193results about How to "Improve diagnostic accuracy" patented technology

The invention discloses a multi-modal contrast learning fault diagnosis method for a small sample scene, and the method comprises the following steps: carrying out the enhancement of a one-dimensional signal and two-dimensional image fused fault data set through physical simulation for the small sample scene with scarce industrial fault data, and constructing a positive and negative sample pair through a plurality of data enhancement strategies; based on heterogeneous multi-modal fault data, designing a double-flow encoder architecture of a time sequence branch and an image branch, extracting depth features and mapping the depth features to a unified feature space through a projection head; performing supervised contrast learning pre-training based on intra-modal and inter-modal dual contrast loss; supervision fine tuning is carried out based on multiple loss functions such as physical guidance, so that accurate diagnosis of equipment faults is realized in a small sample scene. According to the fault diagnosis method under the unbalanced sample and limited labeling conditions, the problem that a traditional data driving model depends on large-scale labeling samples is effectively relieved through supervised comparative learning and cross-modal information alignment.

The invention discloses a power grid monitoring alarm event handling method and system based on a large model, and relates to the technical field of power systems, and the method comprises the steps: obtaining a historical sample of a power grid monitoring alarm event, and carrying out the preprocessing; constructing a balance training sample set based on a first large language model and resampling combined sample enhancement method; based on the pre-training language model, utilizing the balance training sample set to carry out fine tuning training, and constructing a power grid monitoring alarm event diagnosis model; on the basis of a second large language model, a power grid monitoring alarm event disposal model is constructed, and the disposal model is used for retrieving reference information from a historical disposal knowledge base in combination with an event type diagnosis result output by the diagnosis model and generating an auxiliary disposal suggestion for an input alarm event text; and integrating the diagnosis model and the disposal model to form a power grid monitoring alarm event disposal framework. According to the invention, intelligent diagnosis and auxiliary disposal of the power grid monitoring alarm are realized, and the diagnosis accuracy and the disposal efficiency are improved.

The invention discloses a bearing fault diagnosis method and system based on a simulated physical neural network. The method comprises the following steps: S1, preprocessing a collected vibration signal to obtain a to-be-diagnosed signal; s2, executing a hybrid optimization algorithm to obtain an optimal transmission band parameter and an optimal weight parameter; s3, configuring a feature extraction module according to the optimal transmission band parameter, and writing the optimal weight parameter into a classification module; s4, inputting the to-be-diagnosed signal into a feature extraction module to obtain a simulation feature vector; s5, inputting the simulation feature vector into a classification module, and outputting a classification voltage signal; and S6, determining a fault type, and outputting a result. According to the method, a hybrid optimization algorithm is adopted, the ratio of the inter-class dispersion degree to the intra-class polymerization degree of the feature vectors is calculated, optimal adaptation of feature extraction and classification tasks is achieved, and the diagnosis precision and generalization ability are improved; by constructing a full analog domain signal processing architecture, analog-to-digital conversion and digital calculation are not needed, and microwatt-level power consumption and microsecond-level real-time response are realized.

The invention discloses an electromechanical equipment fault cross-domain diagnosis method and system based on minimum category confusion, and the method comprises the steps: selecting an external public data set or labeled historical data as a source domain data set, and then collecting the real-time operation data of electromechanical equipment to be diagnosed, taking the real-time operation data of the electromechanical equipment to be diagnosed as a target domain data set; constructing a fault diagnosis model; performing joint adversarial training on the fault diagnosis model by using the preprocessed source domain data set and target domain data set, and performing lightweight processing and parameter solidification after training is completed to obtain a final fault diagnosis model; and deploying the final fault diagnosis model to an edge computing equipment end, and diagnosing the preprocessed real-time fault data of the electromechanical equipment by using the final fault diagnosis model to obtain a diagnosis result. According to the method, the multi-scale feature extractor is adopted to perform multi-scale feature extraction and fusion, so that the feature extraction capability is improved, and missing of key features is avoided.

