121 results about "Fuzzy clustering" patented technology

The application discloses a kind of big data-based optimization analysis method and system of territorial space planning, it is related to big data and optimization analysis technical field of territorial space planning, including real-time data acquisition and dynamic preprocessing, dynamic regional division, multi-model integrated space-time prediction, multi-objective dynamic optimization planning, real-time feedback and adaptive adjustment.The big data-based optimization analysis method of territorial space planning provided in the application adopts space-time weighted fuzzy clustering method, divides the territorial space into several sub-regions according to the spatial coordinates and time attributes of data, constructs the weighted distance regular objective function between data points and regional center, and updates the membership and the position of regional center iteratively, realizes the self-adaptation and space-time smoothing of regional segmentation, effectively captures the dynamic change characteristics in region.

The invention provides a lithium ion battery safety valve opening and failure early warning method based on expansive force, and belongs to the technical field of lithium ion batteries. Battery expansive force and cycle data under different pre-tightening force conditions are collected, statistical features are extracted to construct a state feature set, health state groups are divided by adopting a fuzzy clustering algorithm, and the early warning result is obtained. Establishing a segmented nonlinear mapping model of the expansive force and the internal pressure, performing wavelet denoising and robust differential calculation on expansive force signals, and optimizing an initial expansive force derivative threshold value by analyzing time dispersion at different heating rates; a multi-scale feature fusion algorithm based on hierarchical attention aggregation is utilized to construct a state self-adaptive early warning model to correct a threshold value, and a four-stage early warning mechanism is set to monitor the opening and failure states of the safety valve. The technical problem that the opening time of the safety valve cannot be accurately predicted and self-adaptive early warning cannot be realized under different battery health states and pretightening force working conditions is solved.

The invention discloses a low-voltage distribution box temperature rise abnormity identification method based on an improved fuzzy clustering algorithm. The method comprises the following steps: S1, generating a temperature-current synchronous acquisition data set according to a time sequence; s2, constructing a load-temperature difference weight matrix in combination with the current current amplitude; s3, obtaining a current membership matrix and a cluster center set; s4, calculating the membership slip amount of each measuring point according to the current membership matrix and the membership matrix at the previous moment, and generating a temperature rise trend state sequence; s5, judging whether the temperature rise trend state sequence has a measuring point which continuously slides from the normal cluster to the risk cluster or not; if yes, corresponding cluster centers in the corresponding cluster center sets are extracted and mapped to the physical coordinates according to the measuring point index table, and positioning information containing the measuring point numbers, the types of the electrical parts and the risk levels is generated. According to the invention, the fault positioning accuracy and the operation and maintenance efficiency are greatly improved.

The invention relates to the technical field of power distribution network fault monitoring, in particular to a fault recognition method and system based on an intelligent fusion terminal, and the method comprises the steps: obtaining an instantaneous multi-dimensional electrical data set at each moment, and constructing an input sample with the current moment as an end point, inputting the input sample into the trained long-short-term memory model to calculate a first fault probability of the input sample; inputting the input sample into a trained optimal fuzzy clustering model to calculate a second fault probability of the input sample; and distributing respective weights for an output result of the long and short term memory model and an output result of the optimal fuzzy clustering model, carrying out weighted fusion on the first fault probability and the second fault probability to obtain a comprehensive fault probability of the input sample, and judging whether the power distribution network has a fault according to the comprehensive fault probability. According to the invention, through multi-source information fusion, model collaborative optimization and dynamic weight distribution, the fault identification precision and response speed of the power distribution network under complex conditions are effectively improved.

The invention discloses a power system abnormal data clustering and vulnerability detection method based on a fuzzy mean value algorithm, and belongs to the field of power system security. Aiming at the defects of a traditional method in the aspects of data fuzziness, multi-dimensional association and dynamic adaptability, a'data preprocessing-dynamic fuzzy clustering-vulnerability diagnosis' closed-loop process is constructed. 12-dimensional feature vectors including electrical quantities, equipment states and environmental parameters are constructed, and Z-score standardization is combined with a sliding window updating mechanism to carry out data preprocessing; a feature weighted fuzzy C-means algorithm with entropy regularization is used, and a time decay factor and space-time correlation modeling are fused to realize dynamic fuzzy clustering; abnormal clusters are screened through double thresholds, and vulnerability diagnosis and scoring are completed in combination with an association rule base and a three-level vulnerability scoring model. According to the method, through verification of power grids with different voltage levels, the anomaly detection recall rate reaches 95% or above, the operation and maintenance efficiency is improved by 30%, and the accuracy and real-time performance of anomaly detection of the power system are effectively improved.

