Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

325 results about "Model free" patented technology

FSW joint mechanical property model-free adaptive control method

The invention belongs to the field of welding quality control of friction stir welding, and relates to a model-free self-adaptive control method for mechanical properties of an FSW joint. The FSW process is described as a disturbance-containing multiple-input-multiple-output discrete time nonlinear system, and the disturbance-containing multiple-input-multiple-output discrete time nonlinear system is converted into a tight-format dynamic linearization data model; a model-free adaptive controller is constructed according to a control input criterion function, and online estimation of control law parameters is realized in combination with a pseudo Jacobian matrix estimator; estimating the disturbance of the FSW system by using the FNNDO, and carrying out feed-forward compensation on the disturbance; and the joint mechanical property obtained through prediction serves as input of an FNNDO-MFAC controller, welding process parameters are dynamically adjusted through real-time feedback, and therefore precise control over the mechanical property of the FSW joint is achieved. The method does not need to depend on model parameters in the FSW process, through disturbance estimation and compensation of the FNNDO, the disturbance processing capacity of the MFAC is remarkably improved, and the self-adaptability of the system is effectively enhanced.
Owner:DALIAN UNIV OF TECH

Data-driven floating type wind turbine generator model-free control method and system

The invention discloses a data-driven floating type wind turbine generator model-free control method and system, and the method comprises the steps: obtaining the operation state and external environment parameters of a wind turbine generator, and constructing sample data; inputting the sample data into a pre-trained controller, and outputting a control instruction to control the wind turbine generator; the specific process of obtaining the controller comprises the steps that the simulation operation state / historical operation state and external environment parameters of the wind turbine generator are obtained, and an initial controller is constructed based on the simulation operation state / historical operation state and the external environment parameters; determining a control target, a wind turbine generator operating environment, an intelligent agent, a state space, an action space, a constraint condition and a reward function in the initial controller; and performing continuous interactive learning training on the intelligent agent and the operation environment of the wind turbine generator through a deep reinforcement learning algorithm to obtain a trained controller. The method has the advantages of reducing the modeling difficulty, dynamically correcting the control strategy, improving the power generation efficiency and the like.
Owner:CRRC ZHUZHOU ELECTRIC LOCOMOTIVE RESEARCH INSTITUTE CO LTD

Networked multi-robot data-driven formation control method under preview mechanism

Disclosed in the present invention is a networked multi-robot data-driven formation control method under a preview mechanism. A leader-follower formation method is used, wherein a preview point is determined on a reference trajectory, and by means of a cross-track error between a current position and the preview point, a model-free adaptive control (MFAC) algorithm is used to control an angular velocity; each follower uses the coordinates of a leader as the preview point, and the angular velocity and a linear velocity are respectively controlled by means of the cross-track error and an along-track error between the current position and the preview point; and in the algorithm, the angular velocity is controlled by single-closed-loop MFAC, the linear velocity is controlled by dual-closed-loop MFAC, an error term is controlled by weighted collaborative errors of each robot, forward prediction is used to compensate for network communication constraints in control algorithms, and a velocity control quantity after predictive compensation is transmitted to an end-device robot by means of an edge-end network, thereby realizing stable specific-pattern coordinated formation of multiple mobile robots. The method has stronger scenario applicability, flexibility and scalability.
Owner:HUNAN UNIV +1

Model-free incremental reinforcement learning-based hovering stability control method for unmanned aerial vehicle with arms