The utility model relates to connecting pipe technical field discloses a high quality visual electronic cystoscope catheter, including operation handle, the outside fixed connection of operation handle has endoscope catheter, the inside slide connection of endoscope catheter has connecting pipe, the outside fixed connection of connecting pipe has curved end, the outside of operation handle is equipped with a plurality of limit slot, the outside slide connection of limit slot has telescopic mechanism, the outside fixed connection of operation handle has quick -witted mechanism, telescopic mechanism includes follow -up block no.

The application provides a die cutting and hot stamping equipment intelligent state monitoring and fault diagnosis system and method, and relates to the field of intelligent monitoring.The method comprises the following steps: collecting working parameters of multiple key parts of the die cutting and hot stamping equipment, constructing a time sequence collection window, slidingly collecting the working parameters, and obtaining characteristic information reflecting the equipment state; based on the characteristic information, constructing an anomaly detection model, performing anomaly detection on the equipment state, obtaining an anomaly score, and judging whether the equipment state is abnormal according to the anomaly score; for the characteristic information judged as abnormal, constructing a fault diagnosis model based on the fault type to which the characteristic information belongs, performing fault diagnosis on the equipment state, and generating a diagnosis result; and generating a comprehensive diagnosis and operation and maintenance decision report according to the diagnosis result.The application realizes comprehensive perception of the internal state of a closed host through multi-sensor collaborative monitoring and dynamic time sequence collection, breaks through the limitations of traditional monitoring, and provides accurate data basis for early fault warning and predictive maintenance.

The application discloses a variable working condition cross-component causal coupling modeling and fault diagnosis method and device, and relates to the technical field of rotating machinery fault diagnosis. The method comprises the following steps: collecting and preprocessing multi-component signals under variable rotating speed working conditions of a rotating machinery; based on multivariate Granger causal modeling, prior information and dynamic disturbance information are fused to construct a dynamic causal diagram; a double-view structure of a main view of the dynamic causal diagram and an auxiliary view of a correlation diagram is constructed, multi-scale coupling features are extracted through a multi-order spectrum filter and an attention mechanism, a symmetric InfoNCE contrast learning loss and a supervised classification loss are combined to optimize and train a model, and fault classification is realized. The device is correspondingly provided with signal acquisition, dynamic causal diagram construction, feature fusion, model training and fault prediction modules. The application improves the accuracy of fault feature representation and the robustness of diagnosis under variable working conditions, is suitable for complex industrial scenes with multi-component coupling and frequent rotating speed switching, and has strong engineering practicability.

The application provides a kind of laser physical experiment ultrafast image measurement system and method based on end side coordination architecture, it is related to laser physical experiment image measurement technical field, comprising the following steps: laser target shooting generates plasma, captures the X-ray signal image of plasma, generates original data stream;Through lightweight convolutional neural network model, the original data stream is handled, and the feedback control signal for adjusting the laser parameter of the next laser is generated;Obtain the laser parameter related to each physical parameter characteristic value, adjust the laser parameter related to the physical parameter characteristic value;Store the adjustment data each time, periodically train lightweight convolutional neural network model based on adjustment data.The advantage of the application is to realize the instant, reliable experimental parameter control in the experiment process.

The application discloses a three-dimensional detection and diagnosis simulation verification method and platform for tunnel apparent diseases and a storage medium. The method comprises the following steps: collecting point cloud data and image data of a tunnel model, performing difference analysis based on the two types of data to obtain an apparent detection result, and positioning a suspicious disease area of the tunnel model according to the apparent detection result. A machine learning model is used to analyze a disease diagnosis result corresponding to the suspicious disease area, and the disease diagnosis result is compared with preset real disease information of the tunnel model, and a comparison result obtained can be used to optimize the machine learning model. The scheme avoids the limitations of real vehicle verification and non-entity verification, and effectively improves the verification effect and verification efficiency of the machine learning model.

