86 results about "Adaboost algorithm" patented technology

A multi-model fused avionic product health assessment method includes the following steps: collecting relevant data of an avionic product; performing data pre-processing on the relevant data to obtain first data and second data; training a plurality of base models on the basis of the first data; performing quantitative measurement and fusion on the plurality of base models to obtain an integrated model; and inputting into the integrated model the second data which serves as a test sample to obtain a health assessment result of the avionic product. A plurality of base models are integrated by using an AdaBoost algorithm, and a reference can be provided for a method based on data driving in terms of application in the health assessment, prediction and management of an avionic product.

The invention discloses an equipment part fault diagnosis method, device and equipment based on sensing data mixed noise suppression, and relates to the field of fault diagnosis. The diagnosis method comprises the following steps: acquiring vibration signals of an equipment part under different fault types; performing data preprocessing on the vibration signal to obtain a sample, taking a fault type corresponding to the vibration signal as a real label, and constructing a training set and a verification set; using the training set and the verification set, and using a migratable Adaboost algorithm and an adaptive cost sensitive learning method to train a plurality of deep learning models to obtain a plurality of trained deep learning models; and performing fault diagnosis on the to-be-tested part of the equipment by using the plurality of trained deep learning models. According to the invention, the accuracy of equipment part fault diagnosis in the mixed noise environment is improved.

The invention discloses a listed company risk assessment method based on cross validation and Bayesian optimization, and the method comprises the following steps: 1, obtaining the comprehensive factor data of a listed company, carrying out the dimension reduction of the factor data through employing a principal component analysis method, obtaining a principal component factor, carrying out the effectiveness verification of the principal component factor through an IC and IR analysis method, and carrying out the calculation of the risk of the listed company; selecting a plurality of principal component factors as input features; 2, on the basis of the multi-factor model, constructing an ensemble learning index enhancement model by taking a decision tree and an AdaBoost algorithm as cores; 3, performing system optimization on parameters of the ensemble learning index enhancement model by adopting cross validation and a Bayesian method, and finally determining an optimal parameter combination to obtain a trained ensemble learning index enhancement model; and 4, evaluating the risk of the listed company by using the trained integrated learning index enhancement model. According to the method, the calculation resource consumption of the model can be reduced, the calculation efficiency is improved, and the over-fitting risk of the model can be reduced.

The invention relates to an origin-destination route deduction and travel time estimation method, which can deduce and generate a personalized travel route between origin and destination in combination with user preference on the premise of reducing data annotation quantity as much as possible by combining an antagonistic inverse enhancement network of an active learning mechanism. Furthermore, a plurality of weak learners fusing the graph convolutional network and the Transform network are integrated through an AdaBoost algorithm, and the graph convolutional network can obtain the high-dimensional spatial-temporal characteristics of the traffic network, thereby assisting the Transform network to better capture the long-term and short-term dependency relationship corresponding to the personalized driving route. In combination with learning results of a plurality of weak learners, a more abundant and comprehensive time sequence feature representation of a personalized driving route is obtained, finally, the travel time corresponding to the route is obtained by using the time sequence feature representation, and accurate origin-destination travel time estimation is realized.

The invention relates to the technical field of air temperature risk assessment, in particular to an AdaBoost-based urban air temperature inference and thermal exposure risk assessment method. The method comprises the following steps: acquiring original city form data and city meteorological data of a city; performing data preprocessing on the original city form and the city meteorological data of the city to generate processed original city form data and city meteorological data; integrating the processed original city form data and city meteorological data into a model training set and a model test set; and designing an artificial neural network architecture by adopting an AdaBoost algorithm, and performing model training on the model training set by utilizing the artificial neural network architecture to generate an urban air temperature inference pre-model. According to the method, by fusing multi-source data, applying an advanced machine learning algorithm and enhancing sensitivity analysis and Monte Carlo simulation, the accuracy and reliability of urban air temperature inference and thermal exposure risk assessment are improved.