ActiveCN119045317AIn line with the thinking of exploring and solving problemsImprove training efficiencyControllers with particular characteristicsStabilization controlNetwork output
The invention provides an armed unmanned aerial vehicle hovering stability control method based on model-free incremental reinforcement learning, and the method comprises the steps: building an unmanned aerial vehicle and on-load mechanical arm model, building a deep reinforcement learning algorithm framework, initializing a neural network strategy, designing a layered reward function, and collecting the state information of the unmanned aerial vehicle and the on-load mechanical arm. The strategy neural network outputs a stability augmentation control instruction according to the collected state information, the stability augmentation control instruction and a control instruction output by the PID controller are subjected to weight superposition with parameters, a fusion control law is obtained, then the fusion control law is input into the unmanned aerial vehicle and on-load mechanical arm model, next state information is solved, the next state information is used for calculating a reward value of the state, and the reward value is obtained. And corresponding actions are fed back to the deep reinforcement learning algorithm framework, a distributed near-end optimization strategy is operated to output a strategy gradient, the gradient descent of the strategy is calculated, the neural network is updated by using the gradient descent, and strategy updating is completed. The method can give guidance information in real time, and improves the training efficiency.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Model-free self-adaptive independent variable pitch control method and system for wind turbine generator based on multivariable decoupling

The invention discloses a model-free self-adaptive independent variable pitch control method and system for a wind turbine generator based on multivariable decoupling, and aims to solve the problem of blade fatigue damage caused by blade root asymmetric load under a high-wind-speed turbulence working condition. A multi-input multi-output control architecture is designed, control parameters are dynamically adjusted by using a model-free adaptive control (MFAC) algorithm, a cooperative adjustment instruction of an independent variable pitch angle is generated, optimal control of a three-blade pitch angle is realized, and power output stability is maintained while a blade root load is suppressed. Compared with traditional independent pitch control (IPC), the method has the advantages that model dependence is eliminated through pseudo-gradient matrix multivariable decoupling, the anti-interference capacity under the turbulent wind condition is remarkably enhanced, and technical guarantee is provided for safe operation of a large wind turbine generator.
Owner:XINJIANG UNIVERSITY

Novel model-free superhelix sliding mode control method based on sliding mode disturbance observer

The invention discloses a novel model-free super-spiral sliding mode control method based on a sliding mode disturbance observer, and the method comprises the steps: designing a novel model-free super-spiral sliding mode controller of a rotating speed ring based on the combination of a novel super-local model and a second-order super-spiral law; meanwhile, a sliding mode disturbance observer is designed to estimate uncertain and unknown disturbance parts of system parameters in real time and feed back to a novel model-free super-spiral sliding mode controller of a rotating speed ring, so that the rotating speed of the motor is controlled; the controller introduces a linear system state item and a nonlinear disturbance item according to the novel super-local model, establishes a novel super-local model of the system, combines the novel super-local model of the system with a rotating speed ring state equation of the motor, establishes a novel super-local model of a rotating speed ring, and performs the super-local model of the rotating speed ring; and establishing a novel model-free super-spiral sliding mode control law of the rotating speed ring based on the novel super-local model of the rotating speed ring and an observation result of the sliding mode disturbance observer. The influence of external disturbance on the motor is effectively solved, buffeting is weakened, and effective tracking of the given rotating speed can be achieved.
Owner:SUZHOU UNIV OF SCI & TECH

Intelligent reservoir scheduling system and method based on model-free adaptive control

The invention discloses an intelligent reservoir scheduling system and method based on model-free adaptive control, belongs to the technical field of water conservancy scheduling, and can solve the problems that time and labor are consumed when a precise model is established in a traditional scheduling system, the risk of model failure exists, and quick response cannot be achieved in the face of sudden hydrological changes. The system comprises a data acquisition module used for acquiring real-time hydrological data of a reservoir; the data storage module is used for storing historical hydrological data of the reservoir; the scheduling strategy determination module is connected with the data acquisition module and the data storage module, and is used for determining a scheduling strategy of the reservoir by using a model-free adaptive control algorithm according to the real-time hydrological data and the historical hydrological data; and the scheduling execution module is connected with the scheduling strategy determination module and is used for scheduling the reservoir according to the scheduling strategy of the reservoir. The method is used for intelligent scheduling of the reservoir.
Owner:SHAANXI WATER CONSERVANCY & ELECTRIC POWER SURVEY & DESIGN INSTITUTE (GROUP) CO LTD

