97 results about "Fuzzy model" patented technology

The invention discloses an intelligent automobile double-event trigger control method aiming at double communication networks. The method comprises the following steps: initializing; establishing intelligence to judge whether an SC event triggering condition and a CA event triggering condition are met or not; solving a front wheel steering angle control instruction; and performing intelligent automobile double-event trigger control. According to the invention, a double-event trigger condition is designed to determine whether a state signal of an intelligent automobile path tracking type 1 fuzzy model is updated to a type 1 fuzzy time-lag controller or not and determine whether a front wheel steering angle control instruction calculated by the type 1 fuzzy time-lag controller is updated to an actuator module or not; communication resources of double communication networks are effectively saved; the method has the capability of efficiently avoiding the problem of communication congestion, can save a lot of communication resources, and improves the reliability of the intelligent automobile in the path tracking control process. The fuzzy time-delay controller is designed to calculate a front wheel steering angle control instruction, and the reliability of path tracking control of the intelligent automobile is ensured.

The invention provides a preset time fuzzy control method for a reentrant manufacturing system under intermittent state feedback, and the method comprises the steps: constructing a nonlinear error dynamic model, and employing a fuzzy modeling technology to represent the system as a combination of a plurality of linear subsystems; introducing a time scaling function, and transforming the error state of the global fuzzy model by using the time scaling function to obtain an error scaling state; an event triggering mechanism is designed to realize intermittent state feedback so as to reduce the communication cost; based on the Lyapunov stability theory, a sufficient condition that the system is stable within preset time is deduced, and a controller gain is obtained by solving a linear matrix inequality of the sufficient condition, so that the system still has robustness under external interference. Agile response and low-communication-cost operation of the reentrant manufacturing system within the preset deadline are realized.

The invention discloses an end face tool sharpener control system, and relates to the technical field of numerical control systems. The end face tool sharpener control system comprises a data preparation and recording module, a tool type parameter dynamic modeling module, a multi-axis linkage control module, a grinding wheel pressure self-adaption control module, a grinding wheel abrasion compensation module and a technological parameter optimization module. By comprehensively collecting multi-dimensional historical processing data and constructing a set framework, automatic classified storage of parameters is realized; the NURBS curve interpolation algorithm is adopted, and the machining precision and smoothness of the complex shape are guaranteed; instructions are synchronized in real time, errors are compensated, vibration is monitored in combination with an acoustic emission sensor, and machining stability is improved; a fuzzy PID model and machine learning are utilized to dynamically adjust parameters and optimize the parameters in advance; through machine vision and digital twinning, abrasion is accurately recognized, and the finishing period is predicted. And based on the hybrid model and reinforcement learning, predicting a processing result, dynamically adjusting parameters, and performing error compensation and sensitivity analysis.

The invention relates to the technical field of hydroelectric engineering, in particular to a T-S fuzzy robust control method for a hydroelectric generating set adjusting system based on a linear matrix inequality, which comprises the following steps: establishing a system nonlinear mathematical model considering modeling uncertainty and external interference under a rigid water attack condition, and converting the system nonlinear mathematical model into an affine nonlinear state space form; a T-S fuzzy model is constructed, and precise approximation of global nonlinear characteristics is realized through linearization of a linear triangular membership function and representative working condition points; a fuzzy controller is designed based on a parallel distribution compensation strategy, and a robust control problem is converted into a linear matrix inequality form to solve a feedback gain matrix in combination with a Lyapunov stability theory and an H-infinity performance index. The method effectively improves the adaptability of the system to a complex operation environment, enhances the anti-disturbance capability, can significantly reduce the system oscillation, shortens the stabilization time, guarantees the safe and reliable operation of the hydroelectric generating set, and has important engineering application value.