The invention provides a rolling quality parameter uncertainty quantification method based on mixed entropy-fuzzy clustering. The method comprises the following steps: S1, multi-source data fusion: integrating rolling compaction parameters, meteorological data and real-time monitoring data in an engineering construction process, and constructing a multi-dimensional feature matrix; s2, calculating mixed entropy, namely quantifying the randomness and fuzziness of parameter distribution in combination with information entropy and fuzzy entropy; s3, performing dynamic fuzzy clustering, namely, optimizing a clustering center based on an improved firefly algorithm, and dividing parameter uncertainty levels; step S4, uncertainty contribution degree analysis: quantifying the influence weight of each parameter on the rolling quality through an entropy weight-grey correlation method; according to the method, the information entropy and the fuzzy entropy are fused, and dynamic clustering and an intelligent optimization algorithm are combined, so that precise quantification and hierarchical management and control of the rolling parameter uncertainty are realized.

The invention provides an intelligent cabinet heat dissipation control method and system, and belongs to the technical field of cabinet heat dissipation control. According to the method, data items all have acquisition time and cabinet area identifiers; the method comprises the following steps: dividing a cabinet hot area by using fuzzy clustering based on a historical sample, dynamically modeling by combining an adaptive PID control algorithm, optimizing control parameters through a particle swarm optimization algorithm, adjusting a hot area control model weight coefficient according to real-time feedback, generating a hot area-equipment association map, and constructing an adaptive heat dissipation control network; predicting a temperature trend through a decision tree model by using a correlation map and real-time operation characteristics generated by the network, and generating a fan rotating speed adjusting strategy, an air conditioner power distribution scheme and a multi-stage heat dissipation control strategy according to the temperature trend; inputting a heat dissipation control strategy and an execution result as feedback into the self-adaptive heat dissipation control network, and dynamically optimizing a correlation map and control parameter modeling; and multi-cycle feedback closed-loop optimization control is realized through multi-time feedback and parameter adjustment.

The invention discloses a high arch dam operation modal parameter automatic identification method and system based on discharge excitation. The method comprises the following steps: 1) obtaining a vibration displacement response signal: determining a penalty factor and an optimal decomposition layer number based on an adaptive multivariate variational mode decomposition algorithm to obtain an optimal IMF component of each sensor channel signal, and performing IMF component screening and signal reconstruction through a frequency domain cross correlation coefficient to realize adaptive noise reduction of the signal; 2) establishing a Monte Carlo three-dimensional stability diagram based on a random subspace recognition algorithm driven by a covariance matrix; and 3) modal parameter automatic identification based on an intelligent clustering algorithm. According to the method, the noise is suppressed by automatically optimizing the modal component reconstruction signal of the multi-sensor vibration signal; a Monde-Carlo three-dimensional stability diagram is established in combination with a Monde-Carlo theory and a covariance driven random subspace method to determine a model order, and automatic interpretation of the stability diagram is realized by applying improved fuzzy clustering, so that operation modal parameters of the high arch dam are accurately identified.

The invention provides a financial risk control and anomaly detection method and system based on a graph neural network, and relates to the field of financial risk control, and the method comprises the steps: constructing a financial transaction graph network, constructing a feature graph in combination with transaction time sequence information, extracting a time sequence feature vector, calculating a risk propagation feature vector, and determining a node embedding vector and a fusion node vector. And constructing a transaction flow diagram and carrying out community division, and finally determining an abnormal transaction community through fuzzy clustering and carrying out early warning.

The invention discloses a power distribution network small current grounding fault diagnosis positioning method and system based on edge calculation, and belongs to the field of power system automation, and the method comprises the steps: extracting and recognizing transient features, if a suspected grounding fault is detected, carrying out the multi-source feature fusion analysis through a regional main node, and constructing a transient response time sequence map; a weighted fuzzy clustering algorithm is combined with a multi-channel criterion to determine a fault channel, and a specific fault branch is further positioned through a topology tracking algorithm; introducing a multi-scale wavelet packet energy analysis method into the regional main node, performing energy inversion calculation on the transient current signal under multiple frequency bands, and identifying an energy concentration region near the grounding point through an energy distribution gradient; and constructing a robustness data redundancy model based on the historical data of the edge nodes and the topological relation, and identifying and eliminating abnormal feature data containing noise or distortion. According to the method, transient characteristics are rapidly extracted and preliminary judgment is made after a fault occurs, so that the real-time performance of fault response is greatly improved.