The invention belongs to the technical field of circuit breaker fault diagnosis, and particularly relates to a high-voltage circuit breaker and a mechanical characteristic health diagnosis method and system thereof. The method comprises the following steps: S1, acquiring operation state information of the high-voltage circuit breaker in a switching-off / switching-on process; s2, inputting the running state information into a pre-trained fault diagnosis model to obtain a fault state type of the mechanical characteristics of the high-voltage circuit breaker; the fault diagnosis model comprises a strong classifier, and the strong classifier is a classifier obtained by combining at least two weak classifiers through an AdaBoost algorithm. According to the method, the classification model is constructed by adopting a multi-algorithm fusion technology through the AdaBoost algorithm, and the AdaBoost algorithm enables the model to pay more attention to samples which are difficult to classify by adjusting the weight of data points, so that the classification effect of the model is enhanced. The technical problem of low fault diagnosis precision caused by low classification precision of fault data difficult to classify in the prior art is solved.

The invention relates to the technical field of information, in particular to a black land plough layer thickness analysis method based on machine learning. The scheme has the advantages that double-frequency radar signals (200MHz low frequency and 2GHz high frequency) are combined with power amplification and a broadband antenna, a double-layer feature comparison model is constructed by utilizing the frequency sensitivity inversion characteristic of dielectric constant difference between a plough layer and a plough pan, interface details are captured in cooperation with a 1GS / s super-Nyquist sampling rate, a strong regression model is constructed in combination with an AdaBoost algorithm, and a high-precision feature comparison model is constructed. The method achieves the high-precision, non-destructive and large-area rapid detection of the thickness of the plough layer of the black land, and solves the problems that a conventional method is time-consuming and labor-consuming, is low in precision, and cannot give consideration to the penetration depth and resolution of a single-frequency radar.

The invention relates to the technical field of wind power plant active power control, and discloses an active power control method and system for a wind power plant, and the method comprises the steps: obtaining the historical data of a fan, and constructing a training set according to a wake flow influence result of a fan state; based on an AdaBoost algorithm, constructing a strong classifier in combination with the training set; the method comprises the following steps: determining fans influenced by wake flow by using a strong classifier, determining upstream fans generating wake flow by using a wake flow center line deflection angle, and defining all wind turbine generators which are not influenced by wake flow and generate wake flow which does not influence downstream fans as a controllable fan group; and solving the wind turbine generator groups with the minimum number of execution actions in the wind power plant by utilizing a dynamic programming algorithm, and executing active power control operation. According to the method, the space-time coupling influence caused by the wake effect in the active power control process of the wind power plant can be eliminated, the environmental disturbance generated by the execution of the power control action of the fan to the wind power plant is reduced to the minimum, and the real-time accurate control of the active power of the wind power plant can be realized.

This invention relates to a medium-term electricity forecasting method based on Prophet, and belongs to the field of medium-term electricity forecasting for power systems. To address the difficulty of a single Prophet model in fully exploring the deep features of complex time series and integrating multi-source exogenous variables, this method extracts time features through customized seasonality, decomposes historical targets into trend, seasonality, and holiday effects, and constructs joint features to introduce exogenous variables. Furthermore, the AdaBoost algorithm and the N-BEATSx model are used to achieve monthly electricity forecasts, respectively. Optuna automatic parameter adjustment and Bayesian Ridge regression are then used to stack and fuse the forecast results. This method is suitable for medium-term dispatch planning of power systems, providing a scientific decision-making basis for grid security.

The invention relates to the technical field of lithium batteries, in particular to a battery SOC estimation method based on an xLSTM model. A battery SOC estimation method based on an xLSTM model comprises a data acquisition module, a data preprocessing module, an xLSTM-based voltage prediction module, a single voltage prediction module and an SOC prediction module. Compared with the prior art, the xLSTM model-based battery SOC estimation method provided by the invention has the advantages that the xLSTM model is introduced, so that a long dependency relationship in time sequence data can be better captured, and the precision of time sequence prediction tasks such as the battery SOC and the like is improved; by combining the steps of data preprocessing, model construction, training, verification and the like, the xLSTM can realize relatively high prediction performance in practical application; and an Adaboost algorithm and Kalman filtering of integrated learning are combined to realize accurate prediction of the SOC of the battery. The method enhances the robustness and prediction precision of the system, and is suitable for the practical application of the battery management system.

