy and early warning timeliness are improved, and the system is suitable for the field of electric power and industrial automation.

The invention discloses a method and a device for monitoring the running state of a voltage transformer, relates to the technical field of detection, and mainly aims to solve the problem of poor effectiveness of running state monitoring of an existing voltage transformer. Comprising the following steps: acquiring voltage data of a voltage transformer, and performing principal component analysis on the voltage data based on a kernel principal component analysis model which completes model training to obtain an analysis result; determining a fault evaluation standard threshold value through residual space statistics obtained through the analysis result, and determining an abnormal operation state of the voltage transformer when the voltage data is matched with the fault evaluation standard threshold value; and classifying the voltage data of the abnormal operation state to obtain an abnormal voltage phase, and determining the abnormal voltage phase as a monitoring result of the abnormal operation state of the voltage transformer.

The invention discloses a switch cabinet partial discharge fault identification method based on multi-fault information fusion, and the method comprises the steps: building different partial discharge fault models in a switch cabinet, and carrying out the data collection of partial discharge signals generated by different models through a plurality of sensors; dividing the collected multi-fault multi-source signal data into a training set and a test set; carrying out noise reduction processing on the signal data by using an LMS-wavelet transform method; constructing time domain feature parameters for the denoised data, and extracting features by using a sliding window method; performing dimension reduction processing on the features by using a kernel principal component analysis (KPCA) method; and training a PNN model based on the signal features to realize fault identification. According to the method, monitoring information of various sensors is fused, the LMS-wavelet transform method and the KPCA kernel principal component analysis method are introduced at the same time to carry out noise reduction and feature dimension reduction on complex multi-source data, the operation time of fault recognition is greatly shortened, and the efficiency of switch cabinet partial discharge fault detection is improved.

The invention is suitable for the technical field of radar signal processing, and provides a tomographic SAR super-resolution imaging method based on a structured sparse network, and the method comprises the steps: firstly obtaining multi-channel SAR observation data, constructing multi-channel observation vector MMV data in a data domain, and constructing a multi-pixel signal model corresponding to the MMV data based on a neighborhood pixel elevation consistency hypothesis. The method comprises the following steps: designing a kernel principal component analysis KPCA expansion network model, carrying out dimension reduction and enhancement on MMV data, introducing a norm compressed sensing model on the basis of the MMV data after dimension reduction and enhancement, solving the compressed sensing model by using an ADMM iterative algorithm, expanding the ADMM algorithm into a deep network, reconstructing an elevation spectrum, and obtaining an SAR image super-resolution three-dimensional reconstruction result. According to the method, the super-resolution performance and the solving efficiency of three-dimensional reconstruction can be effectively improved, and high-resolution three-dimensional reconstruction of a large-scale scene can be efficiently realized.

The invention provides an automatic steering driving humanoid trajectory planning method and system. The method comprises the following steps: acquiring relative distance information between a vehicle and obstacles on two sides of a road and vehicle kinematics information by acquiring and processing human control data in a curve scene; non-linear features are extracted from the vehicle kinematics information based on a kernel principal component analysis (KPCA) method; the multi-state cycle prediction model is constructed based on an LSTM network, and the method comprises the following steps: carrying out weighted attention on key data of long and short term information by cell state information; the model inputs the nonlinear features, the relative distance information between the vehicle and obstacles on the two sides of the road and the kinematics information of the vehicle into a multi-state cycle prediction model, and predicts future driving track points. Therefore, the mapping precision of the network is improved, human manipulation behaviors are well learned, and the stability of the planned trajectory is improved.

