32 results about "Neural fuzzy" patented technology

The invention belongs to the field of data processing, and particularly relates to a dynamic cooperative control system and method for a gas turbine and a micro-grid, and the method comprises the steps: constructing a micro-grid real-time monitoring module, continuously collecting distributed energy real-time output, controllable load demands, bus voltage frequency and equipment state parameters, and carrying out the filtering and noise reduction through a preprocessing unit, thereby guaranteeing the data precision; calculating a real-time power difference value based on the preprocessed data, calling an adaptive neural fuzzy inference system, taking the power difference value, the bus voltage deviation and the frequency deviation as input, and judging whether the power difference value, the bus voltage deviation and the frequency deviation exceed a preset threshold value by means of a fuzzy rule base and a neural network model; if the threshold values are not exceeded, the current states of the gas turbine and the energy storage system are maintained; if any one exceeds the threshold value, a dynamic cooperative control instruction is triggered, precise cooperative control of the gas turbine and the micro-grid is achieved, and the operation stability, the operation efficiency and the reliability of the micro-grid are improved.

The invention relates to the field of artificial intelligence and computer science, in particular to a causal structure and latent variable-based adaptive reinforcement learning reasoning migration method, which comprises the following steps of: constructing a causal world model fused with multi-modal observation and a decoupling latent variable space; establishing a hierarchical inference engine comprising an intuition layer, a conventional layer and a planning layer; pre-training a quick response and judicial planning dual-mode strategy and generating an interpretable fuzzy rule base; performing calculation level coarse tuning based on task identification and causal complexity; evaluating the real-time state criticality through an adaptive neural fuzzy system and dynamically switching a decision mode; after the action is executed, the threshold and the rule are subjected to closed-loop optimization, and cross-environment efficient migration is realized by utilizing a causal modularization characteristic. According to the technical scheme, consumption of computing resources is remarkably reduced on the premise that decision precision and safety are guaranteed, and the response speed and cross-scene adaptive capacity of a system on edge equipment are improved.

The invention relates to the field of education data mining and teaching process evaluation, in particular to an online and offline mixed teaching performance dynamic evaluation method and system based on a PDCA (Packet Data Convergence Architecture) circulation, and the method comprises the steps: generating initial Rubric configuration and formulating a multi-source data collection scheme through the analysis of course types and learning condition information around the PDCA circulation; then, online and offline multi-modal information is collected and preprocessed, and data with labels and basic statistics are obtained; and in combination with causal graph construction and quantum multi-group fuzzy weight optimization, carrying out comprehensive evaluation on the data, outputting adaptive Rubric configuration and student scores, and generating a readable report and an early warning through a neural fuzzy abstract. And according to the score and early warning, implementing difference enhancement and holographic AR feedback, collecting intervention process data again, and dynamically adjusting Rubric to complete iteration. According to the invention, the teaching performance can be continuously optimized, and accurate early warning and personalized intervention are realized.

The invention discloses an intelligent feces treatment system and method, and belongs to the field of sewage treatment.The intelligent feces treatment system comprises a data acquisition module used for collecting COD, ammonia nitrogen, DO, pH, water temperature, SS and microbial activity parameters of sewage in real time and conducting normalization processing on the collected water quality parameters to form a unified standard data basis; the first model module is used for optimizing membership function parameters and fuzzy rules of an adaptive neural fuzzy inference system by applying a particle swarm algorithm based on the data processed by the data acquisition module, outputting a predicted value of COD concentration in a biochemical pool in real time by training an ANFIS model, and forming a COD prediction model; and the second model module is used for constructing a Stacking integrated model by taking the COD predicted value in the first model module and the data processed in the data acquisition module as input, the integrated model comprises a base learner and a meta learner, and then a prediction result of the base learner is generated by adopting a five-fold cross validation mode.

