160 results about "Fuzzy entropy" patented technology

The invention discloses a multi-region collaborative power grid planning system and method based on an improved multi-target particle swarm optimization algorithm, relates to the technical field of power system planning, and solves the problems of multi-target coupling and cross-region coordination in traditional power grid planning by constructing an economical, environment-friendly and reliable multi-dimensional target function and introducing a game theory method to quantify a multi-target constraint relation. The system comprises a data acquisition module, a multi-objective optimization model construction module, an improved particle swarm algorithm execution module, a collaborative decision module and a result output module, the improved particle swarm algorithm adopts dynamic adaptive inertia weight, time-varying acceleration coefficient and differential mutation operation, and the convergence speed and Pareto frontier distribution quality are remarkably improved; and the collaborative decision-making module realizes cross-regional parameter interaction and scheme optimization through a hierarchical collaborative mechanism and a fuzzy entropy theory. According to the method, collaborative optimization of calculation efficiency and scheme balance is realized in multi-regional power grid collaborative planning, and technical support is provided for scientific planning of a complex power grid system.

The invention discloses a transformer substation on-line monitoring system based on big data analysis, and relates to the technical field of power system state monitoring, the system obtains data through a data acquisition module, and after the data is processed by a signal preprocessing and feature window extraction module, a system response entropy calculation module calculates a multi-scale permutation entropy, a multi-scale fuzzy entropy and a transfer entropy; the method comprises the following steps of: constructing a composite entropy feature vector, establishing a working condition self-adaptive health entropy baseline by an entropy feature baseline management module by utilizing a machine learning algorithm, comparing a current entropy feature with the health baseline by a degradation evaluation and critical early warning module, performing analysis by combining various abnormal judgment rules and indexes based on a critical moderation theory, and outputting an evaluation and early warning result; according to the method, the functional out-of-order of the equipment can be sensed in advance, the dynamic interaction health degree is evaluated in a non-intrusive mode, effective early warning is provided for critical transformation such as system instability, and the reliability and safety of operation of the transformer substation are remarkably improved.

The invention discloses an industrial equipment intelligent control method and system, and the method comprises the following steps: S1, collecting and preprocessing equipment operation data, and constructing a state data set; s2, establishing a trend prediction model by adopting Gaussian process regression, and outputting a state prediction value; s3, constructing a graph structure representation model, and combining a graph convolutional network and a semi-supervised learning method to carry out joint training and identify a working condition category and an operation level; s4, based on the equipment operation data, calculating a fuzzy membership degree and a fuzzy entropy index, and generating an entropy distribution curve; s5, fusing the state prediction value, the working condition category, the operation grade and the fuzzy entropy index to generate a state evaluation result; s6, adjusting control strategy parameters according to a state evaluation result, and issuing a control instruction to an equipment control system; and S7, collecting feedback data, updating the state data set, and realizing closed-loop iterative optimization. The method has the advantages of accurate prediction, stable identification, flexible evaluation, fast control, self-learning and the like, and is suitable for complex and changeable industrial application scenes.

The invention discloses a GIS disconnecting switch multi-state intelligent sensing system, and relates to the field of GIS disconnecting switch state monitoring. A self-calibration multi-mode sensor is deployed for multi-source data acquisition, and novel sensors including terahertz imaging and the like are included; in data preprocessing, deep learning noise reduction is applied, fuzzy entropy is used for dynamic weighted fusion, and abnormal values are processed by an improved algorithm; feature extraction is combined with a plurality of frontier algorithms to process vibration signals, and CRNN is used to analyze acoustic signals; the QPSO evidence theory is adopted for state fusion perception, the node relation is learned by means of GNN, and the weight is adjusted according to the information gain rate; state assessment and early warning are based on transfer learning, GAN and LSTM-attention mechanisms, and early warning priorities are ranked by FAHP. According to the invention, multi-mode accurate acquisition, intelligent data processing, deep feature mining, innovative fusion perception, accurate evaluation and early warning and efficient fault diagnosis and positioning are realized, the state of the GIS isolation switch can be comprehensively and accurately perceived, the system is self-learned and optimized, the equipment safety is guaranteed, the risk of a power system is reduced, and the power operation and maintenance benefits are improved.