The invention discloses a dynamic scene deblurring method and system based on physical information adversarial learning, and the method comprises the steps: obtaining original blurred image data, carrying out the preprocessing of the original blurred image data, and obtaining a preliminary deblurred image; inputting the preliminary deblurred image into an initial dynamic scene deblurring model for training to obtain a dynamic scene deblurring model; the initial dynamic scene deblurring model comprises a generator network, an optical flow estimation network, a three-stage progressive training strategy and a multi-scale discriminator network, the generator network is used for mapping an initial deblurred image into a deblurred image, and the optical flow estimation network is used for estimating a motion field and calculating optical flow consistency loss; the three-stage progressive training strategy is used for carrying out three-stage training on the initial dynamic scene fuzzy model in sequence, and the multi-scale discriminator network is used for judging image authenticity on different scales; and inputting a to-be-processed blurred image into the dynamic scene deblurring model to obtain a blurred image. According to the invention, the deblurring effect is improved.

The invention provides a coupling fuzzy control, ORC (Organic Rankine Cycle) and Carnot cell waste heat utilization method and system, which combines a fuzzy T-S model, an ORC and Carnot cell coupling system, and excites an ORC waste heat generator set by using a pseudo-random signal modulated based on a fuzzy model. The implementation process of flue gas waste heat utilization and Carnot cell compensation is monitored, regulated and controlled in real time, the adaptability limitation of a traditional static model on the time-varying characteristic of waste heat parameters is broken through, and coordinated control over multi-level gradient utilization of industrial waste heat and stored energy release is achieved. And the flexibility, the energy efficiency level and the new energy friendly access capability of the energy system are improved. According to the method, a multi-energy-flow collaborative optimization mechanism is constructed based on the fuzzy T-S dynamic clustering algorithm, the flue gas waste heat recovery rate is increased, the waste heat resource gradient utilization efficiency and the energy system operation flexibility are remarkably improved, and an efficient solution is provided for low-temperature waste heat deep recovery in the iron and steel industry.

The invention relates to the technical field of unmanned ship safety control, and discloses an anti-spoofing-attack self-adaptive sliding mode control method and system for an unmanned ship and a medium, and the method comprises the steps: S1, constructing an unmanned ship T-S fuzzy model under the spoofing attack and external disturbance; s2, designing a dual-adaptive sliding mode observer based on the unmanned ship T-S fuzzy model constructed in S1; s3, designing a sliding mode controller based on S1 and S2; and S4, forming a closed-loop control system based on S1-S3 to perform sliding mode control: integrating the unmanned ship T-S fuzzy model constructed in S1, the dual-adaptive sliding mode observer designed in S2 and the sliding mode controller designed in S3 to form the closed-loop control system, and realizing sliding mode control. According to the method, the dynamic suppression capability of the composite threat can be remarkably improved, precise compensation of a spoofing attack signal and external disturbance of the ocean is realized, high-precision zero-flutter control is realized under the coexistence of the spoofing attack and the external disturbance, and an autonomous control solution with safety, robustness and real-time performance is provided for the unmanned ship.

The invention discloses a cross arm and insulator installation robot motor control method based on a T-S fuzzy model, and the method comprises the following steps: building a permanent magnet synchronous motor nonlinear model according to electromagnetism and motor dynamics; based on a sector nonlinear method, establishing a permanent magnet synchronous motor T-S fuzzy model; designing an observer to obtain a load torque estimated value; designing an L-infinity robust controller to ensure that the angular velocity of the motor can track a reference instruction; and an anti-control gain matrix solving criterion is formulated, and it is ensured that the system meets performance indexes. According to the method, the nonlinear control problem of the permanent magnet synchronous motor system is effectively solved, the influence of continuous interference signals on the system can be effectively suppressed, and the robustness of the system is enhanced.