The invention discloses a lithium battery system state-of-charge estimation method based on a Hammerstein model, and the method comprises the steps: constructing a second-order RC circuit equation of a lithium battery, describing a dynamic linear module of the Hammerstein model through a noise transfer function model, and constructing a lithium battery system through a static nonlinear module of an adaptive neural fuzzy network; designing a Gaussian signal, inputting the Gaussian signal into the agent model of the lithium battery system to obtain corresponding Gaussian signal output, and decoupling the static nonlinear module and the dynamic linear block by using the covariance function characteristic of the Gaussian signal; identifying parameters of the noise transfer function model by using a least square method based on a covariance function, solving parameters of the adaptive neural fuzzy network by using a crown porcupine optimization algorithm, and updating the weight of the adaptive neural fuzzy network by using a stochastic gradient algorithm with a forgetting factor; and constructing an OCV-SOC curve of the open-circuit voltage and the state of charge by adopting polynomial fitting, and taking output obtained by the Hammerstein model as input of the polynomial fitting to obtain an estimated value of the state of charge SOC.

The invention discloses an intelligent segmentation and feature analysis method for a medical image, and relates to the technical field of image analysis, and the method comprises the steps: reading a multi-modal medical image, and carrying out the preprocessing and size standardization; performing medical image segmentation based on a U-Net structure, performing edge detection by adopting a Sobel operator, and optimizing the edge of the segmented image in combination with morphological operation to obtain an edge-optimized focus segmentation map; feature point matching is carried out on the multi-modal focus segmentation image based on self-organizing mapping, and non-rigid registration is carried out through TPS transformation based on matched feature points; carrying out foreground region enhancement operation on the registered image, introducing a channel attention module based on a DenseNet-201 model to carry out feature extraction on the registered image, and optimizing features by using a whale optimization algorithm to generate an optimal feature subset; and carrying out illness state classification on the feature subsets by an adaptive neural fuzzy inference system optimized based on a genetic algorithm.

The invention relates to the technical field of industrial control systems, and particularly discloses a selenium-rich water equipment water yield control system based on neural fuzzy control. The system comprises a data acquisition module, a neural fuzzy control module, an actuator driving module and an online learning and parameter adjustment module, fuzzy rules and membership parameters are dynamically optimized through a neural network, a gradient descent algorithm and a working condition memory unit are combined, high-precision self-adaptive control over the water yield is achieved, and the response speed and stability of the system are improved.

The application provides a power system frequency anti-interference regulation method and device under certainty network multiple attacks, and the method comprises the following steps: obtaining multiple groups of frequency regulation related parameters of a controlled area; inputting regional frequency deviation data and regional power deviation data in each group of frequency regulation related parameters into an adaptive network attack detection system to obtain estimated regional control error data; the adaptive network attack detection system utilizes sample data under multiple network attacks collected in advance to train a neural fuzzy system physical model; according to actual regional control error data and estimated regional control error data of the multiple groups of frequency regulation related parameters, root mean square error is calculated; according to the root mean square error and a preset range, a relieved regional control error is determined from the actual regional control error and the estimated regional error. The application comprehensively considers multiple attacks, can quickly detect new attacks, and improves power adjustment efficiency.

The invention provides a partial discharge intelligent identification method and system based on collaborative reasoning, and belongs to the field of partial discharge detection.The method comprises the steps that a semantic structure of high-dimensional PD data is explicitly deconstructed through a multi-scale feature information graph and a sparse spectrum division algorithm, and feature sub-channels strongly related to a discharge mechanism are separated; semantic interference in field data is effectively inhibited; furthermore, a fuzzy modeler induced by a channel structure is adopted to independently learn a local rule set, and a dynamic fusion mechanism driven by cross-channel prediction consistency is combined, so that the tolerance to voltage phase loss, background noise disturbance and equipment isomerism is remarkably improved. Compared with a traditional neural fuzzy model, the method has the advantages that non-exclusive fuzzy classification of an unknown discharge mode is realized while interpretability is maintained, the problem of model failure caused by data distribution offset in field deployment is solved, the recognition error rate is obviously reduced, and a high-robustness solution is provided for intelligent diagnosis of power equipment.

