51 results about "Fuzzy logic inference" patented technology

The invention discloses a rainfall type landslide early warning method based on multi-source environment threshold and nonlinear fusion. The method comprises the following steps: constructing a landslide disaster-inducing factor set; introducing soil humidity, vegetation indexes and evapotranspiration, and calculating a threshold parameter corresponding to the rainfall type landslide event to obtain an environment threshold point set; according to the landslide disaster-inducing factor set, constructing and training a landslide susceptibility model based on progressive learning; adopting a double-layer nonlinear fusion model based on multi-source data fusion and quality perception gating, and combining a landslide susceptibility model to obtain comprehensive risk probability distribution; and performing graded early warning based on the comprehensive risk probability distribution to complete rainfall type landslide early warning. According to the method, on the basis of traditional rainfall parameters, early-stage disaster-pregnant environment factors are introduced, and a multi-source environment threshold value is formed; fuzzy logic reasoning is adopted to realize nonlinear fusion of the threshold information and the landslide susceptibility base map; and dynamically reflecting a regional environmental condition evolution process in combination with an annual iterative updated susceptibility layer, and realizing finer and more adaptive space grading early warning.

The invention discloses an operation risk analysis method and system for a virtual power plant, relates to the field of risk analysis, and solves the problem of insufficient operation stability of an existing virtual power plant, and the method comprises the steps: S1, collecting the operation data of various devices of the virtual power plant; s2, acquiring historical fault data, and constructing a fault rule base; performing fuzzy logic reasoning based on historical fault data to obtain membership values of the abnormal parameters; real-time equipment parameters are collected, calculation is carried out, and a fault judgment value is obtained; fault equipment is judged; s3, calculating the fluctuation condition of the equipment parameters, constructing a fluctuation interval, analyzing and calculating a fault risk value according to the fluctuation interval, judging pre-fault equipment, counting the fault equipment and the pre-fault equipment, and constructing a maintenance equipment list; s4, adjusting the energy supply of the equipment according to the energy supply plan in combination with the maintenance equipment list; the stability of the virtual power plant can be effectively improved.

The invention relates to the technical field of agricultural Internet of Things, and discloses an edible mushroom growth environment regulation and control method and system based on multi-source sensing data, and the method comprises the steps: deploying a multi-source sensor network, unifying time synchronization, and carrying out event-driven space-time alignment and three-dimensional mapping. Carrying out multi-dimensional reliability evaluation and environment correction, and obtaining an environment parameter fusion data set by adopting a fuzzy logic reasoning method; performing space-time Kriging interpolation, and obtaining a heterogeneous microenvironment feature database by adopting a multi-source data collaborative correction method; carrying out cross-modal attention fusion; performing multi-scale convolution and time sequence attention classification; carrying out deep reinforcement learning and multi-objective optimization; carrying out online incremental learning optimization to obtain a self-adaptive optimized partition collaborative regulation and control strategy; according to the method, the technical problems of insufficient multi-source data fusion precision, lack of environment spatial and temporal distribution modeling, inaccurate parameter coupling prediction, lack of self-adaptability of regulation and control strategies and the like are solved.

The invention relates to the technical field of robot intelligent control, and discloses an inspection robot task scheduling and state switching method for quantifying a state machine, which comprises the following steps: acquiring state machine operation configuration data; performing health degree evaluation on the sensor, navigation, communication and battery systems in an initial state; in the idle state, a segmented charging strategy is adopted, and task priorities are calculated through a neural network; a breakpoint resume and event-driven architecture is adopted to execute tasks in the inspection state; in a warehouse returning state, a deep neural network is adopted to predict return flight energy consumption, and a path is re-planned through multi-objective optimization when the electric quantity is insufficient; processing a control instruction by adopting speed limitation in a manual or mapping state, and starting an SLAM module in the mapping state; and in an abnormal state, a fuzzy logic reasoning system is adopted to calculate an abnormal grade, and recovery waiting, degradation protection or alarm is executed according to the grade. According to the invention, autonomous operation and intelligent decision making of the inspection robot in a complex dynamic environment can be realized.

