133 results about "Confusion matrix" patented technology

The invention discloses an urban flood prediction method based on a dual-drive urban flood model, and the method comprises the steps: carrying out the early-stage preparation of model construction, constructing an urban flood hydrological and hydrodynamic coupling model frame, constructing a deep learning model frame based on a GBDT algorithm, and carrying out the prediction of the urban flood. Assimilation of predicted values and measured data of a hydrological hydrodynamic model and a deep learning model is realized through a real-time data assimilation technology, then an output result of an urban flood hydrological hydrodynamic coupling model is used as an input feature of the deep learning model, and the input feature and parameters are dynamically adjusted according to the matching degree of a confusion matrix. The TP in the confusion matrix is maximum, the TN in the confusion matrix is minimum, finally, construction of the dual-drive urban flood model is completed, and prediction is conducted through the model. According to the method, the characteristic of high calculation efficiency of the deep learning model is exerted while calculation accuracy is considered, a layered coupling architecture is provided, and the problems that the calculation efficiency of a hydrological hydrodynamic model is low and a traditional deep learning model has a black box effect are solved.

The embodiment of the invention provides a mobile communication PCI (Peripheral Component Interconnect) decision-making method and device based on an improved ant colony algorithm, and the method comprises the steps: obtaining MR (Measurement Report) data of a base station and a real-time network state; the base station MR measurement report data comprises a conflict matrix, a confusion matrix and a modulo 3 interference matrix; extracting a network topology feature vector according to the MR measurement report data of the base station; according to the network topology feature vector and the real-time network state, obtaining a heuristic weight and a pheromone volatilization rate parameter; based on an ant colony algorithm, obtaining an improved ant colony algorithm according to the heuristic weight and the pheromone occurrence rate parameter; based on the quantum revolving door, determining a three-level objective function according to the conflict matrix, the confusion matrix and the modulo 3 interference matrix; and based on an improved ant colony algorithm, generating an optimal PCI allocation scheme according to the conflict matrix, the confusion matrix, the modulo 3 interference matrix, the three-level objective function and a preset constraint condition. The problem of optimization target imbalance is solved, and the reliability of the PCI decision method can be ensured.

In various examples, the present disclosure relates to using temporal filters for automated real-time classification. The technology described herein improves the performance of a multiclass classifier that may be used to classify a temporal sequence of input signals—such as input signals representative of video frames. A performance improvement may be achieved, at least in part, by applying a temporal filter to an output of the multiclass classifier. For example, the temporal filter may leverage classifications associated with preceding input signals to improve the final classification given to a subsequent signal. In some embodiments, the temporal filter may also use data from a confusion matrix to correct for the probable occurrence of certain types of classification errors. The temporal filter may be a linear filter, a nonlinear filter, an adaptive filter, and / or a statistical filter.

The invention discloses a real-time network intrusion detection method based on a genetic algorithm and a bidirectional long-short term memory network, and belongs to the technical field of network security, and the method comprises the following steps: 1, extracting continuous and category network traffic features from a constructed data set, and carrying out the feature preprocessing and preliminary screening; step 2, performing feature selection optimization based on a genetic algorithm so as to screen out an optimal feature combination with high accuracy and low dimension; 3, adopting a bidirectional LSTM algorithm to construct an abnormal traffic detection model based on the feature subset selected by the genetic algorithm, wherein the abnormal traffic detection model is used for identifying normal and abnormal samples in the network traffic; 4, evaluating the performance of the abnormal traffic detection model by adopting the confusion matrix; and step 5, deployment and real-time detection of an abnormal flow detection model. According to the invention, a lightweight and traceable intrusion detection framework is constructed. The generalization ability and precision of the detection model are improved; the method gives consideration to accuracy, interpretability and system response capability.

The invention discloses an offshore wind power low-frequency circuit breaker fault diagnosis method and a related device, electrical parameter data, environmental data and mechanical data are fused and spliced into a multi-dimensional feature vector, various fault feature information of a low-frequency circuit breaker in a complex working environment is comprehensively captured, the fault sensitivity and recognition capability are improved, and the fault diagnosis accuracy is improved. The random forest algorithm is adopted to realize high-precision diagnosis under a small sample, limited low-frequency circuit breaker data is fully utilized, the overfitting problem is effectively avoided, the number of decision trees in the random forest is optimized, the classification performance of the model is improved, the ROC curve and the confusion matrix are adopted to evaluate the performance of the low-frequency circuit breaker fault diagnosis model, and the reliability of the low-frequency circuit breaker fault diagnosis model is improved. And the effectiveness and reliability of the fault diagnosis model are improved. The technical problems that an existing offshore wind power low-frequency circuit breaker fault diagnosis method based on a single data source is high in false detection rate and an offshore wind power low-frequency circuit breaker fault diagnosis method based on multi-modal data fusion has model overfitting are solved.