The invention relates to an automatic instrument parameter self-tuning method and device based on deep learning. According to the method, real-time operation data of an instrument is collected through a multi-source sensor, time sequence alignment is carried out to form a multi-dimensional data tensor, and then local time sequence features and a long-term dependency relationship are respectively captured by using a convolutional layer and a bidirectional long-short-term memory network in a depth feature extraction network; the two types of features are fused through an attention mechanism to form a depth feature vector, on this basis, the vector is mapped into a working condition membership degree vector by adopting a differential fuzzy clustering method, and finally, the working condition membership degree is non-linearly mapped into a PID parameter adjustment amount through a multi-layer perceptron network, and the PID parameter adjustment amount is superposed to a basic parameter to realize parameter self-tuning. Therefore, under the condition that manual intervention is not needed, an automatic instrument can automatically adapt to complex and changeable operation conditions, the control precision and the system stability are remarkably improved, and the problem of adaptability of traditional PID control in a time-varying nonlinear system is effectively solved.

The invention provides an electric vehicle ordered charging method and system based on an improved whale optimization algorithm, and belongs to the technical field of electric vehicle ordered charging, and the method comprises the steps: constructing a fuzzy clustering model based on threshold value optimization according to the electrical load prediction data of a micro energy grid user side, an improved particle swarm algorithm is adopted to carry out optimal division of the peak and valley periods of the micro-energy network on the fuzzy clustering model based on threshold optimization; according to historical electric vehicle charging load data, a charging load prediction method based on variable-variable variational mode decomposition and a long-short-term memory neural network is adopted; according to the electrical load prediction data, the photovoltaic output prediction data, the time-of-use electricity price and the electric vehicle charging load prediction data of the micro energy grid user side, the double-layer multi-target optimization model is solved by adopting an improved whale optimization algorithm based on a hybrid reverse learning strategy, and an optimal ordered charging strategy of the electric vehicle is obtained. According to the method, the electric vehicle can be charged more orderly, and the influence on a power grid is smaller.

The invention provides a concrete waste crushing particle size distribution analysis method and device, and the method comprises the steps: obtaining concrete waste image data, extracting a particle contour and geometric parameters through image recognition, determining a particle contact point displacement feature, and recognizing a stress concentration region migration path. Obtaining a particle morphology data set containing stress transfer path deflection information; performing gray value processing on the particle surface image, identifying a cement paste stripping area caused by shear stress component change through brightness difference to obtain interface stripping stress state distribution information, and calculating shear breaking ultimate strength distribution characteristics based on stress transfer path deflection information; and fuzzy clustering processing is carried out on the particle data set, if boundary fuzzy particles exist, crushing force transmission characteristics of the boundary fuzzy particles are obtained according to mechanical response time-frequency analysis, and the crushing risk level of the boundary particles is identified in combination with a particle internal crack initiation force threshold.

The invention discloses a hydrogen liquefaction control method and system based on AI decision making. The method comprises the steps that real-time operation data and parameters of a hydrogen liquefaction device are obtained; based on the real-time operation data and the parameters, a fuzzy clustering algorithm is utilized to identify the current working condition so as to determine the working condition type to which the current working condition belongs; based on the working condition type, a reinforcement learning algorithm is utilized to generate a target control strategy, and the target control strategy comprises at least one control strategy of the yield, the energy consumption and the equipment service life early warning of the hydrogen liquefaction device; and according to the target control strategy, utilizing a particle swarm optimization algorithm to adjust PID parameters of the hydrogen liquefaction device so as to control at least one of yield, energy consumption and equipment life early warning of the hydrogen liquefaction device. The response speed, stability and anti-disturbance capability of the control loop of the hydrogen liquefaction device can be improved, dependence on experience of operators is reduced, performance degradation of the hydrogen liquefaction device is avoided, and efficient operation of the hydrogen liquefaction device is guaranteed.