The invention discloses a visual scene graph generation method based on differentiable fuzzy logic reasoning, and solves the technical problems of semantic fuzziness, logic common sense deficiency and the like during long tail relation processing in the prior art. The method comprises the following steps: inputting a training image into a target detection module, and respectively outputting corresponding high-dimensional geometric embedding vectors to a relation classifier and a fuzzy mapping layer; outputting a visual prediction branch by the relation classifier; meanwhile, the fuzzy mapping layer outputs a fuzzy membership degree vector; the logic tensor reasoning module is combined with a common sense rule in an external knowledge base, simulates a logic reasoning process by utilizing a differentiable logic operator, and outputs a logic reasoning branch of which the relation of each pair of objects meets a preset logic rule in the training image; a gating residual fusion module performs weighted fusion on the visual prediction branch and the logical reasoning branch to generate a scene graph triple of the training image; and finally, training the network model, inputting a test image into the trained model, and outputting a corresponding visual scene graph.

This invention belongs to the field of industrial network performance optimization technology, specifically providing a DDS-5G network collaborative optimization method based on fuzzy logic. By setting static mapping rules, the QoS Policy parameters of the DDS are mapped to the QoS flow identifiers of the QoS flows in the 5G network, thereby achieving initial DDS-5G collaboration. Simultaneously, by establishing a fuzzy logic inference system, using the QoS Policy parameters and real-time network state parameters as input variables and 5QI as the output variable, and by optimizing and adjusting the QoS Policy parameters of the DDS through DQN and updating the fuzzy logic parameters of the fuzzy logic inference system, further DDS-5G network collaborative optimization is achieved. Through a cross-layer adaptation mechanism, efficient collaboration between the application layer and the 5G network is realized, making it suitable for scenarios with high requirements for low latency and high reliability, such as industrial automation and intelligent manufacturing.

This invention relates to the field of speed control technology, specifically to an intelligent lamination and tension control system and method for multi-ribbed belt production lines in washing machines. The system includes: a multi-dimensional state information extraction module, a real-time collaborative control module, a control performance evaluation module, and a fuzzy rule self-tuning module. In this invention, by calculating tension error and lamination position deviation, a basis for dynamic adjustment is provided, eliminating reliance on preset fixed parameters. By invoking a fuzzy logic inference engine, tension error, error change rate, and position deviation are fused and processed to achieve synchronous and precise control of the transmission roller speed and the position of the correction mechanism. This effectively replaces the slow-responding mechanical tension device, solving the problems of tension fluctuation and lamination deviation. Furthermore, a long-term comprehensive performance index is introduced to evaluate the control effect. When performance deteriorates, a gradient descent algorithm is immediately triggered to self-tune the fuzzy rule parameters, continuously optimizing the control strategy and ensuring the system maintains high stability and high accuracy.

The application discloses a charging pile power management system based on Internet of Things and concretely relates to the technical field of Internet of Things, and comprises a data acquisition module for collecting real-time operation data of the charging pile through a sensor to form a data set; a data processing module for processing the data according to a preset or optimized strategy to generate a processed data set; a scene analysis module for analyzing the processed data set and dividing charging pile operation scenes; a data feature extraction module for extracting and analyzing features when the optimized mechanism is triggered; a logic judgment module for formulating an optimized strategy through fuzzy logic reasoning and sending the optimized strategy to the data processing module; and a power energy efficiency management module for adaptively adjusting power distribution and improving system energy efficiency; the application can reduce data transmission delay and improve response speed, so that users can obtain a smoother experience when using the charging pile, and the transmission of redundant information is reduced and efficient power management is realized through the optimized strategy.

The invention discloses an energy efficiency optimization control method for a motor system driven by an industrial internet of things, and provides a three-stage progressive energy efficiency optimization algorithm: in the first stage, a collaborative optimization mechanism of a multi-physics coupling loss model and fuzzy logic reasoning is established; carrying out nonlinear mapping on iron loss, copper loss and mechanical loss by adopting a variable universe adaptive fuzzy controller; in the second stage, a self-adaptive parameter identification engine based on improved particle swarm optimization (PSO) is designed, and motor parameter online drift compensation and loss model coefficient dynamic correction are achieved; and in the third stage, a real-time execution strategy combining model predictive control (MPC) and dynamic flux linkage trajectory planning is implemented, and the amplitude and phase angle of the stator flux linkage are actively adjusted according to a load torque prediction result. The method overcomes the defects that traditional loss model control (LMC) is sensitive to parameters and search control (SC) is slow in convergence.