The present application belongs to the technical field of automobile parts detection, and particularly relates to a kind of tensioner online detection method and system.The system includes data acquisition subsystem, online analysis and diagnosis subsystem and multi-stage warning subsystem;Data acquisition subsystem synchronously acquires tensioner working condition data through multi-source sensor array, online analysis and diagnosis subsystem fuses latent variable feature extraction, blind source separation and independent component analysis functions, realizes tensioner health state detection, fault accurate identification and positioning by constructing frequency constraint, envelope constraint and similarity constraint, and can also simultaneously predict residual life.The present application solves the defects of low efficiency of traditional offline detection, inability to reflect real working state and insufficient fault positioning accuracy, realizes real-time detection of tensioner under multiple working conditions, has high detection accuracy and strong robustness, and is suitable for full life cycle monitoring of automobile engine tensioner.

The application discloses a health baseline construction and fault diagnosis method based on a twin residual network, and comprises the following steps: dividing a diagnosis signal into three parts of a pre-training data set, a training data set and a test data set, and performing normalization processing; constructing a twin residual network, and training a residual network feature extraction part in the twin residual network by using the pre-training data set to form a health baseline model; taking out the residual network feature extraction part in the health baseline model to construct a residual network diagnosis model, and training the residual network diagnosis model by using the training data set; and performing fault diagnosis test on the trained residual network diagnosis model by using the test data set, and evaluating network performance.

The application discloses a mechanical and electrical equipment and electrical equipment remote AI monitoring system based on a management platform, and relates to the technical field of equipment monitoring.The application comprises a data server, a display unit and a control unit, the control unit comprises an edge computing layer, a data acquisition layer and an AI analysis engine, the AI analysis engine comprises a deep learning module, a photovoltaic optimization module, an agent cluster and a fault tracing module, the output end of the data acquisition layer is connected with the input end of the edge computing layer, the port of the edge computing layer is in bidirectional communication with the port of the data server, and the output end of the edge computing layer is connected with the input end of the deep learning module and the photovoltaic optimization module respectively.The application adopts multiple agent learning technologies, can realize sharing of model parameter updating among multiple parks, protects local data privacy at the same time, constructs an industry expert rule library, cross-verify with deep learning results, and avoids misjudgment caused by the black box model.

This application discloses an AI-powered intelligent diagnostic system for AC / DC power supplies in substations. By dynamically adjusting the data acquisition frequency and preprocessing algorithm parameters, it first achieves a balance between data acquisition quality and resource consumption. Furthermore, the adjustment process is combined with the real-time operating conditions of the equipment, making the acquired data more valuable. Through online dynamic fusion diagnosis of the first and second models, it overcomes the limitations of a single model, improves the accuracy of early fault diagnosis, and partially solves the problem of performance degradation of a single model over time. The two models use continuously generated time-series feature vector streams as the basis for diagnosis and continuously learn from diagnostic data and results as new samples, thereby continuously improving diagnostic accuracy. By combining the fusion diagnosis with the preliminary fault hypothesis set constructed for the equipment and generating classified handling suggestions through steps F1-F2, it reduces the false alarm rate of equipment and AC / DC power supply systems in substations and achieves flexible control over the urgency of maintenance.

The application discloses a water and fertilizer management control method based on image data processing, samples each sampling unit of a to-be-controlled land plot, obtains a synchronous nutrient change curve and an extreme weather influence factor, and constructs a soil-crop-climate three-dimensional reference library; performs radiation correction, spectral calibration and real-time correction of spectral drift on a hyperspectral sensor; generates a dynamic collection time table, collects crop spectral data; automatically identifies an optimal sensitive wave band based on a random forest model, extracts spectral waveform features of the optimal sensitive wave band; compares the spectral waveform features with data of a same land plot in a designated period in the reference library in time sequence, calculates a nutrient change rate, constructs a two-dimensional diagnostic matrix of static content+dynamic trend, and obtains a nutrient deficiency type and a nutrient gap amount; constructs a multi-objective optimization function based on the nutrient deficiency type and the nutrient gap amount, calculates target fertilizer application amounts of each sampling unit and a fertilizer formula to obtain a fertilization scheme and executes the fertilization scheme, and realizes transformation from experience fertilization to data-driven precision fertilization.