The invention discloses a natural gas pipeline leakage detection method based on novel wavelet basis transformation and singular value decomposition in a two-dimensional convolutional neural network. Firstly, a sound signal collected by a sound wave sensor is converted into a digital signal; secondly, in the data preprocessing stage, singular value decomposition is carried out on the digital signals to effectively eliminate background noise interference, and then batch normalization is carried out on the processed data; then, converting the one-dimensional time sequence signal into a two-dimensional time-frequency image by adopting a self-defined Morlet wavelet basis function; and finally, based on the time-frequency images, constructing and training a 2D-CNN model for fault classification, and presenting a diagnosis result through a confusion matrix and a comparison graph. According to the method, 97.55% of fault recognition accuracy is obtained in a public data set, and compared with other competitive methods, the method shows more excellent noise robustness and classification performance, and has higher accuracy and wide application prospects in pipeline leakage diagnosis in a complex noise environment.

The invention discloses a remote sensing hyperspectral image classification method, system and device and a medium, belongs to the technical field of remote sensing image processing and mode recognition, and aims to solve the technical problem of how to improve the precision and efficiency of remote sensing hyperspectral image classification, reduce the calculation complexity, fully extract spectrum and spatial features and improve the classification efficiency of remote sensing hyperspectral images. According to the technical scheme, the method comprises the following steps: dividing a training set and a test set: dividing all pixels of a remote sensing hyperspectral image into the training set and the test set according to a set proportion; constructing a classification model: through a cross attention mechanism, constructing the classification model in combination with Transform of a spectral attention mechanism and KL divergence driven mutual learning classification; the test set is input into the classification model, a prediction result of the test set is obtained, a confusion matrix of the prediction result and a real label is calculated, and the final classification precision is obtained; and splicing a visual image.

The invention relates to a transferable vector quantization alignment method and device based on unsupervised domain adaptation, and the method comprises the steps: extracting the features of a source domain and a target domain of a source domain data set and a target domain data set through a feature extraction unit, and calculating an overall feature distribution loss function through searching a feature item closest to the features in a codebook; calculating a local alignment loss function through a bottleneck layer, performing classification through a classifier to obtain a source domain pseudo-label and a target domain pseudo-label, calculating a cross entropy classification loss function according to the source domain pseudo-label and a corresponding truth value label, performing normalization processing on the target domain pseudo-label, introducing mutual information to obtain a sample weight in each target domain data set, and obtaining a sample weight in each target domain data set; and calculating mutual information weighted maximization confusion matrix loss functions, and updating parameters in each module by using the loss functions until convergence to obtain a target classification architecture with cross-domain extraction, feature alignment and time sequence signal classification capabilities. By adopting the method, the identification performance of the label-free target domain can be improved.

The invention provides a large-model intelligent label synthesis and data automatic labeling integration method and system, and belongs to the technical field of label synthesis and data labeling, and the method comprises the steps: carrying out the semantic embedding and robust clustering of text data, and obtaining a stable cluster set; when new data is introduced, semantic consistency alignment of cross-round clustering results is realized through a confusion matrix matching strategy, and label drift is inhibited; maintaining an editable hierarchical label directed acyclic graph to support label system evolution; driving a large language model to generate a high-quality and interpretable cluster-level semantic tag based on the representative sample; carrying out automatic annotation and confidence evaluation by using large model context learning for clustering non-attribution or low-confidence samples; and propagating the cluster-level labels to the instances, and combining the cluster-level labels with an automatic labeling result to construct a full-process traceable label management mechanism. According to the method, the efficiency, quality and consistency of text labeling are improved, and powerful support is provided for large model training and intelligent data management.