The invention discloses an AdaBoost-based chlorophyll concentration forecasting method and device and a readable medium, and the method comprises the steps: constructing training data, constructing a chlorophyll concentration strong forecasting model integrating a plurality of weak forecasting models, and carrying out the iterative adjustment of the distribution weight of the training data through employing an AdaBoost algorithm in the training process of the weak forecasting models, training each weak forecast model by using the training data used in each iteration to obtain a plurality of trained weak forecast models, and calculating the weight of each trained weak forecast model; inputting the input data into each trained weak forecasting model to obtain a forecasting result of each trained weak forecasting model, and calculating according to the forecasting result of each trained weak forecasting model and the weight of the corresponding trained weak forecasting model to obtain a forecasting result of the chlorophyll concentration strong forecasting model. The method can improve the prediction precision of the near-shore chlorophyll concentration, and provides more accurate and effective prediction support for the protection of a marine ecosystem.

The invention discloses a credit risk level assessment method, device and equipment and a storage medium, and belongs to the field of artificial intelligence, and the method comprises the steps: obtaining to-be-assessed credit data of a target object; inputting the to-be-evaluated credit data into the target evaluation model to obtain a credit risk level corresponding to the target object; wherein the target evaluation model is obtained by training a credit risk level evaluation model based on an Adaboost algorithm based on a sample credit data set. According to the invention, the accuracy of user credit risk assessment is improved, and the credit risk in the credit business of banks and other financial institutions is reduced. Meanwhile, credit approvers do not need to check the loan application materials of the borrowers one by one, so that the loan approval efficiency of financial institutions such as banks is improved, and the business handling time of the borrowers is shortened.

The present invention discloses a voice analysis method for key feature parameters of freezing gait symptoms in Parkinson's disease based on the AdaBoost algorithm. Step 1: Collect continuous and stable vowels of Parkinson's disease patients and record whether the Parkinson's disease patients have freezing gait symptoms; Step 2: Perform denoising preprocessing on the voice signals and remove the silent segments; Step 3: Extract various voice features; Step 4: Use the CART algorithm to perform feature selection on the original features and screen out the key features that can effectively represent the information of freezing gait symptoms; Step 5: Train the AdaBoost model; Step 6: Input the feature vector of the voice to be measured into the model to obtain the key feature parameters of the freezing gait symptoms in Parkinson's disease. The present invention uses the AdaBoost algorithm to analyze the freezing gait symptoms in Parkinson's disease, improves the model accuracy by using ensemble learning, and reduces the cost of early analysis of the freezing gait symptoms in Parkinson's disease.

The invention discloses a computer information security assessment method and system based on big data. The method comprises the steps of data acquisition, data preprocessing, computer information security assessment model construction, model parameter tuning and computer information security real-time assessment. The invention belongs to the technical field of security assessment, and particularly relates to a computer information security assessment method and system based on big data, and the method comprises the steps: determining features through information gain, constructing a random sample subset through a bootstrap method, selecting a first basic classifier based on classification precision, and selecting second to B basic classifiers based on an AdaBoost algorithm and importance. Combining the selected basic classifiers based on weights; a cosine function is used to generate a mapping function to initialize a position, an elite individual and a common individual are divided based on a dynamic elite selection factor, the positions are updated respectively, optimal parameters are found to complete tuning, the robustness and adaptability of the model are enhanced, and the reliability and accuracy of evaluation are improved.

The present invention discloses an anti-interference target acquisition method based on machine vision technology measurement, the steps of which include: S1, original image multi-stage filtering preprocessing; S2, target feature extraction; S3, random forest construction: calling a historical data sample library to obtain an anti-interference target acquisition library, randomly selecting M data points from it, creating a decision tree for the selected data points, each decision tree will produce a result, comprehensively analyze the results and output a majority vote or average; S4, through random forest, obtain a target feature reference set; S5, select the first N frames of the on-site detection picture as a training set, obtain appropriate counting weights through continuous training, and then start from the N+1th frame image, perform voting analysis by determining the weight and using the Adaboost algorithm to determine the final target. The present invention can effectively solve the interference problem in the target capture process under complex scenes, and can effectively improve the accuracy and robustness of target detection.

The invention discloses a real-time subway passenger destination prediction method based on a subway-bus network, and the method comprises the steps: making a subway passenger travel data set which comprises the context information of a subway passenger starting station, the arrival frequency of a subway passenger, the instant travel information of the subway passenger, and the subway-bus fusion travel information; constructing a graph convolution attention network model GCAISN, and training the GCAISN model by using the subway passenger travel data set to obtain a trained GCAISN model; and integrating a plurality of trained GCAISN models by using an AdaBoost algorithm to construct a strong learning device, and predicting metro passenger destinations with different travel characteristics through integrated learning. According to the method, the subway travel records of the subway passengers are analyzed, the travel preferences of the subway passengers can be effectively analyzed and mined, the time cost of a large number of training samples can be effectively reduced, and the accuracy of predicting the subway destinations of the passengers in real time is improved.