The invention relates to the technical field of data processing, in particular to a data processing method and system for a flexible regulation and control terminal, and the method comprises the steps: determining a fuzzy entropy value of each voltage data point in voltage data according to a fuzzy entropy calculation method, and carrying out the abnormality judgment according to the fuzzy entropy value, determining a voltage data point window where the voltage data is located at the sampling moment; calculating a first stability degree according to the quartile distance of the voltage data in the voltage data point window and the number of extreme points; calculating a second stability degree according to the similarity of the voltage data segment and the current data segment in the voltage data point window; and according to the second stability degree, calculating to obtain the sub-window length in the voltage data point window. According to the scheme, the accuracy of fuzzy entropy calculation and the reliability of anomaly detection are remarkably improved.

The invention discloses a distribution box fault detection method. The method comprises the following steps: collecting current signals of a distribution box in different fault states; performing VMD decomposition on transient fault current signals in different fault states to obtain IMF components in different frequency bands, calculating permutation entropy of the IMF components, denoising the IMF components when the permutation entropy is greater than or equal to a preset value, and not denoising if the permutation entropy is less than the preset value; calculating the fuzzy entropy value of each IMF for the de-noised IMF components and the IMF components which are not de-noised; and taking the fuzzy entropy as a fault feature vector, clustering the fault feature vector through a GG clustering algorithm, and identifying different fault types. VMD decomposition is combined with permutation entropy screening and denoising, fault feature vectors are extracted based on multi-scale fuzzy entropy, fault classification is achieved through a GG clustering algorithm, the problems that a traditional method is low in feature extraction precision and poor in clustering adaptability are solved, and the method has the advantages of improving fault signal feature extraction precision and clustering accuracy.

The invention provides a valve leakage diagnosis method and system based on an improved Hereum algorithm optimized SVM (Support Vector Machine), and relates to the technical field of valve leakage diagnosis. Decomposing the collected original signal to obtain a limited number of IMF components; calculating a fuzzy entropy, and constructing a feature vector; taking the feature vectors as data samples, and dividing the data samples into a training set, a verification set and a test set; using the training set to train the SVM model, and according to the classification error rate of the verification set on the trained SVM model, performing iterative optimization on the parameters of the SVM model based on an improved He-Ma algorithm to obtain an optimized SVM model; inputting the test set into the optimized SVM model to obtain a valve leakage diagnosis model; and acquiring a new acoustic emission signal, and inputting the new acoustic emission signal into the valve leakage diagnosis model to obtain a diagnosis result. The method not only can improve the classification accuracy and generalization ability of the diagnosis model, but also can enhance the stability of the model under different working conditions and environmental noise.

The invention discloses a hydrological data management method and system based on machine learning. The method comprises the following steps: S1, generating a hydrological monitoring data set with a unified temporal-spatial resolution; s2, constructing a fuzzy entropy matrix of the hydrological monitoring data; s3, generating a hydrological monitoring data causal model expressed in a directed acyclic graph form; s4, identifying the abnormal hydrological monitoring data in real time by dynamically adjusting the abnormal detection threshold value; s5, generating an abnormal traceability candidate path, and forming an abnormal hydrological monitoring data causal chain; and S6, performing fuzzy entropy optimization processing on the abnormal traceability candidate path, screening out a key abnormal causal path according to the fuzzy entropy value of the hydrological variable in each causal chain and the influence weight of the hydrological variable in the causal chain, and further positioning the root cause of the abnormal hydrological monitoring data. The invention provides a more efficient and intelligent technical scheme for water resource management, disaster prevention early warning and environment monitoring.

