365 results about "Unbalanced data" patented technology

A full-link reconciliation method based on a snowflake algorithm, an apparatus, a device, and a medium are provided. The method includes: responding to a reconciliation request of a cross-border service and acquiring bill source data from a service end; parsing the bill source data, and converting the bill source data into target bill data; calling a reconciliation rule engine to acquire a corresponding reconciliation rule, selecting a corresponding reconciliation algorithm, and performing a full-link reconciliation task on the target bill data to acquire a reconciliation result; transmitting unbalanced data to a corresponding exception processing system for a check processing of abnormal data; generating, based on an optimized snowflake algorithm, a unique target ID to perform a corresponding bill association with the reconciliation result, automatically penetrating, according to the unique target ID corresponding to the reconciliation result, full link data of an information flow and a fund flow, and tracing, according to the unique target ID, a whole process of the corresponding bill flowing between the fund flow and the information flow, to achieve a complete closed-loop of reconciliation.

The invention discloses a main and distribution cooperative fault detection method and device based on a Mama network, and a medium. The method comprises the following steps: S1, measuring fault data of a main network and a distribution network, and constructing a training set; s2, representing a topological structure of the main and distribution network through an adjacent matrix of the graph, constructing the adjacent matrix and an edge feature matrix of the graph, and defining the weight of edges to obtain an edge feature matrix E and a feature matrix X as priori knowledge; s3, constructing a Mama network model based on the prior knowledge and the measurement data, wherein the Mama network model comprises a time sequence feature extraction network LSTM, a graph convolutional neural network, a prior knowledge and feature fusion module, a Softmax layer and a Mama network; and S4, training and testing the Mama network model by using the training set and adopting a joint loss function. According to the method, information propagation can be optimized, the calculation complexity is low, the unbalanced data processing capacity in the main and distribution cooperative power grid is effectively improved, and the model training precision and effect are improved.

The invention relates to a bearing unbalance fault diagnosis method and system cooperatively guided by double classifiers, and the method comprises the steps: collecting bearing vibration signals in each health state under different working conditions, carrying out the fast Fourier transform, converting the signals into frequency domain signals, obtaining a data set, and carrying out the classification of the data set; dividing the data set into source domain data and target domain data under different working conditions, and marking the source domain data; constructing a fault diagnosis model, wherein the fault diagnosis model comprises a shared feature extractor, a balance classifier and a standard classifier; constructing a loss function based on the source domain data and the target domain data; training the fault diagnosis model by using a loss function to obtain a trained fault diagnosis model; and inputting a vibration signal of the bearing to be detected into the trained fault diagnosis model to obtain a fault diagnosis result. The problems that in the prior art, the performance of a diagnosis model is scarce by labels, data distribution is unbalanced, and the generalization ability of the model is improved can be solved.

The invention discloses a heart sound-electrocardio multi-modal fusion detection method based on federal learning. According to the method, collaborative fusion of multi-modal information of heart sound and electrocardio data is achieved through a cross-modal collaborative attention mechanism, the comprehensive performance of federal learning is effectively improved, and the detection accuracy of a federal model is remarkably improved; meanwhile, by introducing a weight distribution mechanism, the adaptability of the model to the imbalance of each modal data is enhanced; a differential privacy protection technology is introduced to enhance the safe aggregation of model parameters; and the method has better robustness and privacy protection in practical application.

The invention discloses a dynamic multivariate time sequence-oriented infrastructure load prediction method, which comprises the following steps of: predicting an infrastructure load by adopting a trained prediction model, segmenting acquired multivariate time sequence data, querying based on time steps and nodes of input segmented data to obtain a space-time pattern vector, and predicting the load of the infrastructure by adopting a dynamic multivariate time sequence-oriented infrastructure load prediction model. A sequence mode vector is obtained based on input segmented data query, the space-time mode vector and the sequence mode vector are spliced into a dual-mode vector output by a dual-mode pool module, and then in a dynamic MTS encoder, the dual-mode vector and segment embedding representation are spliced to obtain a final feature vector; and finally, inputting the final feature vector into a multi-scale decoder for decoding to obtain a prediction result. Aiming at challenges such as data imbalance, data missing and space-time dependence erosion, the accuracy of a prediction result is improved under the condition that repeated training is not needed, repeated training needed during topological change is avoided, and the robustness, prediction precision and calculation efficiency of the model are improved.