The application discloses a kind of transformer health degree intelligent evaluation system based on fuzzy logic, it is related to fuzzy logic reasoning field.The application obtains abnormal type combination and operation data value interval combination according to the test operation data kind with abnormal identification, and then generates several multimodal state combinations, sets initial decision evaluation value to each multimodal state combination, obtains result decision evaluation value by the initial decision evaluation value of each multimodal state combination for multiple rounds of iteration, starts to collect several real-time operation data from the target transformer put into use, whenever a health assessment time point judges that real-time operation data exists abnormal, according to the kind and the value of real-time operation data, multiple multimodal state combinations are retrieved, the multimodal state combination with the maximum result decision evaluation value is selected to update the residual life length of target transformer.

The invention discloses a water level threshold value dynamic adjustment method and system based on automatic drainage of a transformer substation, and relates to the technical field of transformer substation hydraulic monitoring, and the method comprises the following steps: obtaining water level data of a transformer substation drainage pipe, and classifying water level states based on the water level data to obtain a water level state set; constructing a membership degree input set based on the water level state set, and performing fuzzy logic reasoning on the membership degree input set to obtain a drainage pump control signal; adjusting an interval range of a preset membership function according to the drainage pump control signal to obtain a water level fuzzy decision set; state transition is carried out on a drainage pump control signal based on a water level fuzzy decision set, a transition control threshold sequence is obtained and discretized into a drainage pump start-stop command capable of being recognized by a PLC, and the problem that drainage is not timely or frequent start-stop is possibly caused due to the fact that a drainage threshold value is fixed and inflexible due to water level fluctuation in substation drainage pump control is solved.

This invention discloses an energy-saving operation method for hydraulic motors based on pressure detection and energy replenishment, specifically relating to the field of energy-saving control. The method includes: firstly, collecting, filtering, and preprocessing multiple operating parameters of the hydraulic system and drive motor using time synchronization; then constructing a dimensionless characteristic function from multiple dimensions and achieving nonlinear fusion through adaptive weight allocation to obtain a comprehensive state coupling value; constructing a pressure advance prediction model based on historical data, and performing consistency verification and confidence analysis on the comprehensive state and predicted state; using the comprehensive state coupling value, pressure prediction value, and confidence value as inputs, employing fuzzy logic reasoning to output motor speed and accumulator valve group control commands, ultimately driving the actuator and transmitting the operating parameters back to form a closed loop; this invention improves the system's dynamic response and anti-interference capability, optimizes the motor operating range while ensuring pressure stability, and improves energy utilization, making it suitable for efficient and energy-saving operation of hydraulic systems under complex working conditions.

The application provides a kind of hybrid model fault early warning method and system based on timing prediction and fuzzy logic, device state feature set is constructed by collecting the operation and maintenance data of equipment in continuous operation cycle, feature correlation analysis is carried out on device state feature set, device state potential vector reflecting the dynamic coupling relationship between parameters is generated, fuzzy rule matching is carried out by calling pre-trained fuzzy logic inference model, and fuzzy state set containing multi-dimensional fuzzy subset is generated;Fuzzy state set is processed by space-time correlation, and multi-dimensional decision cloud chart is generated, which is reconstructed in space by quantization weight distribution mechanism, and the optimized decision matrix is obtained;Based on the confidence distribution characteristics corresponding to each fault type, the fault early warning signal containing fault early warning level and fault location positioning information is generated.The application can improve the accuracy and timeliness of fault early warning, and provides reliable decision support for equipment operation and maintenance management.

The invention discloses a trajectory tracking and stability cooperative control method for a multi-axis distributed driving vehicle, and provides a hierarchical control architecture. The upper-layer trajectory tracking controller comprises a self-adaptive preview linear quadratic regulator based on fuzzy logic reasoning, and the self-adaptive preview linear quadratic regulator dynamically adjusts the preview distance according to the vehicle speed and the acceleration and outputs a steering angle instruction; and the seven-section S curve speed planner generates a smooth speed and acceleration curve. The lower-layer stability and torque distribution controller comprises an equivalent sliding mode controller for calculating an additional yaw moment based on the yaw velocity and the side slip angle error; and based on a torque distributor of quadratic programming, introducing an inter-axle yawing moment coefficient as a geometric constraint, tracking a required torque, and minimizing a tire attachment utilization rate and a slip rate as a target distribution torque. Through cooperation of the upper layer and the lower layer, high-precision trajectory tracking, high robust stability and longitudinal smoothness are considered, and the comprehensive performance of the multi-axle vehicle under the limiting working condition is remarkably improved.