The invention relates to the technical field of performance evaluation of fiber composite yarns, in particular to a comprehensive performance evaluation and intelligent prediction method for multi-component fiber composite yarns. By combining a fuzzy analytic hierarchy process, a fuzzy ideal solution sorting method Fuzzy-AHP-TOPSIS and an adaptive neural fuzzy inference system (ANFIS) algorithm, quantitative evaluation of yarn performance and accurate prediction of key indexes are realized. A Fuzzy-AHP algorithm is utilized to reasonably distribute the weight of each performance index, and a Fuzzy-TOPSIS method is utilized to compare the distance between a sample and an ideal optimal solution and the distance between the sample and a worst solution so as to carry out dynamic sorting. An ANFIS algorithm is adopted to learn a complex nonlinear relation between fiber characteristics and yarn performance, so that a high-precision prediction model is established. The research and development efficiency and scientificity of textile enterprises are improved, an innovative solution is provided for evaluating and predicting the performance of the multi-component fiber composite yarn in an actual scene, and the method has wide application prospects in the fields of textile material research and development and yarn production.

The invention discloses a method for testing the oil content of low-water-content oil field sludge, and relates to the technical field of intelligent oil field environmental protection monitoring, and the method comprises the following steps: collecting a solid slag deposition original frequency signal, combining a frequency drift rate characteristic and a sludge viscosity parameter, constructing a neural fuzzy inference model, and generating a real-time oil content estimated value; calculating a comprehensive dynamic risk quantized value and a solid slag accumulation space gradient vector according to the real-time oil content estimated value, triggering a mechanical arm grabbing instruction, and marking a high-oil-content solid slag sample; carrying out vacuum pressure forming treatment on the marked high-oil-content solid residue sample, calculating a thickness error and a flatness error, and generating a standard detection sample with a flat surface and controllable thickness; a standard detection sample is placed in a quantum-terahertz coupled field, quantum-state multi-source response data are synchronously collected, and accurate oil content is generated through a deformable convolution kernel modulated by fluorescence lifetime. According to the method, the bottleneck of insufficient sensitivity under the condition of low water content is broken through, and high-precision quantitative analysis is realized.

The invention relates to the technical field of milling process risk assessment and parameter optimization, in particular to a deep neural fuzzy reasoning system which comprises a semantic layer, a rule layer and a reasoning layer which are in signal connection in sequence and cooperatively achieve tool risk and quality risk assessment of a milling process. The method specifically comprises the steps that a semantic layer receives milling parameters, and numerical milling parameters are converted into a fuzzy feature matrix through an interval Type-2 Gaussian membership function; according to the method, expert knowledge is embedded through interval Type-2 fuzzy logic to adapt to a small sample milling scene, an IF-THEN activation rule is output to enable a risk decision basis to be traceable, reasoning real-time performance is guaranteed by means of Top-k sparse aggregation, meanwhile, closed-loop self-adaptive adjustment of milling process parameters is supported, the method is suitable for milling scenes of complex parts and novel materials, and the method is suitable for large-scale popularization and application. And the production efficiency can be improved while the machining quality is guaranteed.

The application discloses a kind of based on adaptive neural fuzzy inference fuel cell ship energy management strategy method, comprising the following steps: obtaining the topological structure of fuel cell ship hybrid power system, and its operating typical working condition information, the steps of obtaining the globally optimal hybrid power system load distribution by offline algorithm;By discrete solving working condition every moment optimal equivalent factor, the step of taking working condition calculation result as training sample;Build and train adaptive neural fuzzy inference system (ANFIS), calculate to obtain optimal equivalent factor, the step of bringing result into ECMS algorithm, on-line calculation ship sailing working condition obtains optimal distribution result, the improvement of the present application is realized on-line ideal power distribution by ANFIS calculation ECMS equivalent factor, combined with the calculation characteristics of three strategies, can on-line calculation obtain the optimal solution of ship real-time power distribution, with good global optimization ability.