The invention discloses an unbalanced sample-oriented interactive fault diagnosis method and device and a storage medium, and belongs to the field of fault diagnosis. The method comprises the following steps: firstly, acquiring operation monitoring data of a target object, and dynamically extracting time domain / frequency domain features through a sliding window algorithm to construct a mixed feature vector; and then, extracting a preset global key feature value from the mixed feature vector, and inputting the preset global key feature value into a trained fault diagnosis model to directly output a classification result. Wherein in the training process of the fault diagnosis model, original unbalance data is converted into a class equilibrium data set by using a CGAN network integrated with a sliding window, the global contribution degree of features is quantified based on an SHAP algorithm, a Top-K key feature set is dynamically locked in combination with man-machine interaction feedback, feature representation is enhanced through a feature adaptive weighted fusion network, and the fault diagnosis model is obtained. And a focus loss function is adopted to train a LightGBM classifier to focus a minority class of samples, so that the diagnosis performance and reliability of the fault diagnosis model under the unbalanced data are improved.

The invention discloses an object classification method, a classification model training method, related equipment and a program product, and relates to the technical field of machine learning. The method comprises the steps of obtaining parameter data of a to-be-classified object; performing feature extraction on the parameter data to obtain parameter features; the parameter features are sent to a classification model to obtain a classification result, the classification model is obtained by training a random forest model through a reinforcement learning strategy, and the weight parameter of each decision tree in the random forest model is updated and fixed in the reinforcement learning training process. Through the reinforcement learning strategy, the weight of the decision tree can be automatically adjusted, so that the classification accuracy and robustness of the classification model on complex and unbalanced data are improved. In addition, compared with a deep learning model, the parameter quantity is smaller, and the required computing resources are lower.

The invention discloses a power transmission and transformation equipment fault risk assessment method and system in extremely severe weather, and the method and system improve the fault detection effect through the cloud-side intelligent cooperation technology, a self-learning federated learning mechanism and the construction of a risk map. Power transmission line fault detection based on cloud edge cooperation is composed of an edge end and a cloud end. The edge end comprises a hidden danger identification module, a data acquisition module and an algorithm iteration module. And the cloud is responsible for integrating and globally updating the model and the map. A self-learning federated learning method is used, the edge ends use own data to train a model, and model parameter data uploaded to the cloud end by each edge end are updated globally at the cloud end and deployed to each edge end. The phenomenon that the recognition capability is low due to unbalanced data collection at the edge end, missing of sample categories and overfitting is avoided, and the problem that the transmission pressure of a network channel is too large is solved.

The invention discloses a transformer fault diagnosis method based on a time-frequency domain feature interactive fusion network. The method comprises the following steps: data collection: collecting a data set of dissolved characteristic gas in transformer oil with a marked type; data preprocessing: removing obvious error data through data cleaning, and then processing unbalanced data by using oversampling and downsampling; fault type judgment is carried out based on three pairs of ratio coding combinations of gas; network construction: constructing an interactive fusion network based on time-frequency domain features; network training: inputting the training data set into the constructed network for network training; and fault classification: inputting the test data set into the trained time-frequency domain feature-based interactive fusion network to obtain a classification result. The method improves the feature expression capability, reduces the overfitting risk, improves the accuracy and efficiency of fault diagnosis, and can be used in the field of transformer operation and maintenance.

The invention discloses a pulmonary tuberculosis image classification and recognition system based on feature aggregation and focus area perception, and the system comprises the steps: carrying out the local and global feature extraction and fusion of a pulmonary tuberculosis image through a feature extraction subsystem; the method comprises the following steps: constructing a graph structure of fusion features through a pulmonary tuberculosis classification subsystem based on focus area perception, dynamically aggregating node information, realizing three classifications of health, tuberculosis and disease but non-tuberculosis in a first stage, and carrying out active tuberculosis and old tuberculosis subdivision in a second stage on a pulmonary tuberculosis image in combination with focus structure features; through an unbalanced data set processing subsystem based on characteristic aggregation and dynamic data amplification, under-sampling is carried out on the characteristic that active tuberculosis data samples are large by adopting a characteristic aggregation technology, and resampling is carried out on old tuberculosis with few data samples by implementing a dynamic data amplification strategy; and key information learned from active tuberculosis categories is reserved through a knowledge distillation mechanism, so that more accurate focus recognition and classification are realized.