The application relates to a significant scene graph generation method and device based on fuzzy logic reasoning relationship importance, a scene graph generation model test method and device, and a computer device. The method comprises the following steps: S100, calculating the importance score of the real relationship of each image sample in a target data set; S200, constructing a target detector; S300, constructing a semantic extractor and an instance feature refinement module; S400, constructing a bounding box modeling module and a feature splicing module; S500, constructing a feature fusion module and a relationship representation modeling module; S600, constructing a relationship loss weighting module; S700, under the condition that the number of training image samples reaches the batch processing size, returning to step S200; under the condition that all image samples in the training set are read, entering step S800 to output a scene graph generation model. The method can flexibly and comprehensively evaluate the importance of the relationship without reducing the number of relationship samples.

This application provides a parking charging strategy generation method and system based on user behavior analysis, relating to the field of parking management technology. The method includes: constructing a multi-dimensional user behavior profile; using a time series prediction model to predict the expected dwell time and the target power demand upon departure; inputting real-time vehicle status data into a fuzzy logic inference engine to calculate charging urgency; based on charging urgency, target power demand, and the real-time availability of charging piles in the parking lot, using a deep reinforcement learning model to perform dynamic game theory to generate a personalized charging stop strategy; pushing the strategy to the user terminal and, in response to the user's confirmation command, executing pre-locking of charging pile resources. This application solves the technical problem of low charging pile utilization efficiency in existing technologies due to the inability to dynamically respond to real-time vehicle status and user behavior changes, and improves the utilization rate of charging pile resources through personalized charging stop strategies.

The application provides an electric loader, and an energy recovery system and method, wherein a whole vehicle controller identifies and synthesizes the whole vehicle braking intensity according to the displacement and speed of a brake pedal and an accelerator pedal, hydraulic braking pressure information and vehicle speed through fuzzy logic reasoning, the driver's deceleration and braking intention, deceleration, coasting and braking intensity, then calculates the whole vehicle braking force demand according to the whole vehicle braking intensity and performs front and rear wheel braking force distribution, and performs electro-hydraulic braking force distribution according to the braking force demand and the braking intention, finally, the front and rear shaft motors are controlled and adjusted to perform regenerative braking through a PID control algorithm, and the first and second electromagnetic proportional directional valves are controlled and adjusted to perform hydraulic braking, so that the whole vehicle braking and energy recovery are completed, and the problem of low energy recovery efficiency of the electric loader is solved.

The application discloses a method for reducing the false alarm rate of biological induction perimeter alarm, and particularly relates to the field of infrared induction technology; background temperature data of a monitoring area is acquired, a background thermal field benchmark model is constructed, and a background benchmark temperature value is calculated; current background temperature is acquired according to a preset time interval, and a dynamic background temperature difference drift rate is calculated; heat source change information is extracted from a thermal imaging image sequence, the variance of the heat source change in a time window is calculated, and the stability of the static heat source signal is obtained; the above two features are normalized, and a feature parameter set is constructed; the set is input into a fuzzy logic reasoning model, a PIR sensor signal credibility parameter is output according to a preset fuzzy rule; according to the credibility result, an alarm judgment path is dynamically selected, intelligent fusion and judgment of the PIR signal and the video recognition result are realized; the method can effectively identify the PIR false triggering risk in a complex thermal environment, reduce the false alarm rate, and improve the reliability and adaptability of the perimeter security system.

The application belongs to the technical field of airport perimeter security monitoring, and discloses an airport perimeter hierarchical early warning linkage method and system based on fuzzy logic reasoning. The method generates infrared and visible light panoramic images through panoramic scanning of the airport perimeter, detects and identifies the intrusion targets in the perimeter defense area in the infrared and visible light panoramic images through a multi-modal target detection algorithm based on deep learning, divides the intrusion target warning levels through a fuzzy logic algorithm, judges the priority of the intrusion target warning levels, uses an OPENCV algorithm library to mark the trajectories of multiple coordinate points closest to the intrusion target in the perimeter panoramic base map, displays the motion trajectory of the current intrusion target, and judges the intention of the intrusion target. The application can adapt to different airport environments through the self-optimization capability of the rule base, reduce the artificial patrol load while ensuring high reliability, and enhance the intelligent level and safety and control efficiency of the perimeter security system.