The invention discloses an underwater target image recognition method based on feature selection. The method mainly comprises six steps. Firstly, an original image of an underwater target is obtained, and median filtering is applied for denoising to enhance the edge of the image; then, contrast enhancement and sharpening processing are carried out on the denoised image, and target edge features are optimized in combination with mathematical morphology operation; secondly, extracting color features, texture features and edge features of the image, and performing normalization processing on the color features, the texture features and the edge features; the features are selected and dimensionally reduced through a kernel principal component analysis (KPCA) method. And based on the dimension-reduced features, constructing an artificial neural network for classification by using a multi-layer perceptron (MLP), and optimizing the model through a back propagation algorithm. And finally, the classification result and the performance index of the model are verified through experiments to ensure the effectiveness of the method. According to the method, automatic identification of the underwater target can be realized, and effective technical support is provided for related fields.

The invention discloses a motor train unit dynamic load modeling method based on measured data, which comprises the following steps: acquiring load-related data in the interval operation process of a motor train unit according to a time sequence, preprocessing, extracting load characteristics, and forming a load characteristic sequence by all load characteristics under each time sequence; according to the load extraction method based on data window state discrimination, load state classification is carried out on all the load feature sequences, the load feature sequences in the on-load state are input into a multi-classification SVM based on a kernel principal component analysis method to carry out main load feature recognition, and the recognized main load features are input into a BP neural network. Predicting the load of the motor train unit in the on-load state; and for the load characteristic sequence in the no-load state, constructing the load of the motor train unit in the no-load state by combining the load active power in the no-load state with the no-load loss. According to the method, the dynamic load condition of the motor train unit in the interval operation process is obtained by collecting the actual operation data of the motor train unit.

The invention discloses a fault diagnosis method and system based on improved residual error and GRF feature fusion. The method comprises the following steps: integrating signals of a multi-source sensor; reducing dimensions by using kernel principal component analysis; extracting features in parallel by adopting an improved residual network, an LSTM (Long Short Term Memory) and a Transform; after normalization and projection transformation are carried out on output of each branch, feature weighted fusion is carried out by adopting a dynamic gating weight mechanism, and timing sequence modeling capability is enhanced by utilizing a gating recursion unit; and finally, stage mark embedding and dynamic zooming processing are introduced, and diagnosis results are output through a full connection layer and Softmax classification. According to the method, the global and local information of the time-frequency domain of multiple sensors is fused, and the diagnosis precision of the complex fault of the rolling bearing is remarkably improved.

The invention relates to the technical field of natural disaster risk assessment, in particular to a multi-disaster disaster-inducing factor internal correlation analysis method, which comprises four steps of data preprocessing, Bayesian network correlation model construction, space-time dynamic evolution analysis and risk early warning threshold model construction. And deep coupling analysis of disaster-inducing factors of multiple disasters such as mountain torrent-debris flow and the like is realized. The method comprises the following steps: firstly, collecting 17 disaster-inducing factor data such as terrain and rainfall, performing dimensionality reduction through kernel principal component analysis, and calculating a dynamic weight by adopting an entropy evaluation method; then constructing a Bayesian network model to quantify conditional probability association; introducing a space-time attention mechanism to optimize a multi-scale coupling weight; and finally, establishing a coupling risk early warning threshold value and outputting a relevance intensity matrix. According to the method, the problem that a traditional single-disaster analysis method cannot capture the space-time linkage effect of disaster-inducing factors is solved, the risk early warning accuracy of multiple disasters is improved, and scientific decision support is provided for regional disaster prevention and reduction.

The invention provides a concrete continuous rigid frame bridge temperature-induced deflection prediction and safety early warning method based on health monitoring, which aims at a concrete continuous rigid frame bridge type and extracts specific indexes reflecting structural performance based on mass measured data acquired by a bridge health monitoring system. Extracting section temperature gradient information of the concrete continuous rigid frame bridge through kernel principal component analysis, and performing wavelet decomposition on deflection data to extract temperature-dependent deflection; the structure performance change is reflected through the prediction model of the temperature-induced deflection, the long-term change rule of the bridge structure performance is effectively analyzed, and a bridge temperature-induced deflection index prediction model with a clear physical meaning is constructed; setting a bridge safety early warning threshold value based on the model prediction error, and performing multi-stage early warning on the bridge state by simply adjusting parameters according to the actual operation condition of the bridge structure and the requirements of bridge owners; the function of monitoring bridge health is realized, important guidance is provided for bridge operation management, and the system has a wide application prospect.