The invention discloses a transformer fault diagnosis method based on feature selection and improved IPSO-BP-Adaboost, and the method comprises the following steps: calculating an out-of-bag error rate through a random forest, screening out a gas combination which is most beneficial to the improvement of diagnosis precision, carrying out the optimization of parameters of a double-hidden-layer back propagation network through an improved particle swarm algorithm, and carrying out the optimization of the parameters of the double-hidden-layer back propagation network. And an Adaboost algorithm is used to improve the robustness of the IPSO-BP diagnosis model. According to the method, four strategies of SPM chaotic mapping based on reverse learning, adaptive inertia weight, spiral flight search and crisscross variation are innovatively introduced to improve the particle swarm optimization. According to the method, the problems that a traditional particle swarm algorithm is prone to falling into local optimum, low in convergence speed and insufficient in population diversity are solved; the defect that a traditional BPNN network is sensitive to the weight and bias of neurons is overcome; the accuracy of the diagnosis result is greatly improved, and the stability of the model diagnosis result is ensured.

The application discloses a GIS partial discharge pattern recognition method based on polar coordinate distribution entropy optimization, and belongs to the field of large power grid on-site power equipment defect diagnosis and recognition. Firstly, aiming at the signal missing phenomenon of photoelectric partial discharge signals, a non-subsampled contourlet transform is used to fuse and process photoelectric PRPD graphs, so that photoelectric fusion graphs are obtained. Then, feature points and scale vectors of the fusion PRPD graphs are extracted based on a KAZE algorithm. Next, the feature points are dispersed to polar coordinate expressions according to coordinates and scale vectors. Distribution entropy of each region divided on the polar coordinates is calculated to form a feature vector. Finally, the feature vector is loaded into a long short-term memory network optimized by an Adaboost algorithm to verify the accuracy of partial discharge pattern recognition. Compared with a statistical parameter method and a KAZE feature extraction method, the algorithm can better extract a PRPD graph feature vector, and the accuracy of partial discharge defect pattern recognition is significantly improved.

The invention discloses an anti-interference target acquisition method based on machine vision technology measurement. The method comprises the following steps: S1, performing multi-stage filtering preprocessing on an original image; s2, target feature extraction; s3, random forest construction: calling a historical data sample library to obtain an anti-interference target acquisition library, randomly selecting M data points from the anti-interference target acquisition library, creating decision trees for the selected data points, generating a result for each decision tree, comprehensively analyzing the results and outputting a majority vote or average; s4, obtaining a target feature reference set through a random forest; and S5, selecting the first N frames of the on-site detection picture as a training set, obtaining a proper vote counting weight through continuous training, and performing vote analysis from the (N + 1) th frame of image through the determined weight by using an Adaboost algorithm to determine a final target. According to the method, the interference problem in the target capturing process in a complex scene can be effectively solved, and the accuracy and robustness of target detection can be effectively improved.

The present invention discloses a credit risk rating assessment method, apparatus, device, and storage medium, belonging to the field of artificial intelligence. The method comprises: obtaining credit data to be assessed of a target object; inputting the credit data to be assessed into a target assessment model to obtain a credit risk rating corresponding to the target object; wherein the target assessment model is obtained by training a credit risk rating assessment model based on an Adaboost algorithm based on a sample credit data set. The present invention improves the accuracy of user credit risk assessment and reduces credit risk in the credit business of financial institutions such as banks. At the same time, there is no need for credit approval personnel to review the borrower's loan application materials one by one, thereby improving the loan approval efficiency of financial institutions such as banks and shortening the business processing time of borrowers.