The invention discloses a method for reducing the false alarm rate of biological induction perimeter alarm, and particularly relates to the technical field of infrared induction. Acquiring background temperature data of a monitoring area, constructing a background thermal field reference model and calculating a background reference temperature value; obtaining a current background temperature according to a preset time interval, and calculating a dynamic background temperature difference drift rate; heat source change information is extracted through the thermal imaging image sequence, the change variance of a heat source in a time window is calculated, and the static heat source signal stability is obtained; performing normalization processing on the two features, and constructing a feature parameter set; inputting the set into a fuzzy logic reasoning model, and outputting PIR sensor signal credibility parameters according to a preset fuzzy rule; according to a credibility result, an alarm determination path is dynamically selected, and intelligent fusion and determination of a PIR signal and a video identification result are realized; according to the method, the PIR false triggering risk in the complex thermal environment can be effectively identified, the false alarm rate is reduced, and the reliability and adaptability of a perimeter security system are improved.

The invention discloses a unified operation and maintenance management and control method, and relates to the technical field of equipment management, and the method comprises the steps: collecting operation data, carrying out preprocessing standardization and denoising processing, and obtaining processed data; based on the processed data, constructing a digital twinborn model, and performing optimization by adopting a multi-dimensional optimization algorithm to obtain optimal parameters; monitoring and trend prediction are carried out by adopting a deep neural network through the optimal parameters, and fault prediction data are acquired; performing reinforcement learning by using a Q-learning algorithm according to the fault prediction data to obtain an optimal operation and maintenance strategy; and performing adaptive adjustment and evaluation based on the optimal operation and maintenance strategy to obtain a recovery strategy. According to the method, multi-dimensional recovery effect evaluation is realized through recovery effect evaluation combined with fuzzy logic reasoning and the game theory.

The invention belongs to the technical field of double-shaft excitation phase modifier control, and discloses a double-shaft excitation phase modifier virtual inertia self-adaptive control method, system and device based on rotor rotating speed and a medium. The excessive energy release at low rotating speed is easy to cause equipment off-network, and the supporting potential cannot be fully exerted at high rotating speed. The method comprises the following steps: acquiring real-time data of rotor speed and power grid frequency; calculating a rotating speed margin according to a preset rotating speed operation interval, taking a power grid frequency change rate as input of a fuzzy logic controller, and calculating a virtual inertia gain coefficient through fuzzy logic reasoning; multiplying the reference inertia by the gain coefficient to obtain a final virtual inertia coefficient; and generating a control instruction based on the coefficient, changing the electromagnetic torque, and realizing virtual inertia self-adaptive control.

A computer-implemented method of generating a thin volume mesh in a Computer-Aided technology (CAx) model of an object is described. In the method, a volume region lying between a first surface mesh having a first set of mesh parameters and a second surface mesh having a second set of mesh parameters is selected. This volume region has a thickness corresponding to the distance between the first and second surface mesh. prismatic cell volume mesh is generated to fill the entire volume region when the volume region is thin. Whether or not the volume region is thin is given by a crisp value calculated using a fuzzy logic inference scheme including the fuzzy sets thin and non-thin, and wherein the relationship between the first and second sets of mesh parameters and the thickness determine the membership of the fuzzy sets thin and non-thin.

The invention discloses a decision suggestion generation method and device for adding site services, and the method comprises the steps: obtaining quantitative data corresponding to a to-be-added service item for each to-be-added service item, including demand data, competitive data, target site capability data and cost income data, carrying out the fuzzy processing of the quantitative data, and obtaining a decision suggestion of the to-be-added service item; obtaining a fuzzy set group G1 corresponding to demand data, obtaining a fuzzy set group G2 corresponding to competitive data, obtaining a fuzzy set group G3 corresponding to target site capability data, obtaining a fuzzy set group G4 corresponding to cost income data, performing fuzzy logic reasoning on the fuzzy set groups G1, G2, G3 and G4 corresponding to the to-be-added service item, and obtaining a fuzzy set group G4 corresponding to the to-be-added service item; the decision suggestion corresponding to the to-be-added service item is generated according to the to-be-added service item, fuzzy logic reasoning can be carried out according to market dynamic requirements, competitive environments, operation capability and income, the complexity and uncertainty of the market environment are reduced, and accurate and scientific decision suggestions for adding site services can be provided.

The invention discloses a water conservancy project intelligent management method and system based on big data, and belongs to the technical field of water conservancy project intelligent management. Multi-source operation data such as the water flow rate, the capillary permeability, the freezing depth and the structural stress fluctuation are collected and reconstructed into time-space coupling data; through tensor decomposition, extracting an operation abnormity pilot factor, constructing a freeze-thaw model and deducing a structure accumulation risk factor; the risk factors are embedded into a graph structure, and future local degradation sensitive points are predicted in combination with a graph neural network; performing fuzzy logic reasoning on the sensitive points, and outputting reinforcement suggestions; constructing a region-level freezing environment vulnerability map among multiple projects, and generating a maintenance schedule and an inspection path; according to the method, prospective identification and refined maintenance of the freezing and thawing risk of the hydraulic structure are realized, and the engineering operation safety and the resource allocation efficiency are improved.