The invention discloses an unmanned aerial vehicle guaranteed performance trajectory control method, and relates to the field of unmanned aerial vehicle tracking control, and the method comprises the following operation steps: S1, carrying out the longitudinal dynamics modeling of a fixed-wing unmanned aerial vehicle; s2, constructing a T-S fuzzy model; s3, a Fuzzy-GCC controller is designed; s4, the LMI of guaranteed performance control is solved; and S5, intelligently optimizing the parameters. According to the unmanned aerial vehicle guaranteed performance trajectory control method, the control models of the fixed-wing unmanned aerial vehicle can be integrated to obtain a unified form, so that the control law design and parameter tuning of the fixed-wing unmanned aerial vehicle are greatly simplified, a complex propulsion system and a longitudinal controller are decoupled through a lookup table, and the control efficiency of the fixed-wing unmanned aerial vehicle is improved. According to the method, the complexity and nonlinearity of the whole model are remarkably reduced while the control precision is kept, a T-S fuzzy model for longitudinal control of the fixed-wing unmanned aerial vehicle is deduced, and a GCC method and a stability criterion thereof are proposed based on the model, so that the global asymptotic stability of the designed nonlinear state feedback controller is ensured.

The present application relates to a kind of facing polynomial fuzzy control system cost control stability judging method, comprising the following steps: establishing polynomial fuzzy model;According to the first SOS condition based on Lyapunov function, try to solve the first polynomial matrix and the second polynomial matrix, omit non-convex term in solving process, judge whether it is successful, if yes, based on the first polynomial matrix and the second polynomial matrix, obtain feedback gain;Based on feedback gain, according to the second SOS condition, try to solve positive definite matrix, judge whether it is successful, if yes, based on positive definite matrix, construct polynomial Lyapunov function, realize cost control analysis based on polynomial Lyapunov function.Compared with prior art, the present application solves the non-convex optimization problem in cost control in two steps, avoids the influence of the constraint existing in input matrix itself on the flexibility of fuzzy control system design, and improves the performance of control system by obtaining the numerical value of cost J.

The invention discloses a method for constructing an image classification model based on semi-supervised learning, and belongs to the technical field of image classification. According to the method, the risk coefficient of an unmarked image sample is judged, fine-grained evaluation can be carried out on an unmarked image, and the image classification accuracy is improved. A relatively high risk coefficient is set for the image of which the feature information is difficult to distinguish compared with the fuzzy model, so that the influence of the image in the model training process is reduced; and the performance robustness of the image classification model is ensured based on the integrated learning method and the baseline model. Specifically, due to the fact that uncertainty exists in the model training process of unmarked images, a plurality of semi-supervised learning subsets are constructed from an original data set through the sampling technology, a plurality of image classification models are trained based on the subsets to serve as base learners, and therefore a base learner pool is created; the final image classification model is generated from the base learner pool based on ensemble learning, and it can be guaranteed that the model performance is not weaker than that of a baseline model trained from marked image samples.

The invention discloses a nuclear power plant reactor coolant system fault diagnosis method and a related device, and relates to the field of fault diagnosis, and the method comprises the steps: obtaining sensor data of target equipment, inputting the sensor data to a fuzzy CNN model, and obtaining a plurality of pooling feature intervals based on an interval type-2 fuzzy set; the fuzzy CNN model is determined according to the CNN model and an interval type-2 fuzzy set method; inputting all pooling feature intervals based on the interval type-2 fuzzy set into a fuzzy GRU model to obtain a plurality of hidden state intervals based on the interval type-2 fuzzy set; the fuzzy GRU model is determined according to the GRU model and an interval type-2 fuzzy set method; inputting the hidden state intervals of all the interval type-2 fuzzy sets into a fuzzy softmax model to obtain a fault diagnosis result of the target equipment; the fuzzy softmax model is determined according to the softmax model and an interval type-2 fuzzy set method. According to the invention, the fault identification precision can be improved in a complex working environment.

The invention discloses a motor modeling and non-cascade servo control method and system based on T-S fuzzy. The method comprises the following steps: establishing a mathematical model on a two-phase synchronous rotation orthogonal coordinate system to obtain state space description; obtaining a T-S fuzzy model and a closed-loop system according to the state space description; and for the closed-loop system, determining the gain of the non-cascade servo controller based on the Lyapunov stability theory. According to the invention, the control performance and the anti-interference capability of the driving system are effectively improved, and parameter adjustment and physical realization are easy.