The application provides a vehicle fault diagnosis method and device based on multi-source data fusion and a storage medium. The method comprises: collecting real-time state data and real-time alarm data of a target part, obtaining external environment data and map navigation data; after data preprocessing, the multi-source data set target features are obtained by fusion, the target features extracted from the multi-source data set are input into the adaptive neural fuzzy inference system, the target features are mapped to multiple fuzzy sets, and the member function is used for fuzzification; the rule weight of each target feature is calculated to reflect the fuzzy strength; the neural network learning algorithm is used to train the inference system, the member function and the rule weight are adjusted, the fuzzy output is converted into a specific numerical value or a fault level in the defuzzification process by using the output member function, so that the health state of the part is judged. The application provides a fault diagnosis output with high interpretability, improves the accuracy, and can perform fault diagnosis in a wide range of vehicle operating environments.

This invention aims to provide a smart battery control method for cold chain environments, comprising the following steps: A) Sensor data acquisition, real-time acquisition of ambient temperature T, ambient humidity H, condensate level W, battery voltage U, and battery temperature Tb; B) Data preprocessing; C) Setting preset thresholds, including temperature threshold, humidity threshold, SOC threshold, and insulation resistance threshold; D) Establishing a fuzzy rule base, inputting ambient temperature T, ambient humidity H, condensate level, alarm level, and BMS status into corresponding functions of the fuzzy rule base, outputting various control parameters for control by a controller, while simultaneously providing feedback on the status. An adaptive neural fuzzy control algorithm is used to correct and optimize the above functions in real time, achieving nonlinear dynamic regulation. The method of this invention can effectively solve the technical problems of battery range degradation, high short-circuit risk, and shortened lifespan in cold chain environments characterized by low temperature, high humidity, and easy condensation.

The invention relates to the technical field of crossing of coal mine safety engineering and artificial intelligence, and provides a gas extraction and coal seam anti-reflection intelligent decision-making method based on a three-dimensional geological model, which comprises the following steps: extracting multi-dimensional geological parameters in a preset range of a working face to be mined and carrying out standardization processing to form a structured parameter matrix; inputting the structured parameter matrix into a pre-trained adaptive neural fuzzy inference system model, and outputting an extraction difficulty level score of the to-be-mined working face; according to the extraction difficulty level score, matching at least one gas extraction and coal seam anti-reflection technology combination from a preset structured measure library; and based on a mixed water circulation-moth fire optimization algorithm, engineering parameters in the matched technical combination are optimized, and an optimized gas extraction and coal seam anti-reflection construction scheme is output. According to the method, rapid and accurate optimization of multi-target engineering parameters is realized, and the scientificity and decision-making efficiency of a gas extraction scheme are remarkably improved.

The present invention belongs to the field of intelligent construction and specifically discloses a shield axis deviation prediction model and its construction method, prediction method, and system. The method comprises: training a hybrid model using a training set; the trained hybrid model is the shield axis deviation prediction model; the training set includes splicing parameters and corresponding shield axis deviation data; the shield parameter time series signal is segmented; each obtained signal segment is processed to obtain the splicing parameters; the hybrid model includes an adaptive neural fuzzy inference system (ANFIS) and a fully connected spatiotemporal graph neural network model (FC-STGNN); the ANFIS quantifies the splicing parameters and outputs the parameters; the FC-STGNN performs graph construction and graph convolution based on the splicing parameters and outputs the parameters; and the parameters and the sum are weightedly fused to output the shield axis deviation result. The present invention can improve the accuracy and adaptability of shield axis deviation prediction.