The invention relates to the field of artificial intelligence, and discloses a phase modifier operation data analysis fault diagnosis method, device and equipment, and the method comprises the steps: obtaining a historical operation data sample of a phase modifier, constructing the multi-dimensional operation characteristics of the phase modifier based on a non-coding ratio method, and carrying out the dimension reduction of the multi-dimensional operation characteristics through a kernel principal component method, obtaining a first sample data set; generating a new fault feature sample based on the auxiliary confrontation generative network to balance the sample data set and obtain a second sample data set; and training a phase modifier fault diagnosis model based on a least square support vector machine by using the second sample data set, inputting to-be-diagnosed operation data of the phase modifier, extracting multi-dimensional operation features, performing kernel principal component analysis dimension reduction processing, and inputting the trained phase modifier fault diagnosis model to perform fault diagnosis. According to the method, the problems of few fault samples, unbalanced category distribution, high feature dimension and redundancy of the phase modifier are effectively solved, and the accuracy, generalization and real-time performance of fault diagnosis are improved.

The invention belongs to the technical field of electric data processing, and particularly relates to a data processing method for an intelligent mutual inductor to solve the technical problem that in the prior art, the accuracy of an online evaluation result of the operation state of the intelligent mutual inductor is poor, and the method comprises the following steps: S1, obtaining time sequence sampling data of current or voltage output by the intelligent mutual inductor; s2, performing noise reduction on the time sequence sampling data by adopting an unscented Kalman filtering algorithm to obtain first processed data; s3, windowing truncation is carried out on the data after the first processing, and a preliminary frequency spectrum is obtained through fast Fourier transform; s4, determining a spectral line screening threshold, and generating a corrected harmonic feature vector; and S5, performing kernel principal component analysis on the corrected harmonic feature vector, extracting the maximum feature value as nonlinear principal component energy, and taking the geometric mean of all the feature values as a kernel space generalized variance. And the high accuracy of the harmonic and inter-harmonic spectral lines screened from the frequency spectrum in the aspects of frequency and amplitude is ensured.

The invention discloses a photovoltaic power prediction method and system based on improved VMD and Stacking ensemble learning, and a storage medium, and the method comprises the following steps: S1, collecting original meteorological data, and carrying out the preprocessing of interpolation and correlation screening, and obtaining preprocessed data; s2, decomposing the preprocessed data by using the improved VMD, and performing dimensionality reduction on the decomposed data by adopting a kernel principal component analysis method to obtain meteorological characteristic data; improving VMD to dynamically update a penalty factor and a mode total number; s3, the meteorological feature data is used for training an improved Stacking integrated learning model, the improved Stacking integrated learning model is provided with an objective function used for autonomously adjusting the weights of a plurality of base learners, and an output result of the Stacking integrated learning model serves as a prediction result; the device can effectively extract the feature information in the data and fully utilize the diversity of the base learner to provide a more accurate prediction result.

The invention relates to the technical field of mine dynamic disaster prediction, in particular to a rockburst prediction method based on an improved WOA optimized FTWSVM. The method comprises the following steps: firstly, selecting rockburst intensity grade prediction index data, and reconstructing a disaster sensitive index set by adopting a kernel principal component analysis (KPCA) method; then, nucleation extension is added, a fuzzy weight is introduced to improve a double twin support vector machine to obtain an FTWSVM model, and M-Map chaotic mapping and opposition learning are applied to improve a whale search algorithm to obtain key hyper-parameters of an IWOA optimization model; and finally, training the model, establishing a prediction model based on the IWOA-FTWSVM, and verifying the performance of the prediction model through a test set. According to the rockburst intensity grade prediction method provided by the invention, parameter self-adaptability and a small sample modeling method are combined, the rockburst intensity grade prediction capability is improved, and a solution is provided for effective and timely prevention of mining rockburst disasters.