The invention discloses a radiology report generation method and system based on visual collaborative enhancement and a cross-modal fusion network, and belongs to the technical field of natural language processing. According to the invention, a visual collaborative enhancement module is designed for modeling visual features from global and local perspectives to enhance the recognition of abnormal lesions in a radiology image, so that the attention deviation of an abnormal region caused by unbalanced data distribution is relieved. Meanwhile, a cross-modal information fusion device is provided, the module utilizes a novel double cross-modal communication component to promote multi-level fusion of visual and text information, the problem of modal isomerism is solved, and semantic-level feature alignment and refinement are achieved. According to the method, the problem that a model cannot capture key focus features due to unbalanced data distribution in a radiology image is solved, and the problem that effective alignment and fusion are difficult due to the fact that feature spaces of different modal information of image and text information are different is solved.

The invention discloses an unbalanced bearing fault diagnosis method and system based on dynamic feature optimization. The method comprises the following steps: S1, constructing a diagnosis system framework comprising a sample generation and enhancement module and a dynamic penalty feature optimization module; s2, bearing vibration signal data are collected, overlapped sampling preprocessing is carried out, and an unbalanced data set is constructed; s3, in a sample generation and enhancement module, a self-attention condition diffusion model is adopted to generate a balanced fault sample; s4, in a dynamic penalty feature optimization module, using a multi-scale feature extractor to extract fault features, and using a dynamic penalty feature optimization algorithm to adjust feature weights; s5, calculating the importance of each feature based on the SHAP value, dynamically updating the feature weight, and optimizing the sensitivity of the model to the key fault feature; and S6, training a fault diagnosis model by using the optimized features to realize high-precision bearing fault classification, and circularly adjusting the feature weight in the next round of training to continuously improve the diagnosis performance.

The invention discloses a tire defect detection method based on anomaly detection and a conditional generative adversarial network, and the method comprises the steps: inputting a to-be-detected tire image into a tire defect detection model, and obtaining a defect detection result; the tire defect detection model is obtained by taking a total training data set as a training set for training; the training data total set is obtained by expanding a real data set by applying an auxiliary classification generative adversarial network based on feature reconstruction, and attention modules with abnormal weights are embedded in a generator and a discriminator of the auxiliary classification generative adversarial network based on feature reconstruction. The attention module with the abnormal weight is a CBAM attention module combined with an abnormal weight matrix. According to the method, the quality of the training set is improved through the generative data enhancement model, and the method is suitable for a small sample unbalanced data environment; the data enhancement effect is improved through the idea of feature reconstruction and the attention module with the abnormal weight; detection precision is high and an application prospect is good.

The invention discloses a privacy protection recommendation method based on graph federal learning, and belongs to the technical field of intelligent recommendation. The method mainly comprises the following steps: a client receives an initial weight, and constructs an initial user-article interaction graph based on user local data; modeling interaction between nodes on the initial user-article interaction graph based on the graph neural network and the initial weight; training the local user-article interaction model based on user local data; the server side aggregates the article embedding matrix gradient uploaded by each client side; the server side clusters the updated article embedding matrix to generate a sampling article set; and the client performs multi-task joint training based on self-supervised learning on the local user-article interaction model based on the user local interaction subgraph, and performs article recommendation based on the trained local user-article interaction model. The problem of unbalanced data distribution can be relieved, and meanwhile the risk of user privacy disclosure is reduced.

A system and method for facilitating training of large language model based recommender systems are provided. The system may utilize one or more LLMs to create probability distributions for binary classification tasks associated with specific user-item pairs. The probabilities may be utilized to rank one or more tasks directly. The training of the one or more LLMs may involve the use of Knowledge Distillation methods and may be based on incorporating a dual-label system such as, for example, hard labels and soft labels. The one or more LLMs training data may consist of user-item pairs and their corresponding features. The labels used in the training process may include binary classification labels and their respective probabilities. The system may further implement the trained one or more LLMs to determine rankings or recommendations associated with user engagement of one or more content items.