The application discloses a valve cooling system main waterway state prediction method based on deep learning, and the method comprises the following steps: building an electric-flow-heat-mass transfer multi-physical field coupling simulation model of the valve cooling system main waterway; driving a deep learning algorithm with simulation data to obtain a deep learning valve cooling system main waterway data prediction model; using the obtained data prediction model to realize large-scale data acquisition, screening key state variables based on a variable control method; proposing a valve cooling system main waterway state evaluation method based on the deep learning model, and realizing full-automatic state division through an adaptive neural fuzzy system. The application can simulate and analyze the distribution of each key parameter under the condition of multi-physical field coupling of the valve cooling system main waterway, and reduce the dimension of the simulation model through the deep learning algorithm, realizes the high-speed of the valve cooling system main waterway state prediction, and judges the working state of the valve cooling system main waterway through the proposed state evaluation criterion.

The invention provides a color box printing self-adaptive drying method based on multi-mode perception, and belongs to the technical field of intelligent manufacturing and printing process control. Multi-modal data in the printing process are collected through a multi-modal sensor; preprocessing the multi-modal feature sequence into a multi-modal feature sequence with consistent space; and inputting the multi-modal feature sequence into the lightweight cross-modal adaptive coding network, obtaining spatial features of each modal through the shallow feature extraction network and performing weighted optimization, capturing a data time evolution rule of each modal through the time dynamic modeling network, and realizing heterogeneous modal fusion and consistency calibration through the modal consistency correction network. And outputting a comprehensive representation vector of the printing ink drying state, inputting the comprehensive representation vector into an adaptive controller, completing feature fuzzification mapping through a Gaussian membership function, and realizing neural fuzzy reasoning based on a fuzzy rule to generate an optimal drying parameter. According to the method, intelligent upgrading is realized on a closed-loop control link of perception, analysis, decision making and correction, and the energy consumption and the rejection rate are remarkably reduced.

The invention provides a weak power grid-oriented doubly-fed wind turbine generator intelligent cooperative control method, which comprises the following steps of: acquiring the actual voltage of a grid-connected point in real time to obtain a voltage deviation index in a power grid operation state, and generating a weak power grid degree index for representing the congenital strength of a power grid based on a short circuit ratio; the weights of the weak grid degree index and the voltage deviation index are flexibly set, and the control priorities of power maximization and voltage stabilization are adaptively switched, so that a corresponding weak grid strength value is generated; and acquiring the rotating speed and the wind speed of a rotor in real time, inputting the rotating speed and the wind speed into a self-adaptive neural fuzzy inference network of the wind turbine generator, and solving the self-adaptive neural fuzzy inference network by utilizing a chaotic Salp group optimization algorithm based on the weak power grid intensity value so as to output an electromagnetic torque reference value and an active power reference value. According to the method, the wind turbine generator can still operate stably under the weak grid condition, and meanwhile, voltage drop of the power grid caused by MPPT output is prevented, so that the stability of the wind turbine generator and the grid connection friend performance are improved.

The application provides a yellow rice wine fermentation prediction method and system based on an ANFIS and a random fractal search algorithm, the method comprising collecting data samples of a pre-fermentation process of different production batches of yellow rice wine; dividing the data samples into a training set and a test set, and performing normalization processing on the data samples; inputting the processed data samples into a multi-output adaptive neural fuzzy inference system model constructed in advance, identifying and optimizing model parameters of the multi-output adaptive neural fuzzy inference system model by using a hierarchical learning random fractal search algorithm, obtaining an optimized multi-output adaptive neural fuzzy inference system model, and predicting a yellow rice wine fermentation state. The application improves the precision and generalization ability of the model, and can achieve good prediction of the fermentation state of different production batches of yellow rice wine.