This invention belongs to the field of unmanned driving technology and discloses a trajectory tracking control method, device, equipment, and storage medium for unmanned mining trucks. The method includes: establishing a trajectory tracking error model for the unmanned mining truck; discretizing the model; counteracting actuator delay by setting a heading angle pre-aiming distance; determining the heading angle error after pre-aiming to construct the target state variable; determining the gain coefficient using a TS fuzzy model; determining the Q-weight matrix and R-weight matrix after gain based on lateral error and road curvature to achieve real-time transformation matrices; determining the optimal feedback control sequence based on the Q-weight matrix, R-weight matrix, and the discretized state space model; determining the target control quantity based on the optimal feedback control sequence and the target state variable; and controlling the unmanned mining truck based on the target control quantity. Through this method, the unmanned mining truck can provide control quantities in advance during trajectory tracking, improving the accuracy of trajectory tracking control for unmanned mining trucks.

The application discloses an unmanned ship power positioning integral sliding mode fault-tolerant control method based on a fuzzy system, and comprises the following steps: a mathematical model of unmanned ship movement under an actuator fault is established; a T-S fuzzy model of the unmanned ship corresponding to the mathematical model is established; based on the established T-S fuzzy model of the unmanned ship, an integral sliding mode surface with fault information is constructed; and the asymptotic stability of the sliding mode dynamics of the system is proved by combining the definition of performance index and related lemmas.Aiming at the nonlinear term in the T-S fuzzy model of the unmanned ship, a fuzzy logic method is used to approximate the unknown smooth nonlinear term; based on the constructed integral sliding mode surface with fault information, a suitable Lyapunov function is selected, a fault-tolerant controller and an adaptive law are designed, and the reachability of the system is proved.The application can solve the problem that the resolution and complexity of the T-S model of the unmanned ship are difficult to balance, and can also ensure that the system has robustness from the initial stage.

The invention discloses a digital intelligent simulation method for a hydroelectric generating set speed regulating system based on hydroelectric-mechanical coupling, and aims to solve the problems of low hydroelectric-mechanical coupling degree, poor controllability of a simulation tool and insufficient consideration of a water hammer effect in traditional simulation. The method comprises the following steps: establishing a hydraulic electromechanical coupling model containing hydraulic power (simulating hydraulic transient by a characteristic line method), machinery (a T-S fuzzy model self-defined speed regulator) and electricity (PSS / E tidal current + generator equation); constructing a load flow calculation interface layer for secondary development of a PSS / E Fortran API, and integrating intelligent algorithm modules of GSA, DEPSO and BP neural networks; carrying out real-time interactive simulation and optimizing PID parameters of the speed regulator; and verifying dynamic characteristics of the model based on a water hammer effect analytic solution. The method realizes hydroelectric-mechanical-electrical deep coupling, improves simulation controllability and precision, adapts to unit debugging and power grid dispatching verification, and ensures safe and stable operation of the hydroelectric generating set and the power grid.

The application discloses a kind of based on profile model's shovel loader steering control method, device and shovel loader, belong to shovel loader control field.The present application obtains the profile information and walking information of shovel loader;According to profile information and walking information determine position deviation and direction deviation;If the position deviation is greater than the first preset threshold value simultaneously the direction deviation is greater than the second preset threshold value, according to walking information whether the vehicle body movement direction is deviated from path direction;If yes, with preset increase strategy adjustment directional control valve opening;If no, with preset decrease strategy adjustment directional control valve opening;If position deviation is greater than the first preset threshold value simultaneously direction deviation is less than or equal to the second preset threshold value or position deviation is less than or equal to the first preset threshold value simultaneously direction deviation is greater than the second preset threshold value, with preset decrease strategy adjustment directional control valve opening.Using shovel loader profile model, set fuzzy model, under the premise of guaranteeing equipment safety, reach the purpose of safe driving.