The invention discloses a coal mill unbalanced data fault diagnosis method based on a Bayesian network, and belongs to the field of generalized zero sample fault diagnosis of a thermal power generation feed pump set. Aiming at the problems of unbalanced fault data distribution, difficult minority class fault diagnosis and poor result interpretability in an industrial scene, sample distribution is collaboratively optimized through SMOTE data enhancement and Dirichlet prior smoothing, a three-layer causal topology network of'fault layer-attribute layer-observation layer 'is constructed, expert knowledge constraint and data-driven learning are combined, and the fault layer-attribute layer-observation layer-based fault diagnosis method is established. High-precision fault classification is realized; a dual-mode diagnosis mechanism is designed, fault node direct inference and attribute node indirect inference are synchronously supported, and explainable physical-level diagnosis guidance is provided while the fault diagnosis accuracy is guaranteed. The method is successfully applied to a coal mill system of a coal-fired unit, and can be expanded to transparent intelligent operation and maintenance of complex industrial equipment.

The invention provides a bridge design method and system based on pushing displacement and rigidity inversion, and belongs to the technical field of bridge design. A theoretical formula among the axial force of each span of steel box girder, the displacement of each pier and the anti-pushing rigidity of the piers under the condition of system temperature change after each pushing in the walking pushing construction process is deduced, and actual monitoring data of the beam length change of the steel box girder in the walking pushing construction process are combined; numerical analysis software is used for carrying out inversion analysis on the anti-thrust stiffness of each pier, the curve trend of the anti-thrust stiffness changing along with the temperature difference under the theoretical condition is obtained, the theoretical analysis of the influence of the system temperature effect on the longitudinal bridge direction in the walking incremental launching construction process is perfected, and data support is provided for implementation of measures such as pier stiffness adjustment and displacement release in the follow-up process; by calculating the sparse parameters of the missing data, the adaptability to unbalanced data and the data noise redundancy are higher, and the method is suitable for missing data supplementation in the field of bridge design which is susceptible to natural factors.

As described herein, a base model based on imbalanced data may be selected for a machine learning process associated with a specific application. A first false positive error rate may be generated based on the selected base model. A plurality of imbalanced data sets may be generated based on the imbalanced data associated with the base model. A plurality of models may be generated based on the generated plurality of imbalanced data sets. A subset of the outputs of the plurality of models may be ensembled and a second false positive error rate may be generated based on the ensembled output of the subset of the plurality of models. The second false positive error rate may be determined to be less than the first false positive error rate.

The invention relates to an unbalanced data-oriented electric power system lightning disaster risk detection method, which comprises the following steps of: S1, gridding a target detection land parcel to obtain a plurality of grid units; S2, based on latitude and longitude coordinates of each grid unit, obtaining line parameters and environment characteristics of each grid unit in combination with a line database and a geographic information base, wherein the line parameters comprise tower height, span, grounding resistance, loop number, lightning arrester number and transformer capacity, and the environment characteristics comprise soil conductivity, building height and land utilization type; and S3, inputting the line parameters and the environment characteristics of each grid unit into a trained first detection model to obtain the thunder and lightning probability and the maximum peak current of each grid unit. Compared with the prior art, the multi-source data such as the tower height, the span, the grounding resistance and the soil conductivity are comprehensively considered, and the risk assessment result has higher regional adaptability and accuracy.

The invention relates to the technical field of leakage diagnosis, in particular to a gas pipeline leakage diagnosis method based on unbalanced data, and the method comprises the steps: collecting acoustic emission signals in different leakage states, and constructing a training and testing data set; performing principal component analysis on the time-frequency domain signal of the acoustic emission signal to obtain a related signal; reconstructing the related signal into a grayscale image; constructing a five-layer multi-layer feature extraction module of a four-layer structure convolution branch and a side convolution branch to perform feature extraction on the grayscale image; constructing a triple weighting module based on channel weighting, position weighting and identical mapping, and inputting an output feature map of the multi-level feature extraction module into the triple weighting module; and inputting the output characteristic pattern of the triple weighting module into a working condition discrimination module, and outputting the pipeline leakage type. The method solves the problem that the prediction accuracy of unbalanced data in the gas pipeline monitoring data under the normal working condition far more than the abnormal working condition needs to be improved.