This invention belongs to the fields of medical image processing and deep learning technology. It discloses a pathological image classification method and system combining stable learning and hybrid enhancement. The method involves acquiring a pathological image dataset, dividing it into a training set, a validation set, a test set, and an external validation set, and preprocessing the dataset. A deep learning network combining stable learning and hybrid enhancement is constructed and trained using the training set. The optimal deep learning network model is obtained using the validation set. The test set and the external validation set are input into the optimal deep learning network model to output the pathological image classification results. This invention utilizes a well-fitting pathological image classification model to effectively improve the overfitting problem and weak recognition ability of traditional models for domain-biased data, enhancing the recognition accuracy of independent and identically distributed data, improving the robustness and generalization ability of the pathological image classification model, and increasing the diagnostic accuracy of pathological images.

The application discloses a resource self-adaptive federated learning multi-modal knee osteoarthritis auxiliary diagnosis method, which comprises the following steps: a server initializes a multi-modal model for knee osteoarthritis diagnosis, and pre-deploys a low-rank adaptive plug-in in a trainable layer; after a client reports local hardware resources, the server allocates a resource echelon and issues a two-dimensional clipping ratio; the client clips the model in depth and width based on the clipping ratio, activates a LoRA module of a specified layer, loads local knee osteoarthritis X-ray images and clinical text data for multi-modal training, and establishes semantic mapping of image features and clinical descriptions; the client only uploads an activated LoRA parameter update amount, the server aggregates and optimizes a global model through weighted average aggregation and key layer compensation; and the learning ability of the model to key discriminative features of knee osteoarthritis is strengthened in combination with real-time resource monitoring and knowledge distillation. The application covers heterogeneous computing power devices through a resource self-adaptive mechanism, and improves the participation efficiency of primary medical institutions.

The invention relates to the technical field of medical image and artificial intelligence technology crossing, in particular to an intelligent auxiliary diagnosis method and system for a frozen section in a thyroid cancer operation. According to the technical scheme, the method comprises the following steps that a thyroid tissue intraoperative frozen section to be diagnosed is prepared, and the frozen section does not need to be dyed or subjected to section sealing treatment; and scanning the frozen section by using a terahertz near-field imaging system to obtain terahertz near-field image data of the frozen section. According to the method, the terahertz near-field imaging technology is adopted, the situation that cell nucleus morphology is difficult to observe due to ice crystal artifacts in a traditional frozen section is avoided, cancer cells are automatically recognized in combination with an AI model trained based on large-scale labeling data, and the objectivity and consistency of diagnosis are remarkably improved; meanwhile, the steps of dyeing and mounting are omitted, and rapid imaging and analysis are realized, so that the intraoperative diagnosis time is greatly shortened, and a generated visual contour report also provides visual decision support for pathologists.

The invention relates to the technical field of rehabilitation evaluation, and discloses a fracture and complication integrated synchronous intervention rehabilitation treatment evaluation system, which comprises a sensing array, a reference sensing node and an evaluation unit, and is characterized in that the sensing array is arranged on an affected side limb and comprises an impedance monitoring electrode and a heat flow sensing unit; the reference sensing node is used for acquiring a system metabolism reference parameter, the evaluation unit establishes a synchronous acquisition trigger reference according to characteristic offset of interface capacitance along with a load, normalizes a heat flux density relative to the system metabolism reference parameter, calculates a response characteristic value representing microcirculation remodeling capability, identifies a blood vessel backflow state, and evaluates the blood vessel backflow state. Physical level synchronization of physiological signals and load excitation is achieved through interface polarization response, compensatory gait interference is counteracted, blood deposition and tissue effusion are distinguished, and a real-time safety boundary is provided for a rehabilitation scheme.