The invention discloses a distributed energy storage system cooperative control method based on data fusion, and belongs to the field of power system energy storage control. The edge layer performs dimensionality reduction on multi-source data through kernel principal component analysis, the cloud constructs a space-time correlation model by combining a graph neural network with a long-short-term memory network, and data privacy is guaranteed by means of federal learning distributed updating. An upper layer model prediction control framework is combined with an improved whale algorithm to solve multi-target optimization of system economy, energy storage life and power grid stability; the lower-layer power type energy storage adopts self-adaptive droop control, and the energy type energy storage model predicts, controls and quantifies the degradation cost of the battery. When communication is interrupted, the analytic hierarchy process and the consistency algorithm cooperate to disperse power distribution; and when the equipment fails, convolutional neural network diagnosis is combined with alliance chain redundancy switching. Multi-source deep correlation, characteristic differentiation regulation and control and high robustness are realized, the energy storage efficiency is improved, the service life of equipment is prolonged, and the method is suitable for micro-grids, smart grids and other scenes.

The invention discloses a transformer state evaluation method based on kernel principal component analysis and improved semi-supervised fuzzy C-means clustering, and the method comprises the steps: enabling historical monitoring data of a transformer to generate a multi-dimensional reference vector according to a to-be-evaluated transformer state evaluation monitoring index; mapping the multi-dimensional reference vector to a high-dimensional space for dimension reduction through kernel principal component analysis and a kernel function; the data dimension is reduced, feature extraction is completed, and transformer state evaluation monitoring principal component indexes are determined; preprocessing the transformer state evaluation monitoring principal component index data; comprising extraction of labeled sample data and normalization processing of the data; carrying out improved semi-supervised fuzzy C-means clustering on the preprocessed sample data; and carrying out validity and accuracy analysis on the state evaluation result. According to the method, the problem that data information mining of a current transformer state evaluation model is not deep enough is solved, transformer state evaluation can be carried out objectively, accurately and efficiently, and a decision basis is provided for state maintenance of the transformer.

The invention relates to an aero-engine fault diagnosis method and device based on tensor decomposition and a medium, and the method comprises the steps: collecting the gas path parameter time sequence data of a plurality of parts of an aero-engine, and carrying out the time alignment and working condition label labeling; for the multi-parameter data of each component, a kernel principal component analysis and automatic encoder fused feature extraction method is adopted, and parameters of different components are unified into fixed dimension features; the feature matrixes obtained after feature extraction of all the components are combined, and a time-component-feature third-order tensor is constructed; training a high-order singular value decomposition model based on the engine health monitoring data; fault diagnosis is carried out by calculating the reconstruction error of the test data and the monitoring data; and fault positioning is realized by combining core tensor difference analysis. According to the method, the problem of feature fusion of engine multi-source heterogeneous data under variable working conditions is solved, and the engine fault detection sensitivity and positioning precision are improved.

The invention belongs to the technical field of electromechanical system simulation, and particularly relates to an electromechanical simulation model evaluation method based on AI analysis, which comprises the following steps: data preprocessing, AI evaluation engine construction, dynamic index evaluation and closed-loop optimization. An electromechanical simulation model evaluation system based on AI analysis comprises the following layered architecture: a data preprocessing layer, an AI evaluation engine layer, a dynamic evaluation layer and a closed-loop optimization layer, one of kernel principal component analysis or a variational auto-encoder is introduced to carry out nonlinear feature extraction, and game Nash equilibrium is introduced to carry out model weight dynamic allocation. And sliding window anomaly detection is introduced to dynamically adjust the threshold. According to the invention, a'physical rule + AI reasoning 'dual-drive evaluation architecture of the electromechanical simulation model is initiated; the dynamic weight distribution algorithm improves the evaluation efficiency compared with a traditional method; and the three-level indexes converge step by step, so that comprehensive evaluation from local performance to global performance is realized.