The invention relates to a multi-modal medical image intracranial aneurysm segmentation method based on geometric deep learning, and the method comprises the steps: 1, designing a medical diffusion network based on a deep neural network of frequency domain convolution; 2, preprocessing the three-dimensional grid data to realize the manifold of the model and calculate the characteristics of the grid model; and step 3, using a multiple loss function to reduce the influence of the unbalanced data set, and the like. According to the method, the tedious process of manual feature design and multi-stage processing in a traditional segmentation method is avoided; the MedDiffusion Net designed by the method solves the problem of intracranial aneurysm segmentation of medical images of various modalities, and experimental results on MRA, CTA and DSA data show that the method can obtain accurate intracranial aneurysm segmentation without training data of different modalities respectively; and adaptively fusing the features in the neighborhood by learning a diffusion parameter t.

The invention relates to the technical field of unbalanced data processing, in particular to an oversampling method, system and device for avionics equipment test data and a medium, and the method comprises the steps: dividing original avionics equipment test data into minority class samples and majority class samples; respectively clustering the two types of samples by using a density peak value clustering algorithm, redistributing a new label according to a cluster to which each sample belongs, removing noise samples, and combining into a new unbalanced training set; constructing a sample generation model, and training the sample generation model with the new unbalanced training set until the sample generation model is converged to an equilibrium state; and determining the number of new and minority class samples required to be generated, and inputting the minority class samples in the new unbalanced training set into the trained sample generation model to obtain the required number of new and minority class samples. The method can highly fit and approach the real distribution of minority samples, enhance the comprehensiveness, diversity and fidelity of the generated samples, and effectively improve the performance of the sample generation model.

The invention discloses a water chilling unit fault diagnosis method and system for unbalanced data, and belongs to the field of water chilling unit fault diagnosis, and the method comprises the steps: restoring balance fault data with original data characteristics through employing original data based on a disturbance reconstruction mechanism; performing extraction and modeling on the time sequence characteristics and the space structure of the balance fault data by using a space-time automatic encoder, and reconstructing original data; respectively extracting time sequence features and topological features by utilizing a dynamic topological time sequence feature integration network, and performing adaptive fusion by adopting a dynamic gating fusion mechanism; and classifying the fused features to obtain a fault diagnosis result. According to the method, parallel generation of multiple types of fault samples is achieved, it is guaranteed that each type of generated fault data has similar time-space characteristics with original fault data, the method can adapt to the real-time changing working condition of the water chilling unit, collaborative modeling of time sequence characteristics and dynamic topological characteristics in a complex multi-sensor system of the water chilling unit is achieved, and the modeling efficiency is improved. And high-precision real-time diagnosis can also be realized on edge equipment.

The invention relates to an unbalanced bearing data fault diagnosis method based on an improved condition Wasserstein generative adversarial network. The problem of bearing data imbalance under a small sample condition is effectively relieved. According to the technical scheme, the method comprises the following steps: firstly, processing a bearing vibration signal by adopting a sliding window overlapping sampling strategy, and converting the bearing vibration signal into a time-frequency image by applying continuous wavelet transform so as to enhance fault feature representation; secondly, an improved condition Wasserstein generative adversarial network is used for carrying out data enhancement, the network measures sample distribution difference through a Wasserstein distance, introduces gradient penalty and L1 loss, combines spectrum normalization and a self-attention mechanism, stabilizes a training process and prevents gradient explosion, and meanwhile, generates a specific category of high-quality samples through condition information; and finally, carrying out accurate diagnosis by adopting a convolutional neural network equipped with a global attention mechanism. According to the method, the common collapse and instability problems of the generative adversarial network can be avoided, and the precise diagnosis of the rolling bearing can still be realized under the conditions of small samples and unbalanced data.

The invention provides a motor fault diagnosis method for unbalanced data in a noise environment based on a dual-scale network, and the method comprises the steps: collecting acceleration signals of motor vibration in a normal state and a fault state, and constructing a data set; building a fault diagnosis model based on a dual-scale network, wherein the fault diagnosis model comprises a wide convolution kernel 1D convolution module, an attention-based dual-scale module, a convolution-based feature fusion module, an attention 2D convolution layer and a classification module which are connected in sequence; based on the data set, using a category weighted loss function to train a fault diagnosis model based on a dual-scale network to obtain a trained fault diagnosis model; and inputting a motor vibration signal acquired in real time into the trained fault diagnosis model for fault diagnosis to obtain a fault type. According to the method, the influence of noise interference and uneven data on the neural network model is weakened by mining deep fault features and endowing different weights to the loss function.