The invention provides a classifier combination method based on variational Bayesian inference. The method comprises the following steps: respectively training at least two base classifiers through pre-labeled disease attack data; building a probability model by taking the real label of the disease attack data, the confusion matrix of the base classifier and the category prior as hidden variables, and outputting a posterior probability; independently optimizing the posterior probability through a variational inference method to obtain convergent variational distribution output; and obtaining a final disease label according to variation distribution output. According to the method, adaptive fusion of base classifier output is realized through probability modeling and variational inference technologies, and the reliability and efficiency of classifier combination are improved.

The present application belongs to the field of non-technical line loss reduction, and discloses a power stealing detection method based on stacked sparse autoencoder and deep forest, comprising: S1: extracting user power consumption data from an intelligent power supply and consumption database to construct a user power consumption feature dataset; S2: dividing the user power consumption feature dataset into a training set and a test set according to a certain proportion; S3: taking the training set as the input of a power stealing detection model to train the power stealing detection model; S4: testing the power stealing detection model by using the test set and constructing a confusion matrix according to the test result; and S5: evaluating the test result by using accuracy, recall rate and F1 score respectively. The present application uses a stacked sparse autoencoder to reduce the dimension of power consumption data, extracts effective information in high-dimensional power consumption data, and performs power stealing detection, thereby solving the problem of "curse of dimensionality" caused by high-dimensional power consumption data and improving the recognition accuracy of the power stealing detection model, so as to more effectively reduce non-technical line loss.

This invention discloses a RUSBoost islanding detection method applied to DC microgrids. Specifically, it involves: collecting historical data of electrical characteristics under both grid-connected and islanded states to form an unbalanced dataset; using the historical data as a training set and preprocessing it to form a training sample set; constructing a weak islanding classifier based on classification and regression decision trees; evaluating the model's correctness using a confusion matrix; and establishing a RUSBoost-based islanding detection model; applying the constructed RUSBoost-based islanding detection model to the microgrid system to classify grid-connected and islanded states based on real-time voltage and current data. This invention applies an ensemble classification algorithm from machine learning to DC microgrids, solving the problems of slow detection speed and low accuracy of existing detection methods.

The invention discloses an antenna array layout method, which is used for adjusting a plurality of array element positions of a plurality of antenna array elements in an antenna array. The method comprises the following steps: constructing a plurality of steering vectors according to a plurality of arrival angles and a plurality of array element positions; the at least one transmitting antenna array transmits signals to a target to form a first phase difference, the at least one receiving antenna array receives signals to form a second phase difference, and each of the plurality of steering vectors is constructed according to the first phase difference and the second phase difference. The plurality of arrival angles are angles relative to the antenna array when the target is at different positions; constructing a confusion matrix according to the correlation among the plurality of steering vectors; constructing a target function according to the confusion matrix; calculating a plurality of gradient vectors of the target function at a plurality of array element positions; and adjusting the plurality of array element positions according to the plurality of gradient vectors to obtain a plurality of updated array element positions. In addition, the invention also provides an antenna array layout device and a storage medium.

This invention provides a method for high-speed train bearing fault diagnosis and selection based on multi-model comprehensive evaluation. The method first obtains bearing fault feature vectors, then divides the training and test sets using 8:2 stratified sampling, mitigating sample imbalance bias through a sample weighting strategy. Next, it constructs a diagnostic system comprising five models, including random forest and support vector machine, and employs optimal hyperparameters for parallel training. Subsequently, a multi-dimensional evaluation system for accuracy and efficiency is established, and model reliability is verified using a confusion matrix. Finally, model selection is tailored to specific scenarios: multilayer perceptrons are used for real-time monitoring, gradient boosting trees for high-precision scenarios, and random forests or K-nearest neighbors for lightweight deployment. This achieves scientific multi-model selection, balancing diagnostic accuracy, real-time performance, and stability, adapting to the maintenance needs of high-speed trains, and demonstrating strong engineering practicality.

The application discloses a kind of based on neural network's semi-batch reaction thermal behavior identification method, first define thermal behavior label, solve dimensionless mathematical model;Again, extract core numerical features from traditional criterion, and match with NI, TR and QFS thermal behavior to constitute data set;Again, data set is preprocessed, and is divided;Again, the recognition accuracy and generalization ability of different machine learning algorithms to reaction thermal behavior are analyzed and compared, and double-layer BP neural network is selected;Then determine the structure of double-layer BP neural network;Again, the weight and threshold of double-layer BP neural network are optimized using genetic algorithm and bayesian regularization algorithm;Again, confusion matrix is drawn to evaluate the classification performance of double-layer BP neural network;Finally, dimensionless mathematical model and optimized double-layer BP neural network are deployed, simulate and thermal behavior prediction for semi-batch reaction, effectively solve the problem that reaction system thermal behavior identification angle is not comprehensive, with stronger generalization ability and universality.