The application discloses an intelligent excrement sewage treatment system and method, and belongs to the field of sewage treatment.The system comprises a data acquisition module, which is used for collecting COD, ammonia nitrogen, DO, pH, water temperature, SS and microbial activity parameters of sewage in real time, performing normalization treatment on the collected water quality parameters, and forming a unified standard data basis; a first model module, which is based on the data processed by the data acquisition module, uses a particle swarm algorithm to optimize membership function parameters and fuzzy rules of an adaptive neural fuzzy inference system, trains an ANFIS model, outputs a prediction value of COD concentration in a biochemical tank in real time, and forms a COD prediction model; and a second model module, which takes the COD prediction value in the first model module and the data processed by the data acquisition module as inputs, constructs a Stacking integrated model, and contains base learners and meta learners in the integrated model, and then adopts a five-fold cross-validation method to generate a prediction result of the base learners.

The application discloses a kind of crop precision irrigation method and system based on algorithm fusion, it is related to intelligent agriculture and precision irrigation control technical field, method includes: the time series data of meteorology, soil, crop physiology and irrigation process are collected, carry out exception elimination, missing completion and standardization processing and construct derivative feature;The historical characteristic sequence is input to the bidirectional time series network with attention to obtain time series representation, input neural fuzzy inference network to output future water demand prediction value and corresponding prediction interval, obtain confidence from prediction interval;Water demand prediction value, confidence and crop stress are input to the first layer fuzzy inference to obtain basic irrigation duration;Soil water potential and post-irrigation feedback are input to the second layer fuzzy inference to obtain valve fine tuning amount;Fusion generates irrigation instruction and drives execution equipment.By outputting water demand prediction interval and constructing confidence, the prediction reliability is improved, and by double-layer fuzzy inference, soil water potential and post-irrigation feedback are combined to realize executable and safety protection of irrigation instruction.

The invention relates to the technical field of process control, in particular to a chlorinated alkane reaction heat optimization method based on dynamic neural fuzzy control, which comprises the following steps: acquiring a current process state diagram, and generating an error vector by comparing the current state diagram with a reference state diagram; the error vector is input into a dynamic neural fuzzy controller, a depth prediction neural network generates an optimal gain matrix according to spatial features of the depth prediction neural network to realize predictive adjustment, and a fuzzy engine determines basic control intensity according to an intensity trend of the depth prediction neural network to ensure system stability; and the two outputs are combined to generate a final control instruction for adaptive adjustment. The prediction model is trained by a physical simulation model calibrated by experiments. Through cooperation of the prediction model and the fuzzy logic, real-time, accurate and adaptive optimization control of the distributed thermal field is realized.

The invention discloses a material compliance intelligent verification method based on deep learning, and the method comprises the following steps: preprocessing material detection data and a regulation text, and obtaining a material original feature set and a regulation semantic element set; inputting the original feature set of the material into a multi-modal fuzzy coding module to obtain a fuzzy feature set of the material; constructing a law and regulation cognitive map model, and generating a law and regulation fuzzy template and a rule initial set; constructing a hierarchical mixed cognitive neural fuzzy inference network, and outputting a preliminary compliance judgment result; performing self-adaptive updating on the regulation fuzzy template and the rule initial set, and optimizing a multi-mode fuzzy coding module to obtain an updated tracing index; and executing composite compliance reasoning based on the updated traceability index, and outputting a final compliance judgment result and a compliance interpretation report. According to the method, deep learning and neural fuzzy reasoning are fused, intelligent verification of material compliance is realized, and the method has the advantages of high precision, self-adaption and interpretability.

The invention provides a kitchen guarding system with a pipeline flame monitoring function, and relates to the technical field of fire safety, and the kitchen guarding system comprises an acquisition module which is used for acquiring multi-mode environment data of a kitchen; the extraction module is used for carrying out feature extraction on the multi-modal environment data; the judgment module is used for performing prior abnormity judgment on the kitchen environment; the construction module is used for constructing a flame monitoring model based on the improved YOLOv8 model; the monitoring module is used for carrying out flame monitoring on the kitchen pipeline through a flame monitoring model according to the visual ROI features; the fusion module is used for fusing the flame monitoring score and the multi-modal feature vector through a self-adaptive neural fuzzy inference model, and determining the risk probability of the fire in the kitchen; and the guarding module is used for performing graded guarding on the kitchen according to the risk probability and the flame position. According to the invention, environment information can be comprehensively collected, the accuracy of kitchen fire monitoring is improved, and all-around kitchen safety protection is realized.