A flight control abnormal data analysis and fault diagnosis method, system, product and medium based on a generative adversarial network relate to the field of aircraft fault diagnosis. The method comprises: acquiring flight control multi-channel time series data to construct a three-dimensional tensor; extracting its spatio-temporal joint features to obtain a fusion embedding representation representing time dependence and multi-channel physical coupling; inputting flight working conditions into a generation network, combining the embedding representation to obtain enhanced fault samples; constructing a multi-class classification network sharing feature extraction parameters with the generation network; inputting real and enhanced samples into the network, jointly calculating reconstruction and classification losses for end-to-end parameter updating to obtain a diagnosis network; inputting test data into the diagnosis network, calculating an abnormal score based on the reconstruction loss and locating a specific fault type based on the prediction probability. The technical solution provided in the application improves the fault type diagnosis accuracy under complex flight conditions.

The invention is suitable for the technical field of mechanical equipment state monitoring and fault diagnosis, and provides a mine main conveying chain equipment bearing fault embedded diagnosis system and method.The mine main conveying chain equipment bearing fault embedded diagnosis system comprises a tunable piezoelectric energy collecting device which is installed on a bearing seat or a carrier roller shaft and used for converting vibration mechanical energy of a bearing into electric energy, a voltage signal representing the vibration state of the carrier roller bearing is synchronously output; the embedded wireless sensor node is electrically connected with the tunable piezoelectric energy collecting device and is used for managing the collected energy and processing and wirelessly transmitting the voltage signal; and the fault diagnosis module receives the voltage signal and performs feature extraction and fault classification on the bearing state based on a convolutional neural network algorithm. According to the invention, sensing and energy supply integration, frequency adaptive matching, high-quality signal acquisition and lossless embedded installation are realized, and a reliable, long-term and self-energy-supply bearing state in-situ monitoring and intelligent diagnosis scheme is provided for rotating mechanical equipment in various mine main transportation chain equipment.

The invention relates to the technical field of intelligent operation and maintenance of power equipment, and discloses an AmRMR-based transformer adaptive fault diagnosis method and system, and the method comprises the steps: obtaining the detection data of dissolved gas in transformer oil, and constructing a candidate ratio feature set; respectively carrying out standardization processing on the key gas concentration characteristics and the candidate ratio characteristic set; performing discretization operation on the standardized candidate ratio feature set; performing redundancy compression and information contribution evaluation on the discretized candidate ratio features based on an AmRMR algorithm, and outputting a key ratio feature set; and inputting the key gas concentration characteristics and the key ratio characteristic set into a pre-constructed DSD-DQN fault diagnosis model, and outputting a transformer fault diagnosis result. According to the invention, the highest engineering risk that the fault is misjudged to be normal can be effectively avoided, the recognition capability of minority samples such as serious faults is remarkably improved, and transformer fault diagnosis considering engineering safety and diagnosis accuracy is realized.

The application provides a rolling stock running part fault diagnosis model training method, a diagnosis method and equipment, and relates to the technical field of vehicle fault diagnosis. The method comprises the following steps: establishing a coupling system digital twin model corresponding to a rolling stock-track coupling system according to the dynamic parameters of a target rolling stock and the running monitoring data in a normal healthy state; obtaining experimental monitoring data of the target rolling stock in the normal healthy state and a set fault working condition based on a rolling stock rolling-vibration bench experiment, and obtaining simulation monitoring data of the target rolling stock in the set fault working condition based on the twin model; performing sample segmentation and labeling on the experimental monitoring data and the simulation monitoring data respectively, obtaining source domain and auxiliary domain data to generate a combined domain data set, training an initial diagnosis model to obtain a trained domain generalization model as a rolling stock running part fault diagnosis model of the target rolling stock. The application can improve the accuracy and reliability of rolling stock running part fault diagnosis.