The invention discloses a personnel information error correction method and system based on a large model and a storage medium, and the method comprises the following steps: S1, carrying out the data cleaning of the information of personnel to be corrected, and disassembling the duty of the information; s2, performing congruent matching on the information of the personnel to be corrected and the human resource library, if matching succeeds, judging that the information is correct, and ending the process; otherwise, entering S3; s3, searching related personnel information data in a human resource library to construct an initial error correction data set; s4, calculating the comprehensive similarity of each piece of information in the initial error correction data set, and selecting N pieces of personnel information with the highest similarity to form a final error correction data set; s5, inputting the information of the personnel to be corrected and the final error correction data set into the large language model to obtain correct name and job information; s6, the correct information is updated to the human resource library, and the character confusion matrix is updated; error correction can be efficiently and accurately carried out on personnel information, and the error correction accuracy can be improved according to historical error correction behaviors.

The application relates to a data encryption processing method and device, a server and a storage medium. The method comprises the following steps: in an execution environment meeting a preset trusted condition, matching a corresponding matrix multiplication protocol based on user input encryption data; under the matrix multiplication protocol, performing confusion processing on the encryption data to generate a confusion matrix; performing matrix multiplication calculation on the confusion matrix in a graphics processor to obtain a confusion reasoning result of the encryption data, performing de-confusion recovery processing on the confusion reasoning result by using the execution environment to obtain an actual reasoning result, and pushing the reasoning result to the user after encryption. Thus, the technical problem that, in the related art, the manner of processing encryption data in a protected hardware region is not suitable for performing large-scale matrix multiplication and has poor universality, and the matrix calculation based on the graphics processor cannot guarantee the security of the data is solved.

The application provides a large model intelligent label synthesis and data automatic labeling integrated method and system, and belongs to the technical field of label synthesis and data labeling. The method comprises the following steps: performing semantic embedding and robust clustering on text data to obtain a stable cluster set; when new data is introduced, the semantic consistency alignment of cross-round clustering results is realized through a confusion matrix matching strategy to suppress label drift; an editable hierarchical label directed acyclic graph is maintained to support label system evolution; a large language model is driven based on representative samples to generate high-quality and interpretable cluster-level semantic labels; for samples that are not attributed or have low confidence in clustering, automatic labeling and confidence evaluation are performed through context learning on the large model; the cluster-level labels are propagated to instances and combined with the automatic labeling results to construct a full-process traceable label management mechanism. The application improves the efficiency, quality and consistency of text labeling, and provides strong support for large model training and intelligent data management.

The invention is suitable for the technical field of seismic exploration, and provides an scSEVGG16-UNet + + seismic horizon identification method based on data enhancement, and the method comprises the following steps: constructing a UNet basic network employing VGG16 as a trunk; dense connection and a deep supervision mechanism are introduced, and a VGG16-UNet + + network is improved; aiming at the characteristics of seismic data, data enhancement is carried out by adopting a plurality of transverse transformation and noise addition modes; designing an scSE attention mechanism module to enhance the expression ability of the feature channel and the spatial dimension at the same time; an scSE attention mechanism module is embedded into the jump connection part of the VGG16-UNet + +, and a final recognition model is formed; training the network by using cross entropy loss and an Adam optimizer; and finally, the recognition effect is evaluated through the confusion matrix, mIoU and PA indexes. According to the method, the problems of discontinuous identification and layer staggering caused by data scarcity and feature similarity in seismic horizon identification are effectively solved, and the identification precision, continuity and model generalization ability are remarkably improved.