The invention discloses a statistical service modeling and real-time prediction method for the satellite Internet of Things, and the method comprises the following steps: analyzing influence factors, considering the influence of clock drift and terminal electric quantity into service modeling, and obtaining the terminal clock drift amount and the battery electric quantity through a clock drift formula and an ampere-hour integral method; performing statistical service modeling, analyzing service conditions in a typical region, adding influence factors to obtain a regional lumped service volume, and sending the regional lumped service volume to a satellite to obtain an on-satellite service curve; and real-time service prediction is carried out, a parallel CNN-BiLSTM network is constructed, the prediction performance is improved by using an Adaboost algorithm, and real-time prediction of the service volume is completed. According to the method, a traditional 3GPP service model is combined with the Markov Poisson process, actual influence factors are considered, satellite Internet of Things source service modeling is achieved, the working state of each terminal can be reflected, the accuracy of the service model is effectively improved, meanwhile, service prediction is conducted through a CNN-BiLSTM-Adaboost network, and the accuracy of service prediction is effectively improved.

The invention relates to an abnormal data cooperative solving system and method based on a multi-agent technology, and is applied to the technical field of electric quantity abnormal data processing, and the method comprises the steps: constructing a multi-agent system based on an EMS (energy management system) and a TMR (electric energy metering system), obtaining a sample related to abnormal data through the integration of the active power of a corresponding telemetering point of the EMS, and obtaining a sample related to the abnormal data; according to the method, a corresponding approximation function expression is obtained through curve fitting, an estimated value corresponding to abnormal data is calculated, then a substitution value of the abnormal data is calculated through the estimated value, automation and intelligentization of abnormal meter bottom code data monitoring and solving and numerical substitution of the electric energy metering system are achieved, new requirements and challenges are flexibly met, and the method is suitable for large-scale popularization and application. The overall operation efficiency of the electricity market is improved; moreover, the method does not depend on the accuracy and linear law of feature selection, and the precision of a correction result is higher than that of an existing Adaboost algorithm and a Newton interpolation method.

The invention relates to a gas-liquid two-phase flow gas volume fraction measurement method, which comprises the following steps of: acquiring local gas content signals at each position through an array optical fiber probe sensor, measuring by using a flow meter to obtain corresponding standard gas volume fractions, and constructing a sample data set; constructing a BP neural network, and optimizing the weight and threshold of the BP neural network by using a particle swarm optimization algorithm to obtain preset T weak predictors; and combining the T weak predictors according to the following formula to obtain a strong predictor which is used for obtaining a final gas volume fraction predicted value. The optical fiber probe sensor adopted by the invention can accurately detect gas-phase and liquid-phase media in gas-liquid two-phase flow, provides basic data for accurate measurement, optimizes the weight and the threshold value of the BP neural network through the particle swarm optimization algorithm, helps the network to jump out of local optimum, and improves the global search capability of the model, thereby improving the measurement precision, and reducing the measurement cost. According to the AdaBoost algorithm, a plurality of BP neural network weak predictors subjected to PSO optimization are combined into a strong predictor, so that the model prediction precision and stability are greatly improved.

The application provides a multi-LLM collaborative sentiment analysis method and device based on Adaboost dynamic weight adjustment and a medium. The method uses the Adaboost algorithm to dynamically update the weights of multiple large language model analyzers, and obtains target weight parameters associated with each large language model analyzer. Then, sentiment orientation recognition is performed on the preprocessed text by using multiple large language model analyzers to obtain an initial prediction result. When the initial prediction result does not satisfy a preset consistency condition, a large language model arbitrator is introduced, and multiple rounds of collaborative interaction verification are performed by the analyzer and the arbitrator combination to obtain multiple interaction analysis results. The multiple interaction analysis results are weighted and fused, and the final sentiment analysis result is determined according to the statistical score after the weighted fusion. Through the dynamic weight calibration and deep interaction arbitration mechanism, the accuracy, robustness and decision reliability of sentiment analysis are significantly improved.

A network traffic anomaly detection method and apparatus, and an electronic apparatus and a storage medium are provided. The network traffic anomaly detection method includes: acquiring multiple segments of traffic data in different monitoring states; acquiring an anomaly feature vector from the multiple segments of traffic data; training an initial classification model according to the anomaly feature vector and on the basis of a KNN algorithm, so as to obtain multiple initial classifiers; training an initial Adaboost classification model according to the anomaly feature vector and the multiple initial classifiers and on the basis of an Adaboost algorithm, so as to obtain an Adaboost classifier; and classifying collected traffic data via the Adaboost classifier.