The invention discloses a helicopter demand power model calculation method and system, and belongs to the technical field of helicopter control, and the method comprises the steps: constructing a T-S fuzzy model, and dividing flight modes on a flight envelope based on the constructed T-S fuzzy model, so as to obtain a flight mode set; obtaining time sequence data in the flight process of the helicopter, and determining a current flight mode in the flight mode set based on the obtained time sequence data; and calculating the required power of the helicopter based on the determined current flight mode. A flight mode set is divided on a flight envelope through the constructed T-S fuzzy model, the required power of an engine can be well estimated by recognizing flight modes and calculating the required power in the flight process, power matching with the engine is achieved, and a basis is provided for subsequent high-speed helicopter control.

The invention discloses a proportional-integral state estimation method of a nonlinear wind turbine system based on dynamic summation type event triggering. The method comprises the steps of 1, describing nonlinear dynamic characteristics of a wind turbine system based on a T-S fuzzy model method, and establishing a state space model of the wind turbine system; 2, in order to save network resources, an event triggering mechanism based on dynamic summation is established, and redundant triggering is reduced; 3, designing a proportional-integral estimator to estimate the system state due to all the system states which are difficult to measure in actual engineering; and 4, in combination with the T-S fuzzy wind turbine system and the proportional-integral estimator, establishing a closed-loop estimation error system, and performing state estimation on the wind turbine system by designing a state estimator gain matrix. Compared with a traditional event triggering mechanism based on current information, the event triggering mechanism based on historical sampling data is provided, internal variables are introduced into triggering conditions, the triggering interval is further expanded, and more network resources are saved; compared with an event triggering mechanism which only adopts a static threshold, a dynamic triggering threshold is designed, the threshold can be adaptively adjusted along with the evolution of the system, and the flexibility of the triggering mechanism is improved. In addition, compared with a traditional proportional estimator, the method introduces an integral term of a state observation error to improve the precision of system state estimation, and has a certain engineering application value.

The invention provides a turbulence degradation image synthesis method based on continuous exposure time. Turbulence degradation is decomposed into two types of mutually independent physical processes of distortion and blurring. Aiming at the exposure dependence of turbulence blur, an exposure time modulation transfer function is used, and a pure blur point spread function is constructed through inverse Fourier transform, so that continuous transition of blur degradation in an interval from short exposure to long exposure is realized. Meanwhile, the fuzzy width distribution conforming to the statistical law is generated through the spatial random field, so that the generated fuzzy has the characteristic of spatial non-uniformity and is closer to the real turbulence imaging process. The fuzzy model is combined with an independently constructed geometric distortion field, so that turbulence images or videos which show physical consistency and diversity under different exposure conditions can be generated. According to the invention, the turbulence degradation difference caused by exposure time change in a real scene can be effectively simulated, and a reliable high-fidelity data source is provided for a turbulence removal algorithm, imaging system evaluation and data set construction.

The application provides a control method and device for a power converter of an energy storage system, a coupling relationship between active power and reactive power is analyzed through a power outer loop control model based on a virtual synchronous machine and a power coupling coefficient matrix, PI parameters of a reactive voltage compensation channel are adjusted based on the coupling relationship and a fundamental component extracted, a voltage reference value output by a PI controller after correction is obtained, a current value in a prediction time domain is predicted through a model-free predictive control method based on a bias format dynamic linearization in a current inner loop, and the voltage reference value and the current value are optimized in combination with an intuitionistic fuzzy model and a rough decision model, so that a target voltage reference value and a target current value generated after optimization are used for regulation and control. Therefore, through fusion of power decoupling, model-free predictive control, fundamental component extraction, and the intuitionistic fuzzy model and the rough decision model, adaptability, robustness and power quality of the power converter in a complex power grid environment are improved.