The invention relates to the technical field of image data processing, in particular to a connector surface defect detection method and system based on image processing, and the method comprises the steps: obtaining a connector surface image; the method comprises the following steps: calculating a first noise factor of each pixel point in a connector surface image to quantify the noise level in the image, calculating a second noise factor based on the first noise factor to more accurately evaluate the noise feature of the image, and then partitioning the connector surface image to obtain a plurality of blocks with the same size, and calculating the noise expression degree of each block based on the second noise factor, removing the blocks of which the noise expression degrees are greater than a set expression threshold value, calculating fuzzy entropy values of the other blocks, and if the fuzzy entropy values are greater than the set threshold value, judging that the surface of the connector has defects. The problem that the accuracy of connector surface defect detection is not high is solved.

The invention relates to an offshore wind speed prediction method based on a TVFEMD-FE-TCN-Transform model, and the method comprises the steps: obtaining historical offshore wind speed data, carrying out the preprocessing of the data, decomposing the original wind speed data through TVFEMD to obtain a plurality of IMF components, improving the data stability, and carrying out the prediction of the offshore wind speed. According to the method, four types of signals including a high-frequency signal, an intermediate-frequency signal, a low-frequency signal and a trend signal are generated through reconstruction according to IMF component complexity through fuzzy entropy FE, calculation complexity is reduced, a time domain convolutional network TCN is adopted to extract reconstructed signal features, fusion is performed, the reconstructed signal features are input into Transform for wind speed prediction, meanwhile, Transform model parameters are optimized through MWOA, and the wind speed prediction accuracy is improved. Predicting the offshore wind speed by using the optimal parameter combination Transform model to obtain a final offshore wind speed prediction value; according to the method provided by the invention, the problems of insufficient signal decomposition, weak feature extraction capability and low prediction precision of a single prediction model are effectively solved, and powerful support is provided for operation and maintenance management and power grid dispatching of the offshore wind power plant under the condition that the offshore wind speed has intermittent and fluctuation characteristics.

The invention provides an RIES multi-objective optimization planning method considering the uncertainty of source load prediction, and the method comprises the steps: building an RIES basic structure, generating an uncertainty scene set of a source load prediction error through a Latin hypercube sampling method, carrying out the reduction of the uncertainty scene set through a clustering technology, and carrying out the reduction of the uncertainty scene set. According to the method, total cost, carbon dioxide emission and system reliability are taken as objective functions, an RIES multi-objective optimization planning model considering source load prediction uncertainty is constructed, a multi-objective optimization function is solved by adopting a non-dominated sorting genetic algorithm NSGA-III, a Pareto leading set is obtained, and through a strategy of combining a fuzzy entropy theory and TOPSIS, a Pareto leading set is obtained. And selecting the optimal solution of the Pareto leading edge set to obtain a multi-target optimization planning result of each typical scene. The method can comprehensively consider the influence of uncertain source load prediction on planning, improves the reliability of the system and the utilization rate of renewable energy sources, reduces the investment and operation and maintenance cost of the system, and reduces the emission of carbon dioxide at the same time.

The invention relates to the technical field of data processing, in particular to a metal alloy current detection resistor detection data processing method and system. The method comprises the following steps: acquiring a plurality of current data and voltage drop data, and obtaining each sub-window of each current data; obtaining the stability degree of each sub-window of each piece of current data, and obtaining the authenticity of each sub-window of each piece of current data according to the stability degree of each sub-window of each piece of current data and the relation between the numerical value change of the current data and the numerical value change of the voltage data; acquiring a reference window of each current data according to the authenticity; according to the method, the fuzzy entropy value of each current data is obtained according to the reference window of each current data, each abnormal data is obtained according to the fuzzy entropy value of each current data, the judgment of the abnormal condition of the metal alloy current detection resistor is completed, the noise influence is avoided, and the accuracy of abnormal detection is improved.