The application provides a wake-up word registration method and device, equipment and a storage medium. The method comprises the following steps: in response to multiple audio input operations of each user on each wake-up word, generating respective registration audios corresponding to each wake-up word; performing feature extraction processing on the respective registration audios to obtain corresponding embedding features; calculating the similarity of each embedding feature and the respective embedding features; constructing a confusion matrix according to multiple similarities corresponding to all embedding features; determining a corresponding target embedding feature from the respective embedding features according to the confusion matrix; determining a corresponding target registration audio from the respective registration audios according to the target embedding feature, and determining the target registration audio as a target audio template corresponding to the wake-up word; determining a target row element from the confusion matrix according to the target audio template; and determining an adaptive wake-up threshold corresponding to the wake-up word according to the target row element, so as to complete the registration of the wake-up word and improve the accuracy of subsequent user wake-up terminal equipment.

The application discloses a user sensitive information protection method based on a data confusion technology, and comprises the following steps: step S1, generating a sensitive attribute association table based on the association between recommended items and user gender characteristics; step S2, adding confusion ratings to an existing user-item matrix through a sampling strategy according to the sensitive attribute association table obtained in step S1, and constructing a user-item matrix after adding the confusion ratings; step S3, recording the number of confusion ratings added in step S2, applying a removal strategy, and finally generating a confusion matrix after applying the removal strategy; the removal strategy is that the same number of confusion ratings are deleted to maintain the original data size; a user is randomly selected, and when the rating number of the user reaches a set threshold, the items with strong association of the opposite sex are deleted from the rating history of the user. The application can mislead attackers to conduct gender attribute inference, realize user privacy protection, and does not affect the existing personalized recommendation quality of the user.

The invention provides an urban tree species classification method, system and device, and belongs to the technical field of tree species classification, and the method comprises the steps: firstly, selecting candidate wavebands in a red-edge spectrum range, traversing all dual-waveband combinations, and defining a vegetation index through a preset formula; secondly, for each index, generating a vegetation mask by using a plurality of candidate thresholds, and calculating a confusion matrix evaluation index by comparing the vegetation mask with a real mask; and finally, based on the index, automatically screening out an index with optimal performance and a threshold pair. Wherein the index defined by the optimal dual-band combination is the final vegetation index, and according to the final vegetation index, classification and identification of urban tree species are carried out through a machine learning model. The method solves the problem that classification of the classic vegetation index on the urban tree species is not accurate.

The invention discloses an evaluation method and device of a defect detection algorithm, equipment and a storage medium, and belongs to the technical field of evaluation of defect detection algorithms, and the method comprises the steps: determining the sample size of a photoelectric device according to the specificity and sensitivity of the photoelectric device; determining sample distribution according to the type of the photoelectric device and a preset distribution rule; determining a test data set according to the sample size and the sample distribution; based on a target defect detection algorithm and the test data set, obtaining a dichotomy label and a defect prediction probability of the photoelectric device; determining a confusion matrix according to the dichotomy label, the defect prediction probability and the real defect label; and calculating a performance index of the target defect detection algorithm according to the confusion matrix. According to the method, the test data is determined by combining the specificity and sensitivity of the photoelectric device with sample distribution, so that the test data can comprehensively cover the test content, the performance index of the detection algorithm is evaluated through the confusion matrix, and the defect detection algorithm is accurately and comprehensively evaluated.

The present application relates to the field of offshore platform pipeline leakage detection, and proposes a pipeline leakage identification method combining OVMD and GBDT algorithm. First, a pipeline leakage model is established, leakage signals under different working conditions are collected, and real background noise is collected on the offshore platform, which is injected into the laboratory leakage signal to simulate the actual working environment. The original sample data set constructed is decomposed using the OVMD method to obtain multiple signal component functions, feature indicators are extracted, the GBDT algorithm is used to classify and identify the extracted feature indicators, and a confusion matrix and precision-recall curve are formed. The present application effectively improves the identification accuracy of the leakage signal, solves the problems of difficulty in acoustic emission signal collection, low identification accuracy of existing methods, poor robustness and complex implementation.

The application discloses a kind of belonging to power system transient stability evaluation based on multi-source information's transient stability evaluation method.Firstly, by changing system operating state and fault condition, using power system analysis program for batch time domain simulation to construct massive data set for IEEE39 node system.Then, considering the influencing factors affecting system transient stability, the operating information and fault information are used as the input features of the convolutional neural network model.In order to better realize the comprehensive utilization of operating information and fault information, and avoid the influence of feature dimension difference on accuracy, two different feature fusion schemes are adopted for phased fusion of features, and different transient stability evaluation models are formed.Then, the transient stability evaluation model established by training is used to evaluate the transient stability of the test set, and the accuracy, precision, recall and index of the confusion matrix tool are used to evaluate the performance of the model.Finally, the t-SNE algorithm is used to visualize the established transient stability evaluation model.