The invention belongs to the technical field of intelligent health monitoring and exercise rehabilitation equipment, relates to an old people fitness method and system with an intelligent chip, and aims to solve the problem that traditional equipment is insufficient in the aspects of multi-dimensional data fusion, personalized health response model construction and self-adaptive intervention scheme generation. The method comprises the following steps: acquiring and analyzing multi-modal biomechanical and physiological data, and extracting feature vectors; constructing a dynamic health response model based on an adaptive neural fuzzy inference system, and representing a nonlinear mapping relationship between the mechanical load and the physiological stress; and according to the user health target reverse solution model, generating an optimal biomechanical instruction (such as adjusting the resistance of the fitness ball) and personalized nutrition supplement suggestions. According to the technical scheme, health management from popularization to personalization and from passivity to initiative is achieved, and the scientificity and effectiveness of fitness of the old people are effectively improved.

The invention relates to the technical field of power distribution room heat dissipation, in particular to a neural fuzzy control-based high and low voltage power distribution room automatic heat dissipation system, which comprises the following steps: a model construction module, which is used for collecting power distribution room data to construct a simulation model, and the power distribution room data comprises equipment load parameters and environment parameters; the association prediction module is used for acquiring environmental parameters and equipment load parameters of corresponding monitoring points in the power distribution room in real time based on the simulation model to determine target pheromones, and associating a plurality of target pheromones based on a single monitoring point and a corresponding propagation space to obtain an association network; and the heat dissipation control module formulates control information of the heat dissipation mechanism to the power distribution room based on the association network, the control information comprises the heat dissipation direction, the target heat dissipation power and the heat dissipation position, cooling preparation can be made for the position corresponding to the needed monitoring point in advance according to the distribution condition of the temperature field, and the heat dissipation efficiency is improved.

The present invention provides a collaborative reasoning-based intelligent identification method and system for partial discharge (PD). This system belongs to the field of partial discharge detection. By constructing a multi-scale feature information graph and using a sparse spectrum partitioning algorithm, the semantic structure of high-dimensional PD data is explicitly deconstructed, separating feature sub-channels strongly correlated with the discharge mechanism and effectively suppressing semantic interference in field data. Furthermore, a channel-structure-induced fuzzy modeler is used to independently learn local rule sets. Combined with a dynamic fusion mechanism driven by cross-channel prediction consistency, this method significantly improves tolerance to voltage phase loss, background noise disturbances, and device heterogeneity. Compared to traditional neural fuzzy models, this method achieves non-exclusive fuzzy classification of unknown discharge patterns while maintaining interpretability. This solves the problem of model failure caused by data distribution offsets during field deployment, significantly reduces recognition error rates, and provides a highly robust solution for intelligent diagnosis of power equipment.

The application discloses a method for determining the chloride ion permeability of concrete in an underground structure, comprising the following steps: S1, collecting recycled aggregate concrete component data and permeability indexes; S2, dividing the data collected in step S1 into a training set and a test set; S3, establishing a chloride ion permeability prediction model by using an adaptive neural fuzzy inference system; S4, inputting the training set in step S2 into the chloride ion permeability prediction model in step S3, and optimizing and adjusting the chloride ion permeability prediction model parameters by using a chaos-based glowworm algorithm; S5, inputting the test set in step S2 into the optimized chloride ion permeability prediction model, testing the chloride ion permeability prediction error, and obtaining a trained chloride ion permeability prediction model; and S6, predicting the chloride ion permeability by using the trained chloride ion permeability prediction model. The method overcomes the defects of long time period and high test cost of the prior art, and realizes accurate prediction of the chloride ion permeability of concrete.