Method for generating workpiece model based on point cloud data

The invention discloses a method for generating a workpiece model based on point cloud data, and aims to automatically generate a high-precision workpiece model through reverse modeling. The method comprises the following steps: dynamically adjusting a data acquisition amount through a line structure light sensor, and obtaining workpiece surface point cloud data; preprocessing the point cloud, including three-dimensional effective area cutting, uniform downsampling and radius filtering to remove interference data and reduce data volume; carrying out clustering segmentation on the preprocessed data by utilizing a point cloud region growing method, separating a bottom surface part from a non-bottom surface part, extracting contour points of each plane region, calculating normal lines, generating vertexes by fitting contour edges and solving intersection points, and forcibly closing unclosed contours to construct complete geometric features; and finally, generating a workpiece model by combining the point, line and surface information packaged by the open source library. According to the method, the low-error and high-precision model can be directly generated for the model-free non-standard workpiece, limitation of manual modeling or model presetting is avoided, and programming time consumption is remarkably reduced.
Owner:WUXI LICHENG INTELLIGENT EQUIP CO LTD

Model-free micro-grid control method and system based on transfer learning and medium

The invention relates to a model-free micro-grid control method and system based on transfer learning and a medium, and the method comprises the following steps: dividing a DC micro-grid into a plurality of converters, and constructing a converter simulation model; realizing a deep reinforcement learning DDQN algorithm in combination with the converter simulation model, constructing a reward function, an action space and a state space, and performing normalization processing on the state space; parameters of the deep reinforcement learning DDQN algorithm are adjusted; training the converter by using the deep reinforcement learning DDQN algorithm and a reward function, and reconstructing a mapping function; and inputting an action space in the mapping function, outputting a duty ratio to PWM (Pulse Width Modulation), and adjusting the output voltage and the output power of the converter by dynamically adjusting the duty ratio, thereby realizing model-free control on the direct-current micro-grid. Compared with the prior art, the transient performance, the steady-state performance and the generalization performance of the controller are improved.
Owner:SHANGHAI UNIVERSITY OF ELECTRIC POWER

Reinforcement learning control method and system based on physical space feedback

The invention relates to the technical field of artificial intelligence and robot control, in particular to a reinforcement learning control method and system based on physical space feedback, and the method comprises the steps: training an initial strategy through domain randomization in a simulation environment; fusing multi-modal sensor data in a real environment, and constructing an environment state; deploying the strategy network after the strategy network parameters are optimized into a real environment, combining a model base and model-free reinforcement learning, utilizing simulation data and real data to jointly optimize the strategy network, and compensating a dynamical model error through online fine adjustment; and correcting the action instruction in real time based on the security constraint. The system comprises a sensor module, a strategy network module, a security constraint module and a simulation-real migration module. According to the method, the dynamical model error is compensated through online fine adjustment; through a mixed model base and a model-free reinforcement learning architecture, and in combination with multi-modal sensor data and a security constraint mechanism, high-sample-efficiency and high-security physical system control is realized.
Owner:CHANGZHOU UNIV

Model-free weld joint identification method and device

PendingCN119107306AWeld seam recognition implementationImage analysisManufacturing computing systemsPoint cloudWeld seam
The embodiment of the invention provides a model-free weld joint identification method and device, and relates to the technical field of computers. The method comprises the following steps: acquiring a workpiece point cloud of a to-be-identified workpiece; a stored first conversion relation between a first coordinate system where calibration point clouds are located and a second coordinate system where workpiece point clouds are located is obtained through registration calculation, the calibration point clouds are obtained by splicing a plurality of point clouds obtained by conducting point cloud collection on a calibration workpiece, and the calibration workpiece is a workpiece of the same type as the to-be-recognized workpiece; according to the first conversion relation, first welding seam labeling information corresponding to the stored calibration point cloud is converted to a target coordinate system used by the workpiece point cloud, second welding seam labeling information is obtained, and the first welding seam labeling information is used for indicating the position of a welding seam on the calibration workpiece in the first coordinate system; and performing welding seam identification on the workpiece point cloud according to the second welding seam marking information. In this way, weld joint recognition can be achieved without a workpiece model.
Owner:FAIR INNOVATION (SUZHOU) ROBOTIC SYSTEM CO LTD