The invention discloses a micro-grid cluster dimension reduction method and system based on scene self-adaption and topology maintenance. Aiming at different types of energy, constructing a steady-state characteristic index system and decoupling the steady-state characteristic index system into a plurality of groups of characteristics; the method comprises the following steps: clustering system time series data, constructing an operation state manifold diffusion matrix, clustering by using a fuzzy clustering method based on diffusion distance, and outputting an optimal scene division result; constructing a Wasserstein distance matrix by using the steady-state characteristic index of each type of energy, defining a scene objective function and solving an optimal index weight; and calculating a scene membership degree and a fusion index vector weight according to the real-time operation state, weighting the steady-state characteristic index system, and outputting a weighted characteristic matrix. And performing multi-scale topology analysis on the weighted feature matrix, constructing a topology stability constraint, and aggregating the power grid equipment by adopting a hierarchical clustering method based on the topology stability constraint. According to the technical scheme, the internal evolution rule of the operation state can be accurately captured, so that the aggregation result better meets the actual operation requirement.

The invention belongs to the technical field of multi-level RCM, and discloses a multi-level RCM analysis and reliability structure construction method and a related device. The multi-level RCM analysis and reliability structure construction method comprises the following steps: establishing a unit system function model after constructing a unit system database, performing multi-level classification on equipment of a unit system in combination with a fuzzy clustering algorithm, and then determining levels and weights of various types of equipment in the unit system function model, analyzing a failure mode of each type of equipment after multi-level classification through a harmfulness analysis method in combination with a fault tree analysis technology, establishing a correlation model between the equipment failure mode and a unit system function, determining an influence weight of the equipment failure mode on the reliability of the unit system, and establishing a unit system reliability model; inputting the unit system database into the unit system reliability model to obtain a unit system maintenance strategy library; the analysis result accuracy and the system reliability can be greatly improved.

The invention relates to the technical field of power system safety monitoring, in particular to a power transmission line tree flash hidden danger monitoring method based on multi-sensor fusion, which comprises a multi-source data acquisition module, a data fusion and preprocessing module, a risk feature extraction module, a dynamic risk assessment module, an intelligent early warning decision module and a monitoring feedback optimization module. Tree information is collected in real time through multiple sensors such as a laser radar and an infrared thermal imager, data quality is optimized by using improved Kalman filtering and wavelet transformation, risk features are extracted based on a fractional order differential equation, threat indexes are dynamically evaluated in combination with adaptive fuzzy clustering and a Markov chain model, and the risk assessment accuracy is improved. And finally, generating an early warning strategy through mixed integer linear programming. The tree flash hidden danger identification accuracy can be remarkably improved, the potential risk is comprehensively covered, the manual inspection cost is reduced, and intelligent safety guarantee is provided for a power system.

The invention discloses a low-rank multi-modal remote sensing image clustering method and device on a superpixel manifold and a storage medium, and relates to the technical field of multi-modal remote sensing image clustering. The method comprises the following steps: splicing a multi-modal remote sensing image along a channel direction, segmenting the spliced image into a plurality of sub-regions through superpixel segmentation, and solving a mean value for each sub-region to obtain a multi-modal superpixel; embedding the Laplacian matrix of the multi-modal superpixels into manifold regularization about the superpixel clustering matrix, and capturing a local manifold structure of the multi-modal superpixels; under the constraint of manifold regularization, constructing a low-rank reconstruction model of a product of a single-mode clustering matrix and a unified clustering matrix; initializing and alternately optimizing the single-mode clustering matrix and the unified clustering matrix by using fuzzy clustering; and analyzing the super-pixel clustering result, and mapping the super-pixel clustering result into a clustering result of the original image. According to the invention, the accuracy and efficiency of remote sensing image clustering are improved.

The application discloses a kind of based on genetic character figure target edge image extraction method, it is related to image processing field.Data model of the figure target image to be handled is established, image is converted into figure target image matrix, and the grey value of each pixel point of image corresponds the element value in the corresponding position in matrix;Using the fuzzy clustering method with genetic characteristics to each pixel point in figure target image matrix is clustered, and the marking matrix for marking each pixel point belongs to class is generated;Using the corresponding relationship between marking matrix and figure target image matrix, the grey value of all pixel points in the same class is reset as the average grey value of the class, and the figure target clustering diagram is formed;Using 8 neighborhood method, the edge of figure target clustering diagram is extracted, and the figure target edge image is formed.The application not only makes clustering result more approximate real division, improves target clustering accuracy and noise immunity.