The invention discloses a robot joint motor dynamic load self-adjusting method based on fuzzy entropy optimization. The robot joint motor dynamic load self-adjusting method comprises the following steps: S1, acquiring operation parameter data of a robot joint motor by adopting sensors arranged at key joints of a robot; s2, generating a corresponding adaptive adjustment factor data set; s3, forming a load probability distribution model parameter data set; s4, applying the load probability distribution model parameter data set to real-time load prediction, determining the load trend of a robot joint motor in a future period of time, and outputting predicted load distribution data; and S5, dynamically adjusting control parameters of a robot joint motor according to the predicted load distribution data and the adaptive adjustment factor data set to form a new control strategy data set. According to the method, the control parameters of the robot joint motor are dynamically adjusted in different load states, so that the oscillation effect of the robot in a complex load environment can be effectively reduced, and energy consumption is optimized under the condition that the motion precision is not affected.

The invention provides a GIS equipment detection system and method based on partial discharge-vibration signal fusion, and relates to the technical field of GIS equipment detection. The method has the flexibility of adapting to different data conditions, and vibration signals and partial discharge signals at a contact and a basin-type insulator are respectively obtained through blind source separation of collected multi-source signals for GIS equipment fault detection; the respective sequential relationship of the vibration signal and the partial discharge signal is considered, the multi-scale fuzzy entropy of the vibration signal and the partial discharge signal is calculated, the richness represented by the vibration characteristic and the partial discharge characteristic is further enhanced, the problems of poor reliability and large detection error of a fault detection method based on a single technology are effectively solved, and the fault detection efficiency is improved. The problems that the characteristics of an existing vibration diagnosis system and the characteristics of an existing partial discharge diagnosis system are prone to omission and low in accuracy are solved. Meanwhile, a three-dimensional digital twinborn visual model of the GIS equipment is also established, and the operation of the GIS equipment can be monitored in real time in combination with fault information.

The invention relates to the technical field of image processing, in particular to a composite board flatness detection method based on image processing, and the detection method comprises the steps: firstly collecting a surface image of a composite board, dividing the surface image into sub-blocks, evaluating the noise possibility of each pixel point, and measuring the noise interference degree. In each sub-block, pixel points of the sub-blocks are paired according to coordinates, a plurality of groups of pixel points with the maximum gray difference are selected, and the distance between the sub-blocks is calculated in combination with the noise possibility of the pixel points. And then, determining fuzzy membership based on the sub-block distance, carrying out sub-block expansion operation, obtaining fuzzy entropy of the blocks through the difference of the mean values of the fuzzy membership before and after expansion, further determining the flatness of the blocks, and realizing flatness detection of the composite board. According to the detection method, the noise influence is comprehensively considered, the distance between the sub-blocks is accurately quantified, and the accuracy and reliability of flatness detection are improved.

The invention discloses a transformer fault diagnosis method based on chaos theory comparative learning under a strong noise background, and the method comprises the following steps: 1, obtaining a label-free data set and a label data set of vibration signals of a transformer box body, and carrying out the normalization processing of the collected signals; a second step of utilizing a dung beetle optimization algorithm to obtain an optimal parameter for ICEEMDAN decomposition of the vibration signal in each fault state, performing ICEEMDAN decomposition of the vibration signal to obtain a plurality of modal components IMF, calculating a multi-scale fuzzy entropy of each modal component, screening a component with a smaller entropy value and reconstructing the signal, and performing data cleaning and denoising; 3, performing random data enhancement on the de-noised label-free data set, defining positive and negative sample pairs, performing phase-space reconstruction, completing comparative learning of a pre-training model, and migrating trained encoder parameters to a downstream task; 4, performing phase-space reconstruction on the denoised labeled data set, and inputting the denoised labeled data set into a trained encoder after fine tuning; 5, performing preprocessing and phase-space reconstruction on the label-free test data, and inputting the preprocessed label-free test data into the trained encoder; sixthly, the output features are input into a classifier to be classified, and fault diagnosis is completed. According to the method, the problem of low diagnosis precision caused by a strong noise environment and lack of marked data in transformer fault diagnosis and the problems of misjudgment and missed judgment caused by nonlinear characteristics of vibration signals are effectively solved.