The invention belongs to the technical field of meteorological element prediction methods, and particularly relates to a meteorological element class imbalance data processing method based on machine learning. The invention particularly relates to a thunderstorm gale prediction method and system based on a space-time sampling strategy, and the method comprises the steps: obtaining thunderstorm gale observation data and forecast factor data of a target region, carrying out the processing of the obtained observation data and forecast factor data, carrying out the space-time mixed sampling, and obtaining a thunderstorm gale prediction result; the method comprises the steps of space sampling optimization and time sampling optimization: forming a physical mechanism needing 6-12 hours of energy accumulation and water vapor transportation based on thunderstorm gale, designing three time sampling schemes, namely N1, N2 and N3, coupling the three schemes with the determined space optimal proportion, and adopting the sampling data after coupling in the step 3 to obtain the time sampling optimization of the thunderstorm gale. Three machine learning models of MLP, AdaBoost and SVM are subjected to parameter tuning and training, the trained models are utilized to predict thunderstorm and gale in a target area, and an evaluation system is constructed based on a confusion matrix.

The invention discloses a static database multi-stage desensitization method based on a dynamic confusion matrix and a hierarchical key, which comprises the following steps: identifying a sensitivity level through a data classification module, generating a differential desensitization rule through a dynamic confusion matrix module, managing an encryption key through a hierarchical key module, and implementing multi-stage processing through a desensitization execution module. And the security audit module monitors the operation log. According to the method, the problems of single traditional desensitization strategy, complex key management and insufficient dynamic defense are effectively solved, and the data security and the service availability are remarkably improved.

The invention discloses a method for classifying coating manufacturing defects of a liquid crystal display device, which comprises the following steps of: 1, segmenting a binarized defect image by utilizing a watershed algorithm, extracting defect connected domains, and calculating characteristic parameters of each defect connected domain; 2, based on the feature parameters, performing feature selection by adopting a minimum redundancy and maximum correlation method to obtain image comprehensive features; 3, inputting the image comprehensive features into a pre-trained PSO-BA-LightGBM classification model, classifying the defect types of the coating surface of the display, and outputting a classification result; and 4, constructing a confusion matrix according to the classification result, and calculating a defect performance index value based on the confusion matrix. And the identification capability of multiple types of defects and the prediction precision of the whole model are effectively improved.

A system and method are provided for evaluating a prediction model configured to predict occurrence of a clinical event in multiple patients during corresponding patient stays, where the prediction model outputs risk scores for the patients. The method includes identifying patient stays that include at least one risk score generated by the prediction model that crosses a predetermined risk threshold; providing notifications for risk scores that cross the risk threshold; determining a patient-level confusion matrix based on the notifications, where each patient stay contributes one patient data point to the patient-level confusion matrix; determining an event-level confusion matrix based on the notifications, where the event-level confusion matrix includes prediction lead time and notification limit, where each patient stay contributes one event data point to the event-level confusion matrix; calculating classification metrics for false positives and false negatives; and identifying errors in the predication model based on the classification metrics.

The invention discloses a mine transformer fault diagnosis method based on LightGBM-ICPO-XGBoost, and the method comprises the steps: collecting the original concentration data of dissolved gas in the oil of a mine transformer, and constructing a multi-dimensional dissolved gas ratio feature; carrying out normalization processing on the multi-dimensional dissolved gas ratio characteristics, and dividing a data set according to a proportion; quantifying feature importance and screening an optimal feature subset by using an embedded feature selection mechanism of LightGBM; logistic chaotic mapping and a self-adaptive t distribution variation strategy are introduced to improve a CPO algorithm, and hyper-parameters of the XGBoost model are optimized; an XGBoost model is trained based on the optimized hyper-parameters and the screening features, and accurate classification of multiple types of faults is achieved; and evaluating the diagnosis performance by adopting a multi-dimensional index, and analyzing a fault misjudgment reason in combination with a confusion matrix. The method is designed for complex working conditions of a transformer in a mine power supply scene, has high-precision fault identification capability and strong noise robustness, and can provide reliable technical support for state evaluation of power equipment.