The application discloses an anchor point guided clustering based data classification method, device and equipment, relates to the technical field of digital data processing, and comprises the following steps: obtaining an original data set to be classified, converting each sample data into a numerical vector, and constructing a data matrix; initializing a clustering center matrix and an anchor point matrix, and setting a fuzzy coefficient; obtaining the anchor point matrix and the clustering center matrix after joint iterative optimization; calculating the fuzzy membership degree of each sample vector; the category with the maximum fuzzy membership degree is taken as the final category label of the sample vector, and the classification results of all sample vectors are output. The application solves the problems that the existing fuzzy clustering method is sensitive to initial conditions, is easy to fall into a suboptimal solution, leads to unstable and inaccurate classification results, and cannot be directly solved by using a gradient descent algorithm, and is difficult to be applied to large-scale data sets, and realizes the enhancement of complex data classification precision and the applicability in different data scale scenes.

This invention relates to a data-driven intelligent logistics supply chain digital management system. The system includes a demand forecasting and analysis unit, an inventory optimization unit, a supplier management unit, a logistics route optimization unit, a system integration and feedback unit, and a real-time logistics marketing unit. By analyzing historical orders and market data through recurrent neural networks and long short-term memory networks, accurate forecasting of short-term and medium-to-long-term demand is achieved. The inventory optimization unit combines a Bayesian dynamic linear model and a convolutional neural network to achieve dynamic inventory management. The supplier management unit optimizes supplier selection using a multilayer perceptron and fuzzy clustering algorithm. The logistics route optimization unit achieves optimal scheduling of logistics routes based on genetic algorithms and an adaptive large-scale neighborhood search algorithm (ALNS). By integrating multiple functional units, this invention effectively improves the operational efficiency and response speed of the logistics supply chain.

The application relates to the technical field of power distribution network fault monitoring, in particular to a fault identification method and system based on an intelligent fusion terminal, which comprises the following steps: acquiring an instantaneous multi-dimensional electrical data set at each moment, taking the current moment as the terminal point to construct an input sample, inputting the input sample into a trained long short-term memory model to calculate the first fault probability of the input sample; inputting the input sample into a trained optimal fuzzy clustering model to calculate the second fault probability of the input sample; assigning respective weights to the output results of the long short-term memory model and the optimal fuzzy clustering model, weighting the first fault probability and the second fault probability to obtain the comprehensive fault probability of the input sample, and judging whether the power distribution network has a fault according to the comprehensive fault probability. Through multi-source information fusion, model collaborative optimization and dynamic weight distribution, the fault identification precision and response speed under the complex condition of the power distribution network are effectively improved.

A kind of distributed attack-resistant domain management and control method and system for giant constellation, the present application relates to satellite constellation management and control technical field, the present application aims at solving the problem of cooperative management and control and attack-resistant resilience maintenance of multi-layer heterogeneous giant constellation in dynamic topology environment.Technical points: the present application takes the management and control node satellite as core, combines with the cluster head satellite and ordinary satellite in domain, forms distributed management and control domain structure.The structure undertakes cross-orbit communication switching and distributed cooperative management and control function, effectively deals with the cooperative management and control challenge brought by the difference of multi-orbit satellite in operation cycle, communication topology and communication time delay;Introduce multi-element maximum entropy trust model: based on fuzzy C clustering algorithm and maximum entropy principle, construct dynamic trust evaluation system, and comprehensively quantitatively analyze the trust degree of distributed nodes.Through real-time identification of high-risk nodes and implementation of isolation measures, significantly reduce the interference of malicious satellite to inter-satellite data transmission, improve system security.The present application realizes the efficient cooperative management and control and attack-resistant ability enhancement of multi-layer heterogeneous giant constellation, provides key technical support for stable operation of giant constellation under complex threat environment.

This invention is applicable to the fields of artificial intelligence and intelligent transportation, providing a modified vehicle identification method based on attribute fusion and fuzzy product quantization. In the comprehensive vector feature extraction, this invention employs vehicle and license plate detection, parallel feature extraction, and attribute fusion concatenation to obtain comprehensive features containing high-level license plate semantic information, as well as low-level vehicle model and color attributes. This eliminates background noise interference, enhances the response strength of three easily modified vehicle features, and helps compensate for the limitations of single features. Furthermore, it applies fuzzy clustering and cosine similarity distance calculation methods, which can accommodate the uncertainty of input information during modified vehicle retrieval. Compared to traditional Euclidean distance, cosine similarity is not affected by vector length, and can better handle differences in dimensions when retrieving modified vehicles. Compared to the original product vector method, this invention's method has higher retrieval accuracy and robustness in modified vehicle scenarios.