The invention relates to the field of image data processing, in particular to a part defect detection method and system based on machine vision, and the method comprises the steps: obtaining a gray image of the surface of an automobile part, carrying out the preprocessing, and extracting a surface texture image of a part region; using a fuzzy entropy method to block the surface texture image, and obtaining the gray difference degree and the abnormal degree in each block according to the gray value change and the texture expression in each block; dynamically adjusting the number of iterations of the sub-blocks based on the abnormal degree of the blocks; and optimizing an existing fuzzy entropy method according to the number of iterations to obtain a significant fuzzy entropy value of each block, and judging whether the automobile part has a bubble defect area or not based on the significant fuzzy entropy values. According to the method, the gray difference degree and the texture change in each block are analyzed, and the fuzzy entropy method is combined, so that the potential bubble defect area can be identified more accurately.

A seismic wave identification method based on deep learning comprises the following steps: step 1, acquiring seismic wave signals to obtain original data, and performing center interception and normalization processing to obtain unified signals; 2, decomposing a unified signal by using CEEMDAN to obtain a plurality of orders of intrinsic mode functions and residual components, carrying out coarse graining processing on each order of mode function according to a preset time scale parameter to divide into subsequences, constructing a similarity criterion through a fuzzy membership function, calculating fuzzy entropy values of the subsequences, and integrating the fuzzy entropy values into a feature matrix; and 4, inputting the feature matrix after the dimension reduction into a CTCM-1D-CNN model optimized by a tribe competition and member cooperation algorithm, predicting the type of an output seismic wave, and completing seismic wave identification. Therefore, the design has good seismic wave identification precision and stability.

The invention provides an audio signal denoising method based on improved variational mode decomposition and a related product, and the method comprises the steps: obtaining a target input audio signal, and searching the number of target components and a target penalty factor of variational mode decomposition through employing an improved particle swarm optimization algorithm introducing a local optimal solution jump-out mechanism and fuzzy entropy; decomposing the target input audio signal according to the number of the target components and the target penalty factor to obtain a plurality of first target components; calculating the fuzzy entropy of each first target component, and carrying out the noise reduction of the first target component of which the fuzzy entropy is higher than a preset fuzzy entropy threshold value through employing a wavelet threshold value denoising algorithm, and obtaining a first component; and obtaining a target output audio signal according to the first target component of which the fuzzy entropy is not higher than a preset fuzzy entropy threshold and the first component. Through the method and the device, the problem of poor denoising effect caused by unreasonable parameter setting in the prior art can be solved, so that more efficient and accurate audio signal denoising processing is realized.

The invention relates to the technical field of data processing, in particular to a battery connector real-time current monitoring method and system. The method comprises the steps of obtaining a current data sequence of a connector in a current time period, and determining a noise degree value of current data at a target moment in the current time period; determining a first subsequence and a second subsequence from the current data sequence, and determining a plurality of target current data points from the first subsequence, wherein the differences between the target current data points and corresponding positions in the second subsequence are maximum; according to the noise degree values of a plurality of target current data points, performing weighted summation on the distances between the target current data points and the corresponding data points in the second sub-sequence to obtain weighted distances so as to determine the fuzzy entropy of the current data sequence in the current time period, and when the difference between the fuzzy entropy of the current time period and the fuzzy entropy of the previous time period is greater than a preset threshold value, outputting prompt information. According to the technical scheme, the cost of monitoring the connector can be reduced.

The invention discloses a particle filtering fusion positioning method based on indoor and outdoor fuzzy judgment, which comprises the following steps of: firstly, dividing a region to be positioned into dynamic grid units, constructing a space-time signal distribution matrix, and measuring the matching degree of the space-time signal distribution matrix and a standard scene through weighted Jaccard similarity; secondly, designing a dual-channel adaptive membership function based on a fuzzy theory, and converting hard decision into probabilistic weight output; and then a four-parameter joint optimization mechanism based on environmental difference, model uncertainty, fuzzy entropy and confidence is constructed, a classification threshold and a confidence interval are dynamically adjusted, finally an improved particle filtering fusion model is constructed, a hybrid dynamics model is constructed to predict the positions of particles, and a dynamic resampling strategy is combined to improve the particle utilization rate. And the positioning accuracy and stability are improved. According to the invention, the problem that the positioning precision is reduced or the positioning result jumps frequently when indoor and outdoor scenes are switched is solved.