The invention discloses a skin lesion classification method based on an improved Adaboost and lightweight convolutional neural network, and aims to solve the problems of high calculation cost of an existing large model and insufficient precision of a lightweight model under the conditions that the number of skin lesion image samples is limited and the sample category proportion is unbalanced. According to the method, the lightweight convolutional neural network is used as a base learning device, and the weight parameters of the training samples are updated through the improved Adaboost algorithm, so that the lightweight model pays more attention to the samples with classification errors, and the classification capability of minority class samples is improved. According to the method, based on relatively low running resources and hardware cost, the classification accuracy is remarkably improved on the public data set of the skin lesions, intelligent and rapid screening and judgment are provided for clinical diagnosis and treatment of the skin lesions, and the method is suitable for portable and mobile terminal medical equipment and has a good application prospect.

The invention discloses a hyperspectral rock classification method based on a deep ensemble learning algorithm. The method comprises the following steps of: 1, acquiring a hyperspectral data set of 81 types of rock samples from a hyperspectral rock standard database, performing dimension reduction by applying principal component analysis, and segmenting the hyperspectral data set into a three-dimensional cube as spatial features to be input into a 2D convolutional neural network; meanwhile, the center pixel block subjected to dimension reduction processing serves as a spectral feature to be input into a gating circulation unit; 2, connecting a 2D convolutional neural network and a gating circulation unit in series, introducing a full connection layer to fuse spatial features and spectral features, and optimizing model performance in combination with an AdaBoost algorithm; and 3, dividing the hyperspectral data set subjected to principal component analysis dimension reduction into a training set and a test set, and training the hyperspectral rock classification model in batches. According to the method, the space and spectral characteristics of the rock sample are effectively fused, the multi-dimensional information of the hyperspectral rock image is fully utilized, the phenomena of same object and different spectrum and same spectrum and foreign matter are reduced, and the classification accuracy is remarkably improved.

The application discloses an equipment part fault diagnosis method and device based on mixed noise suppression of sensing data and equipment, and relates to the field of fault diagnosis.The diagnosis method comprises the following steps: acquiring vibration signals of equipment parts under different fault types; performing data preprocessing on the vibration signals to obtain samples, taking the fault types corresponding to the vibration signals as real labels, and constructing a training set and a verification set; using the training set and the verification set, using a transferable Adaboost algorithm and an adaptive cost-sensitive learning method to train a plurality of deep learning models, and obtaining a plurality of trained deep learning models; and using the plurality of trained deep learning models to perform fault diagnosis on the to-be-tested parts of the equipment.The application improves the accuracy of equipment part fault diagnosis in a mixed noise environment.

The invention discloses a quantitative investment method, device and equipment and a storage medium, and relates to the technical field of quantitative investing.The quantitative investment method comprises the following steps that price data of multiple stocks are collected in real time, and multiple principal component factor data of different stocks are obtained according to the price data; inputting a plurality of principal component factor data of different stocks into the index enhancement model, automatically generating distinguishing features in a decision tree construction process by a plurality of decision tree algorithms, and classifying the plurality of principal component factor data based on the distinguishing features to obtain a classification result; the AdaBoost algorithm adjusts the weights of the plurality of principal component factor data, and inputs the weights to the plurality of decision tree algorithms again for classification iteration; and obtaining a final classification result of different stocks after iteration, and selecting a plurality of stocks for buying and selling investment according to the final classification result. The method can avoid the negative influence of the highly correlated factor on the model, and reduces the calculation cost at the same time.

The invention relates to a circuit breaker health state evaluation method and system, and belongs to the field of circuit breaker state evaluation. When the health state of the circuit breaker is evaluated, the used model is jointly constructed based on a PSO-AdaBoost-RF algorithm, that is, hyper-parameters in the RF algorithm are determined by using the PSO algorithm; parameters of each decision tree are adjusted through the training set, the decision trees are used as weak classifiers of an AdaBoost algorithm in the training process, and the weights of the weak classifiers are adjusted based on the AdaBoost algorithm; after training is completed, weighted summation is carried out on the weak classifiers with the adjusted weights to obtain a strong classifier of the AdaBoost algorithm, and the strong classifier serves as a classification model. After the corresponding classification model is obtained, online deployment is carried out on the classification model, then a mechanical characteristic curve when the circuit breaker acts is collected in real time, then the state quantity obtained according to the mechanical characteristic curve is input into the classification model, and evaluation of the health state of the circuit breaker can be achieved. According to the invention, faults can be identified in a short time, and the fault identification accuracy is high.