Online intelligent regulation and control method and system for gear life of vertical mill gearbox

The invention belongs to the technical field of vertical mill gearboxes, and particularly discloses a vertical mill gearbox gear life online intelligent regulation and control method and system.The method comprises the steps that a main test gearbox gear rotating speed signal and a box body vibration acceleration signal are collected, whether a gear enters a degeneration stage or not is judged, and if the gear enters the degeneration stage, the gear is started; if yes, constructing a life prediction model and predicting the remaining life of the gear of the vertical mill gearbox by using the life prediction model; in combination with a vertical mill gearbox gear remaining life prediction result and the current expected remaining life, optimal regulation and control working condition parameters are calculated on the basis of a model-free adaptive regulation and control MFAC theory and by introducing a pseudo partial derivative PPD and a tight format dynamic linearization CFDL model; and based on the optimal regulation and control working condition parameters, the operation working condition of the vertical mill gearbox gear is regulated and controlled. By adopting the technical scheme, the remaining life of the gear of the vertical mill gearbox is predicted, the running state of the gear of the gearbox is regulated in real time, and the actual service life of the gear of the vertical mill gearbox is prolonged to be close to the expected service life.
Owner:CHONGQING UNIV

Current ripple suppression method of underwater propulsion motor

The invention discloses a current ripple suppression method for an underwater propulsion motor, relates to the technical field of motor control, and reduces overshoot and adjustment time when the rotating speed of the motor changes suddenly by improving a traditional field-oriented control framework and adopting a differential tracker to smooth an input reference rotating speed. Dead-beat model-free predictive control and an ESO observer are introduced into a current loop, and current ripples caused by parameter mismatch and external interference are effectively restrained. Model-free predictive control is adopted, the number of mathematical model parameters is reduced, the model accuracy is improved, and the control precision is improved. The current ripple is further reduced by identifying the inductance parameter and adjusting the PWM frequency according to the actual inductance value. According to the invention, the overshoot phenomenon in the rotating speed adjusting process is obviously reduced, the stability and efficiency of motor operation are effectively improved, and the service life of the motor is prolonged. The invention provides a new solution for improving the performance of the underwater robot propulsion system.
Owner:HEBEI UNIV OF TECH

Multi-mode redundant automatic driving vehicle model-free longitudinal control method

ActiveCN119568128ARealize vertical stability controlSolve the stability problem of vertical controlDrive by wireControl signal
The invention discloses a multi-mode redundant model-free longitudinal control method for an automatic driving vehicle. The method comprises the following steps: collecting a longitudinal control signal source; establishing an off-line driving torque database and an off-line braking pressure database; designing a model-free vehicle speed control strategy, and calculating a vehicle speed expected driving torque and a vehicle speed expected braking pressure; designing a model-free acceleration control strategy, and calculating an expected acceleration driving torque; a model-free deceleration control strategy is designed, and deceleration expected brake pressure is calculated; and according to the vehicle speed expected driving torque, the vehicle speed expected braking pressure, the acceleration expected driving torque and the deceleration expected braking pressure, a model-free longitudinal control mode arbitration strategy is designed, the request driving torque and the request braking pressure are output, and longitudinal operation is achieved. According to the method, the stability problem of longitudinal control of the automatic driving vehicle can be solved under the condition that vehicle model parameters are missing or the model parameters are uncertain, and unexpected driving or braking caused by interference of factors such as program abnormity and communication congestion is prevented.
Owner:EAST CHINA JIAOTONG UNIVERSITY

Permanent magnet motor continuous set model-free predictive control method based on Bayesian optimization