The invention discloses a residual chlorine determination method, and relates to the technical field of monitoring. The method comprises the following steps: immersing a potential type residual chlorine sensor into a standard residual chlorine solution, collecting a potential response value, calculating a response coefficient, and correcting a potential signal of the sensor; denoising the corrected signal by using a multi-scale fuzzy entropy algorithm to obtain a processed signal; color development time, spectral absorbance and environmental parameter data are collected, the processed signals are combined, and four-dimensional historical data are generated through multi-dimensional quantitative fusion; constructing a four-dimensional residual chlorine concentration detection model based on the three-dimensional curved surface model, and training the model by using four-dimensional historical data; inputting four-dimensional real-time data to the trained model, and outputting predicted residual chlorine concentration; and comparing the predicted value with the actual concentration, directly outputting if the error is smaller than a preset threshold value, fusing real-time data into a historical data retraining model if the error is larger than the threshold value, and outputting after iterative optimization. According to the invention, the four-dimensional residual chlorine concentration detection model is constructed, so that the refined determination of the residual chlorine content is realized.

The invention discloses a short-term photovoltaic power deep learning prediction method based on decomposition sequence complexity evaluation and clustering reconstruction. The short-term photovoltaic power deep learning prediction method mainly comprises the following steps: step 1, decomposing a photovoltaic power time sequence by using successive variational mode decomposition; 2, calculating the complexity of each decomposition component by using a fuzzy entropy algorithm; 3, dividing the components with different complexities by using Gaussian hybrid clustering, and reconstructing the components into high-frequency, intermediate-frequency and low-frequency components; step 4, using a chaos evolution optimization algorithm to optimize hyper-parameters of the bidirectional gating cycle unit (BIGRU) prediction model of each component; 5, performing short-term photovoltaic power prediction on the reconstructed high-frequency component, the reconstructed intermediate-frequency component and the reconstructed low-frequency component by adopting a BIGRU model; and step 6, superposing the predicted values of the components to obtain a photovoltaic power point prediction result. And step 7, using kernel density estimation to form a confidence interval based on a point prediction result, and finally obtaining a photovoltaic power probability interval prediction result. The method has the beneficial effects that the complexity of each decomposition component is evaluated and reconstructed by utilizing the fuzzy entropy algorithm, and comprehensive optimization of each link including model training is realized on the basis of powerful capabilities of capturing context information and processing long sequence data based on the BIGRU.

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 a multi-strategy road flatness detection method, which comprises the following steps of: (1) updating and correcting acceleration data acquired and measured by an acceleration sensor of a vehicle-mounted smart phone in real time by adopting an attitude self-correction algorithm so as to adapt to the dynamic change of a vehicle in a driving process; (2) utilizing a multi-scale fuzzy entropy algorithm to carry out multi-scale processing on measurement data which is collected by a vehicle-mounted smart phone and reflects the road flatness in a vehicle driving process, constructing a road flatness representation model, and combining global features and local features; and (3) adopting a self-attention mechanism convolutional neural network to carry out road flatness identification on acceleration data collected by a vehicle-mounted smart phone in a vehicle driving process. According to the invention, real-time accurate detection of the road flatness can be well realized.

The invention discloses a power transmission and transformation project economic evaluation method, system, equipment and medium fusing adaptive fuzzy entropy weighting and a multi-target grey wolf optimization algorithm, and belongs to the technical field of power system economic analysis, and the method comprises the steps: constructing an economic index system, building a fuzzy membership matrix, and calculating an index weight through combining fuzzy entropy and information entropy; a comprehensive weight is generated by adopting a self-adaptive fusion mechanism, then a multi-target weighted evaluation model is constructed, and finally multi-target search is performed by utilizing a swarm intelligence optimization algorithm. According to the invention, by constructing a self-adaptive weighting mechanism fusing the fuzzy entropy and the information entropy and combining the global search capability of the multi-target grey wolf optimization algorithm, multi-index weight dynamic optimization and multi-target cooperative solution in the economic evaluation of the power transmission and transformation project are realized; the method effectively overcomes the limitation of a traditional method in the aspects of weight distribution subjectivity, insufficient index coupling processing and multi-target balance, and forms a closed-loop evaluation system from index processing to intelligent decision making.