The invention discloses a traditional Chinese and western medicine fusion data analysis system and method based on a multi-mode sensor, and belongs to the technical field of intelligent medical treatment. The system comprises: (1) a tongue diagnosis module, which collects tongue images through a multispectral camera (400-1000nm), and extracts HSV color features (resolution of 0.1 degree) and LBP texture features (radius of 3 pixels); the pulse diagnosis module (2) adopts a laser Doppler sensor (850nm) to obtain a radial artery signal, and extracts pulse position / pulse potential / pulse shape three-dimensional features (sample entropy lt, 1.2 represents chordwise astringent pulse) through wavelet transform; and (3) the data processing module inputs the tongue vein features, fasting blood glucose (blood glucose + / -0.3 mmol / L precision), C-reactive protein and other western medicine biochemical indexes into a fusion decision model, dynamically distributes traditional Chinese medicine and western medicine weights (for example, the traditional Chinese medicine weight is smaller than or equal to 40% when the C-reactive protein is larger than 10 mg / L) through a typhoid miscellaneous disease rule base and a random forest algorithm, and generates physical feature vectors for health state classification. Organic cooperation of traditional Chinese medicine physical sign quantitative analysis and western medicine evidence-based medicine is achieved, the early-stage diabetes screening accuracy rate is improved by 23.7% (compared with single-mode diagnosis), and the method is suitable for family health monitoring and traditional Chinese and western medicine combined diagnosis and treatment.

The invention discloses a qualitative detection method for a loosening fault of a foundation bolt of a reciprocating engine. The qualitative detection method comprises the following steps: step 1, respectively collecting vibration signals of the foundation bolt in a normal state and a fault state in an engine operation state; step 2, obtaining a corresponding speed signal; 3, calculating an average effective value, a difference value and a relative change rate of vibration acceleration signals of the body supporting seat and the foundation in normal and fault states; 4, the average effective value, the difference value and the relative change rate of the vibration speed signals of the body supporting seat and the foundation in the normal and fault states are calculated; 5, the relative change rate of the two feature values is calculated, and whether the engine breaks down or not is judged; 6, calculating an average amplitude spectrum and a difference spectrum of the normal and fault state speed signals; 7, extracting a frequency component, and calculating an energy ratio; and 8, comprehensively judging whether a foundation bolt loosening fault occurs or not. According to the invention, qualitative detection of the loosening fault of the engine foundation bolt can be accurately and efficiently realized.

The invention discloses a singular value decomposition sub-signal selection method for rotating machine fault diagnosis, and belongs to the technical field of rotating machine state monitoring and fault diagnosis. The method comprises the following steps: receiving an original vibration signal of the rotating machine, and adaptively determining the optimal decomposition times of singular value decomposition through exhaustion search by taking the number of periodic pulse quantized values as an optimization target; constructing a Hankel matrix for the original vibration signal and performing singular value decomposition to obtain a group of sub-signals; the square envelope of each sub-signal is calculated, the periodic pulse performance of each sub-signal is quantized, a clustering guide line is drawn, and key sub-signals are screened out; continuously adjacent key sub-signals are classified into one class for reconstruction mixing, fault components are formed for envelope spectrum analysis, and rotating machine fault diagnosis is achieved. According to the invention, periodic impact components related to faults in the signals can be effectively highlighted, and the accuracy and reliability of composite fault diagnosis of the rotating machinery under complex working conditions are remarkably improved.