This invention discloses a big data-based intelligent management method and system for water conservancy projects, belonging to the field of intelligent management technology for water conservancy projects. It collects multi-source operational data such as water flow rate, capillary permeability, freezing depth, and structural stress fluctuations, reconstructing them into spatiotemporally coupled data. Through tensor decomposition, it extracts leading factors of operational anomalies, constructs a freeze-thaw model, and infers cumulative structural risk factors. These risk factors are embedded in a graph structure, and a graph neural network is used to predict future local degradation sensitive points. Fuzzy logic reasoning is applied to these sensitive points to output reinforcement suggestions. A regional-level freezing environment vulnerability map is constructed across multiple projects, generating maintenance schedules and inspection paths. This invention achieves proactive identification and refined maintenance of freeze-thaw risks in hydraulic structures, improving project operational safety and resource allocation efficiency.

The invention discloses a deep learning-based facial micro-expression pain recognition and analysis method. The method comprises the following steps of S1, constructing an original data set; s2, preprocessing the obtained original data set; s3, based on the first-layer generative adversarial network and the preprocessed original data set, generating facial micro-expression images under different pain levels through a first-layer generator; s4, based on the second-layer generative adversarial network, extracting pain level features from the micro-expression image generated by the first-layer generative adversarial network and the real micro-expression data; s5, processing the extracted micro-expression features and pain grade scores through a fuzzy logic module; s6, based on a fuzzy logic reasoning result, performing defuzzification processing on the pain level; and S7, according to the real-time analysis result, continuously monitoring the pain state of the patient, and adjusting the sensitivity of the system to the micro-expression under different environmental conditions. According to the method, the facial micro-expression capture precision and the pain level identification accuracy in a complex environment are improved.

The invention relates to the technical field of urban drainage control, in particular to an explanation method and device for a deep reinforcement learning control strategy of an urban drainage system, and the method comprises the steps: obtaining an input state vector and an output control action of a multi-agent controller under different operation conditions, constructing a state-control action data set of the urban drainage system; identifying at least one sensitive input feature of the multi-agent controller; and taking the sensitive input features as antecedent variables to construct an initial fuzzy logic inference system, optimizing target parameters of the initial fuzzy logic inference system until the target parameters meet preset conditions, and terminating iterative optimization so as to explain a deep reinforcement learning control strategy of the urban drainage system by using the optimized fuzzy logic inference system. Therefore, the problem that in the prior art, due to the lack of transparent interpretable decision logic, strategy uncertainty and response risks exist when extreme weather or sudden working conditions are dealt with is solved.

This invention discloses an adaptive control system for industrial robots that integrates a situation prediction mechanism. Specifically, it relates to the field of situation prediction based on feedforward networks and fuzzy logic. During the execution of the industrial robot, state input data is continuously sampled and input into a feedforward neural network capable of mapping time-series features to obtain a predicted output of the robot's task trend. By constructing a dynamic entropy deviation coordination mechanism between the feedforward neural network and the fuzzy logic inference model, modal attribution conflict identification and control coordination for critical states of multimodal tasks are achieved. This ensures the continuity of the task response path and the stable operation of the control system within the fuzzy transition range, thereby solving the problem of modal misalignment and execution loss of control caused by the lack of entropy coupling between feedforward prediction output and fuzzy inference judgment in the control decision domain.

A method and system for routing unmanned aerial vehicle (UAV) swarms, relating to the field of communication technology, includes the following steps: when a source node needs to send a data packet to a destination node and no valid path exists in its routing table, it generates and broadcasts a routing request message; upon receiving the routing request message, any intermediate node calculates its own node score based on its own parameters and its association with the previous hop node, and forwards the routing request message when its score exceeds a score threshold; when the destination node receives at least one routing request message, it obtains a candidate path for each message, comprehensively evaluates the candidate paths using fuzzy logic reasoning, and outputs the priority of each candidate path; the candidate path with the highest priority is selected as the optimal path, and a routing response message is unicast to the source node. This application achieves selective forwarding of routing request messages, effectively suppressing the flood of unnecessary messages, significantly mitigating broadcast storms, and reducing network energy consumption and congestion.