The invention discloses a system and a method for monitoring the running state of a fan blade based on voiceprint recognition. The method comprises the following steps: acquiring voiceprint data and environment data during running of the fan blade through a data acquisition module; performing noise reduction processing by adopting an improved VMD method, and adaptively optimizing a decomposition modal number and a penalty factor through fuzzy entropy and an energy ratio; constructing a plurality of branch input data according to the voiceprint data; inputting the two types of branch data into a pre-trained multi-branch model, carrying out weighted fusion on similar results by combining a voiceprint signal-to-noise ratio and a defect confidence difference, and outputting a state result of a defect type and confidence; and when the confidence exceeds a threshold value, integrating the environment data, the blade parameters and the GAP features to generate positioning analysis data, determining a defect position through a defect positioning model, and triggering an alarm. According to the method, the feature quality is improved through adaptive noise reduction, the feature fusion effect is optimized through dynamic weight, the defect recognition accuracy is enhanced through confidence fusion, efficient positioning is achieved, and the monitoring efficiency and reliability are remarkably improved.

The invention provides a fault diagnosis method and system based on multi-band multi-scale fuzzy entropy fusion for a traction rectifier with the highest fault rate in an electric locomotive traction transmission system. The method comprises the following steps: firstly, on the basis of an optimal wavelet basis function, decomposing fault signals under different working conditions and different operation modes by a wavelet packet to obtain a series of optimal frequency band information; secondly, performing coarse graining processing on the sequence of each frequency band, and calculating a multi-scale fuzzy entropy; and finally, solving the energy value of the multi-scale fuzzy entropy of each frequency band, and taking the energy value as a fault feature vector. The multiband fuzzy entropy feature obtained based on the optimal wavelet basis function has certain robustness to noise, and the fault diagnosis rate can be further improved through the proposed multi-information fusion algorithm. Compared with other methods, the method has the advantages of higher diagnostic rate and stronger robustness.

The invention provides a radar signal preprocessing method for adaptive filtering and noise reduction. The method comprises the following steps: decomposing a radar signal into a multi-order IMF by performing CEEMDAN on the radar signal, then judging the selection of the IMF through a fuzzy entropy and a cross correlation coefficient, then performing noise positioning and noise reduction processing on the selected IMF through a normalized correlation coefficient, and finally obtaining a noise-reduced signal through signal reconstruction. According to the method, the background noise can be effectively suppressed to the maximum extent while effective signal energy is reserved, and the precision of radar signal characteristic analysis is improved.

The invention discloses a fuel cell health state evaluation method. Improved kernel principal component analysis is used for carrying out feature extraction on working parameters and operating parameters of a fuel cell; the method comprises the following steps: decomposing fuel cell data by adopting a TVF-EMD technology to obtain sub-modes, reducing the non-stationarity of a sequence, reducing the number of the sequence through fuzzy entropy aggregation, and improving the data processing efficiency; a time series prediction model TimeMixer capable of decomposing multi-scale fusion and improved by a self-attention mechanism is provided, multi-scale seasonal and trend components are mixed in two directions from fine to rough and from rough to fine, information in time series data is comprehensively extracted, and prediction robustness is enhanced; and optimizing hyper-parameters of the TimeMixer model by using an improved difference creative search algorithm DCS so as to quickly search out an optimal hyper-parameter combination and realize accurate evaluation of the state of health of the fuel cell. According to the invention, a data-based deep learning technology is adopted to solve the problems of complexity of fuel cell data and health state evaluation.