The application discloses a bearing fault diagnosis method and system based on a CS-SHAP model, bearing operation signals are collected through acceleration, temperature and acoustic emission multi-sensor, multi-dimensional fault features are extracted from time domain, frequency domain and time-frequency domain after wavelet transform or EMD algorithm denoising to complete preprocessing, feature data is divided into similar clusters by K-means clustering, SHAP values are calculated cluster by cluster and weighted according to cluster data density or diagnosis influence degree to obtain feature importance score, a SVM classifier based on RBF kernel function is trained with screened key features, model parameters are optimized through 5-fold cross validation, new collected data is preprocessed and input into the trained model to obtain diagnosis results, feature SHAP values are calculated and visualized by using the CS-SHAP model, and key factors of faults are analyzed. The application realizes accurate diagnosis of bearing faults and interpretability of diagnosis results, and provides technical support for intelligent operation and maintenance of industrial equipment.

This invention discloses a fault diagnosis method, system, and device for inverters, relating to the technical field of fault diagnosis. The method involves acquiring the original signal set of a three-phase inverter and performing a Fast Fourier Transform (FFT) to obtain three-phase frequency domain signals. After transforming each three-phase frequency domain signal, the signals are fused to obtain fault image samples, which are then divided into training and testing sets. A preset image set is acquired, and the backbone network is pre-trained to obtain pre-trained weights. These pre-trained weights are then transferred to an improved model to obtain a preset model. The preset model is then fine-tuned to obtain a target model. The target model is tested to obtain classification results and is validated. The three-phase current is transformed to the frequency domain via FFT to highlight harmonic and imbalance characteristics. A two-dimensional fault image is generated using symmetric point pattern fusion. Pre-trained weights and staged transfer fine-tuning reduce dependence on small sample fault data and improve model generalization ability. The improved model achieves accurate classification, improving diagnostic accuracy and generalizability even with scarce samples.

The application belongs to the technical field of pathological grading, and particularly relates to a lymphoma histological grading method, which comprises the following steps: screening a plurality of regions of interest rich in diagnostic information in a lymphoma pathological section image; inputting the regions of interest into a trained Hover-Net nuclear segmentation model to output a cell separation image; the cell separation image can mark the regions of different cell types, the positions of each cell and the classification information thereof; inputting the cell separation image into a classifier to output a histological grading result and the number of each cell type. The application improves the diagnostic accuracy and efficiency of follicular lymphoma pathological grading by efficiently recognizing lymphoma pathological section images of different pathological grades through a Hover-Net nuclear segmentation model.

The invention discloses a wind turbine generator gearbox state monitoring and fault early warning method and system. The method comprises the following steps: defining a key part of a gearbox of a wind turbine generator as a flexible body, and constructing a multi-body dynamic model based on the flexible body; the multi-body dynamics model receives input multi-source time sequence data, then performs feature extraction and multi-index fault early warning algorithm processing, and outputs signal abnormal information for the current multi-source time sequence data; the signal abnormal information is gearbox fault data; constructing a mixed data set guided by a physical mechanism and performing data enhancement; and inputting a spatial-temporal feature coding fault diagnosis model based on the enhanced mixed data set, and then outputting a health index. According to the intelligent early warning system for the wind turbine generator gearbox, through the technical innovation of making up for data missing through modeling simulation, improving diagnosis precision through an intelligent algorithm and guaranteeing real-time early warning through edge calculation, a set of intelligent early warning system for the wind turbine generator gearbox which is high in precision, low in time delay and strong in generalization is successfully constructed.

This invention provides a non-contact method and device for distribution network fault identification and classification, belonging to the field of distribution network fault detection technology. The method includes: acquiring distance information between the detection device and the tower; adaptively selecting a detection mode based on the distance information; collecting electromagnetic field information around the tower using a non-contact electromagnetic sensor and converting it into characteristic current information; classifying and judging based on the characteristic current amplitude to distinguish between normal, potential fault, and fault states; extracting time-frequency domain features of the waveform under fault states and identifying the fault type through a classification model; and outputting diagnostic results based on location information. This invention supports live-line, non-contact operation, is suitable for complex environments and high-altitude lines, and has advantages such as safe detection, strong adaptability, and accurate diagnosis, enabling early warning and intelligent classification of distribution network faults.