This invention discloses a method for optimizing the synergistic application mechanism of potassium sulfate and magnesium, relating to the field of intelligent agricultural fertilization control. By collecting growth characteristic parameters such as the fruit weight gain rate and root distribution depth of mandarin oranges in real time, the method combines a T-S fuzzy model to calculate and dynamically adjust the fertilizer application rate, ensuring that the fertilizer application rate accurately matches the growth needs of the crop, avoiding over-fertilization or under-fertilization.

The invention discloses a method for evaluating fish habitat and ecological flow regulation and control based on a data-driven fuzzy model, belongs to the field of water conservancy and hydropower engineering environmental protection and ecological hydraulics, and particularly relates to a method for evaluating fish habitat and ecological flow regulation and control. According to the method, a hydraulic parameter membership function is automatically deduced from on-site fish behavior observation data through a fuzzy C-means clustering (FCM) algorithm, a fuzzy rule base is constructed, a habitat suitability index (HSI) model under the synergistic effect of multiple factors such as water depth and flow velocity is established, and an environment flow threshold value based on weighted available area (WUA) maximization is output. According to the method, the defects that a traditional habitat model excessively depends on expert experience and multi-factor interaction processing is insufficient are overcome, objective quantification of model parameters and accurate capture of a complex nonlinear relation are achieved, quantifiable and species-specific decision support is provided for cascade reservoir ecological scheduling, and the method has the advantages of being high in practicability and easy to popularize. And hydroelectric benefits and ecological protection requirements are effectively balanced.

The invention relates to the technical field of power battery performance analysis, discloses a power battery attenuation influence factor quantitative identification method based on ensemble learning, and aims to solve the problems of weak data relevance, fuzzy feature importance and poor model adaptability in a traditional method. Comprising the steps of collecting and constructing a multi-source data set; capturing degradation characteristics of different time scales, and screening key influence factors of the whole life cycle in combination with a Top-K space attention mechanism; performing weighted fusion on static attributes and dynamic time sequence characteristics through a gating fusion module to enhance data relevance; a Stacking ensemble learning model is constructed, a decision tree is taken as a base model, linear regression is taken as a meta-model, sliding window preheating training and Bayesian optimization are combined to realize hyper-parameter tuning and weight updating, and model adaptability is improved; and respectively quantifying global and local feature importance through a feature splitting gain sum and an SHAP value, generating an optimization maintenance report containing an interactive thermodynamic diagram and a three-dimensional network diagram, and realizing accurate identification and control of attenuation influence factors.

The invention belongs to the technical field of computer vision and artificial intelligence, and particularly relates to a video abnormal display fragment detection method and system based on a multi-modal model, which can solve the problems that the existing video abnormal detection efficiency is low, the abnormal positioning is fuzzy, the model and manual work division is not clear, and the multi-model adaptability is poor. The method comprises the following steps: preprocessing acquired video display content of equipment to be tested; based on a preset exception type knowledge base and a model capability label system, executing exception identifiability judgment through two-stage semantic matching, judging whether the exception in the current detection task belongs to an identifiable range of a pre-trained multi-modal model or not, and determining a detection type corresponding to the exception; performing fragment segmentation with timestamps on the preprocessed video, and extracting multi-modal features of fragments; and executing corresponding detection operation according to the detection type.

The application is directed to the problem of fault-tolerant formation control of fuzzy multi-leader UAV system. A fault-tolerant formation control method based on reduced-order observer is proposed, including: using T-S fuzzy model to model the multi-leader UAV system; transforming the original system into a reduced-order form, and then deriving an augmented form; designing a reduced-order fault observer based on the intermediate variable for the reduced-order augmented system to estimate the state of the follower UAV, process fault and system uncertainty; using the relative state information to design a tracking fault-tolerant formation controller, taking the estimation of process fault and system uncertainty as compensation term; designing adaptive parameters for the reduced-order fault observer and the tracking fault-tolerant formation controller; verifying the performance of the reduced-order fault observer and the tracking fault-tolerant formation controller; the application can more prominently deal with the nonlinear and uncertain control problem, while reducing the calculation amount and improving the efficiency of distributed decision-making.