Embodiments of the present application provide an indoor fingerprint positioning method, device and computer readable storage medium, the method comprising: determining an initial cluster number and an initial cluster center of a fingerprint library based on a clustering algorithm; clustering the fingerprint library based on the initial cluster number and the initial cluster center using a fuzzy clustering algorithm to obtain each first cluster; identifying the intersection regions of each two clusters in all the first clusters, dividing the sample points in each intersection region into second clusters, and obtaining third clusters; the third clusters are the first clusters except the second clusters; and training a positioning model corresponding to each cluster based on an improved weighted K nearest neighbor (WKNN) algorithm in each of the first clusters, the second clusters and the third clusters, which is used for positioning a to-be-positioned point.

The invention relates to a structure period segment division method based on structure dynamic response similarity, which is characterized in that on the basis of structure dynamic response under seismic action, objective division of structure period segments is realized by constructing response characteristic matrixes corresponding to different structure periods and introducing a fuzzy clustering mechanism to perform unsupervised classification on the structure periods. According to the method, linear and non-linear structure response characteristics are considered at the same time, the optimal period segmentation number and the boundary threshold are determined in combination with the clustering effectiveness evaluation index, and a more accurate thought and method are provided for more rapidly evaluating seismic damage of the structure in the specific period range and matching input vibration of the structure in the specific period range.

This invention discloses a graph anonymization method for privacy protection in weighted social networks. It combines member fuzzy clustering and simulated annealing to create an optimal cluster of node degree sequences, resulting in a new degree sequence. Edge addition and deletion operations are performed on the original graph to reconstruct the graph and satisfy the new degree sequence. For nodes with the same degree, to resist background knowledge attacks, the edge weights of some nodes are generalized so that the weight values ​​of nodes with the same degree satisfy a diversity model. Experimental results show that, compared with other methods, the combination of member fuzzy clustering and simulated annealing provided by this invention can not only resist background knowledge attacks on node degree and weighted edges in weighted social networks, but also effectively reduce the amount of data loss after anonymization and improve the actual utility of the data.

The invention discloses a ghost probe target detection method, device and equipment and a medium, and the method comprises the steps: collecting first driving data in a vehicle driving process and image data on a front road, and determining second driving data and driving orientation of a pedestrian, and the position information of a target vehicle and the pedestrian; determining a pulse transmission frequency according to the first driving data; performing feature extraction on the image data to obtain image feature data, and inputting the image feature data into a pulse neural network for prediction according to a pulse transmission frequency to obtain a first prediction result; performing fuzzy clustering according to the first driving data, the second driving data, the driving orientation and the position information, and performing minimization processing on a target function corresponding to the membership degree to obtain a second prediction result corresponding to the ghost probe target; and fusing the first prediction result and the second prediction result to obtain a comprehensive prediction result corresponding to the ghost probe target. The method can improve the detection precision of the ghost probe target, and can be widely applied to the technical field of vehicles.

The invention discloses a rail power supply transformer fault identification method based on improved ensemble learning, and relates to the technical field of power supply device monitoring. The method comprises the following steps: collecting measurement data of the rail transit power supply transformer, and obtaining electric-gas multi-physics field heterogeneous data of the rail transit power supply transformer to form a data sample set; according to the initial sample set, forming a power supply transformer state fuzzy cluster in the initial sample set based on a density clustering method; then constructing a fault identification model and carrying out adaptive variable weight training; and finally, designing a power supply transformer fault identification device based on an integrated learning algorithm by using the fault identification algorithm model, wherein the device is used for fault identification of each power supply transformer terminal. According to the method, an improved ensemble learning model of an embedded neural network fusing oil dissolved gas features is constructed, a fault identification ensemble learning framework is provided to improve generalization under the condition of differentiated unbalanced samples, and high-precision and high-adaptability discrimination of multiple types of faults of the rail transit power supply transformer is realized.

The application discloses a fuzzy clustering image segmentation method and system based on Lie group theory, and the method comprises the following steps: extracting image bottom features to obtain image pixel feature vectors; constructing matrix Lie group features of the image based on the image pixel feature vectors; initializing a fuzzy membership matrix and clustering centers; calculating distances from Lie group features of pixels to the clustering centers on a Lie group manifold; updating the clustering centers and the fuzzy membership matrix; terminating iteration and segmenting the image; the application improves sample clustering separability while ensuring stability of the algorithm; optimizes utilization of neighborhood space information, improves anti-noise capability of the algorithm while better preserving image details, and improves convergence speed of the algorithm; compared with the prior art, the method provided by the application has good stability and high operation efficiency while improving segmentation precision.