The invention relates to a dynamic density guided generative adversarial network unbalanced data processing method (DAG-WGAN). The DAG-WGAN realizes unbalanced data processing through data preprocessing, dynamic density estimation and weight distribution, potential structure learning based on a variational auto-encoder (VAE), and density guide generation and dynamic feedback optimization based on WGAN-GP. The DAG-WGAN adaptively evaluates the sample density by using kernel density estimation (KDE) and a Gaussian kernel function, and allocates a weight for a generation process, thereby emphatically enhancing the low density and discriminating the sample generation of a difficult region. The VAE learns a potential manifold structure of a minority class of samples, realizes density-guided generation of a potential space under a WGAN-GP framework, and ensures diversity and manifold consistency of generated samples. In addition, a dynamic feedback mechanism is introduced, the weight and the gradient penalty coefficient are adaptively adjusted and generated, and the training stability and the sample generation robustness are improved.

The invention discloses a robot detection method and system based on a sample equalization strategy and a heterogeneous graph, belongs to the technical field of robot detection, effectively relieves the problem of unbalanced data distribution in robot detection through the sample equalization strategy, and combines the multi-relation modeling capability of the heterogeneous graph to improve the robot detection efficiency. And attention behaviors and semantic similarity among the users are fully mined, and the recognition precision of the social robot is remarkably improved. And feature information in different relational graphs is layered and aggregated by using a graph neural network, and multi-modal data is dynamically fused through a semantic attention mechanism, so that the analysis capability of the model on a complex social network relationship is enhanced. Meanwhile, noise interference is reduced through cooperative application of oversampling and undersampling, the generalization performance of the system on the camouflage behavior of the novel robot is further improved, and the robustness and reliability of a detection result in different application scenes are ensured.

The invention discloses a bridge disease detection and positioning method and device based on 2D-3D data fusion, and the method can achieve the recognition of bridge diseases under the conditions of a complex background and unbalanced data through the homogeneity between an image and a point cloud. The method comprises the following specific implementation steps: (1) collecting a multi-view image and a disease image of a bridge structure; (2) reconstructing a point cloud model of the bridge structure by using the multi-view image and outputting a depth image; (3) building and training an ROI (Region of Interest) extraction model, and outputting a disease image of which the complex background is removed by utilizing the depth image; (4) building and training an improved DeepLabv3 + disease segmentation model, detecting a bridge disease in the disease image after ROI extraction, and outputting a bridge disease segmentation mask; and (5) realizing three-dimensional visualization of the disease based on the bridge disease segmentation mask and the point cloud model. According to the method disclosed by the invention, high-precision detection and positioning of bridge diseases can be realized, and a powerful tool is provided for daily detection of a bridge structure.

The invention discloses a gear fault diagnosis method based on a transfer learning fault diagnosis model, and relates to the gear fault diagnosis method based on the transfer learning fault diagnosis model. The objective of the invention is to solve the problem of low gear fault diagnosis accuracy caused by few fault samples and unbalanced data in the actual gear fault diagnosis process. The method comprises the following steps: constructing a gear training set; constructing a transfer learning fault diagnosis model, and obtaining a trained transfer learning fault diagnosis model; the specific process is as follows: a transfer learning fault diagnosis model sequentially comprises a feature extractor and a classifier; obtaining a trained transfer learning fault diagnosis model; the method comprises the following steps: inputting a gear training set into a feature extractor of a model, and outputting features by the feature extractor; inputting the features into a classifier, and outputting a classification result by the classifier; until the total loss converges, obtaining a trained model; and inputting a test set of an actual gearbox into the trained model to obtain a diagnosis result. The method is used in the field of gear fault diagnosis.

The invention discloses an unbalanced data fault diagnosis method based on self-balancing federal learning, and belongs to the technical field of combination of artificial intelligence and edge computing, and the method comprises the following steps: S1, obtaining client data, and monitoring whether the client data has an unbalanced phenomenon; s2, data enhancement; s3, sharing the weights of the generator and the discriminator; s4, performing intermediary training scheduling; s5, scheduling the client training model by the intermediary server; s6, aggregating model parameters by the federal learning server; s7, returning the aggregated model parameters to the intermediary server, and starting the next round of synchronous training; and S8, the client obtains an accuracy result. According to the unbalanced data fault diagnosis method based on self-balancing federated learning, the problem of data imbalance can be effectively solved through gradient monitoring, data enhancement and intermediary training scheduling technologies, and the precision and stability of a fault diagnosis model are improved.