The invention discloses a payment aggregation channel management method based on an adaptive strategy. The payment aggregation channel management method comprises the steps of 1, collecting structured feature information of a payment transaction request and running state information of a payment channel; 2, performing normalization and embedded coding on the structured feature information; 3, constructing a payment channel structure chart; step 4, a structure embedding vector is generated through the improved GraphSAGE network; 5, constructing an improved Sugeno fuzzy model, and generating a scheduling priority score value and a scheduling intention label; 6, generating a payment transaction request scheduling strategy; 7, collecting transaction feedback information, and generating a channel performance index set, a comprehensive evaluation value and a channel evaluation grade; and step 8, updating the improved GraphSAGE network and the Sugeno fuzzy model, and optimizing a payment transaction request scheduling strategy. According to the invention, the intelligence, stability and adaptive decision-making capability of payment channel scheduling are improved.

The application discloses an interval type-2 fuzzy sliding mode control method based on a parameter uncertain inverted pendulum system and belongs to the technical field of nonlinear system control, and comprises the following steps: establishing an interval type-2 T-S fuzzy model of the parameter uncertain inverted pendulum system; constructing a sliding mode controller of the parameter uncertain inverted pendulum system based on the interval type-2 T-S fuzzy model; the sliding mode controller comprises a sliding surface, an equivalent controller, a switching controller and a comprehensive controller; the sliding surface is used as the only input variable of the fuzzy controller, the switching gain is dynamically controlled by using a fuzzy logic rule, and the sliding mode controller is optimized into an interval type-2 fuzzy sliding mode controller. The application solves the problem that the prior art cannot ensure that the parameter uncertain inverted pendulum system is stably operated on a sliding surface and is prone to chattering when parameters change and external disturbances occur.

This invention proposes a dynamic scene deblurring method and system based on 4D Gaussian representation and pseudo-ground value supervision. The method includes: obtaining a sharp image and a rendered depth map from a 4D Gaussian representation; predicting the motion velocity of dynamic pixels using a velocity MLP network based on the rendered depth map; constructing a fuzzy weight network and predicting the contribution weight of each sampling point on the sampling trajectory; fusing the pseudo-sharp image with the original blurred input using a dynamic region mask to obtain a hybrid pseudo-ground value image; synthesizing a physically blurred image through weighted integration; and constructing a dual-domain reconstruction loss and geometry-motion regularization constraints by combining hybrid pseudo-ground value supervision and gradient decoupling strategies to jointly optimize the scene representation, motion parameters, and fuzzy model, thereby obtaining a sharp dynamic scene representation. This invention achieves explicit modeling of the physical blurring process through 4D Gaussian representation and a fuzzy weight network, improving the realism and view consistency of motion blur synthesis.

This invention discloses an energy management method for hybrid energy storage systems based on fuzzy model predictive control. It constructs a linear variable parameter model predictive control architecture incorporating fuzzy decision-making for closed-loop optimization control. First, an LPV prediction model for the system is established, and the load power sequence is introduced as a measurable feedforward disturbance into the state equation. During the rolling optimization preparation stage, a fuzzy inference mechanism is used to analyze multi-dimensional operating conditions such as system power fluctuations, SOC, and SOV in real time, dynamically adjusting the weighting factors of energy tracking, battery loss, and current smoothing in the cost function to achieve an adaptive trade-off in the control strategy. Simultaneously, a hierarchical setpoint tracking strategy is adopted, intelligently switching the voltage state reference target based on the real-time energy level of the supercapacitor. Finally, based on the time-varying model, dynamic weights, and the reference target, a quadratic programming problem is solved, outputting the optimal control quantity applied to the power converter, thereby significantly improving the system's adaptive coordination capability and overall operating efficiency under complex and variable operating conditions.