The invention provides a permanent magnet motor continuous set model-free predictive control method based on Bayesian optimization, and relates to the field of permanent magnet synchronous motor control. The method comprises the following steps: acquiring a hyper-local model and an extended state observer; determining the bandwidth and the input gain as optimization variables, and obtaining a training set and a test set for Bayesian optimization; joint probability distribution of the training set and the test set is calculated through a kernel function, and a prediction mean value and a prediction variance of optimization variables are determined; an optimization variable combination is screened based on the expected value collection function, and the bandwidth and the input gain are updated based on the optimization variable combination; based on the updated extended state observer and the hyper-local model, calculating the reference voltage of the next control period by using a dead-beat control principle; the reference voltage is decomposed into basic voltage vectors through space vector modulation, and the switching sequence of the basic voltage vectors is executed according to the minimum switching times to drive the permanent magnet motor. The method is not affected by motor parameter changes, and the current prediction control steady-state performance can be improved.
Owner:ZHEJIANG UNIV +1

Model-free superhelix fast integration terminal sliding mode control method for permanent magnet synchronous motor

The invention provides a novel model-free fast integration terminal sliding mode controller method for a permanent magnet synchronous motor based on an improved extended nonsingular terminal sliding mode disturbance observer, and the method is compared with a PI control method and a model-free sliding mode control method based on an extended sliding mode observer. The method can reduce the dependence of a controller on a specific mathematical model of a controlled system, is more suitable for nonlinear and strong coupling systems such as a permanent magnet synchronous motor, employs an improved extended nonsingular terminal sliding mode disturbance observer to estimate unknown total disturbance, and enhances the robustness and anti-interference capability of the method. The control method has high response speed and high control precision, and has a good fault-tolerant control function on the parameter perturbation of the motor, so that the permanent magnet synchronous motor can operate efficiently, stably and reliably under the parameter perturbation condition.
Owner:HUNAN UNIV OF TECH

Method and system for rhythmic motion control of robot based on neural oscillator

A method and a system for rhythmic motion control of a robot based on a neural oscillator, including: acquiring a current state of the robot, and a phase and a frequency generated by the neural oscillator; and obtaining a control instruction according to the acquired current state, phase and frequency and a preset reinforcement learning network so as to control the robot. The preset reinforcement learning network includes an action space, a pattern formation network and the neural oscillator. A control structure designed by the present disclosure, which is composed of the neural oscillator and the pattern formation network, can ensure formation of an expected rhythmic motion behavior; and meanwhile, a designed action space for joint position increment can effectively accelerate the training process of rhythmic motion reinforcement learning, and solve a problem that design of the reward function is time-consuming and difficult in learning with existing model-free reinforcement learning.
Owner:SHANDONG UNIV

Model-free sliding mode single-loop control method for permanent magnet synchronous motor

The invention discloses a model-free sliding mode single-loop control method for a permanent magnet synchronous motor. The method comprises the following steps: step 1, establishing a permanent magnet synchronous motor mathematical model under a d-q coordinate system; step 2, establishing a hyperlocal model of the permanent magnet synchronous motor; step 3, designing a system state equation, including establishing equations of state variables and matching disturbance, non-matching disturbance and q-axis stator voltage; 4, designing a finite time generalized proportional-integral observer for estimating matching disturbance and non-matching disturbance and estimating the change rate of the non-matching disturbance; and step 5, designing a single-loop model-free sliding mode speed controller to obtain the single-loop model-free sliding mode speed controller. According to the model-free sliding mode single-loop control method for the permanent magnet synchronous motor, the permanent magnet synchronous motor hyper-local model is established, the designed permanent magnet synchronous motor hyper-local model does not contain any motor parameter, the dependence on the motor parameter of the system is eliminated, and the anti-interference capability of the system is improved.
Owner:青岛领智电子科技有限公司

Engineering system fault-tolerant tracking control method based on data driving

The invention discloses an engineering system fault-tolerant tracking control method based on data driving, and belongs to the technical field of engineering control methods. Comprising the following steps: S1, establishing an engineering system equivalence model under a fault, and defining a performance index function and a corresponding value function so as to convert an optimal control problem into a zero-sum game problem; s2, aiming at the problem that the state of the engineering system is unmeasurable, reconstructing the state by utilizing historical input and output data so as to design and solve an optimal control strategy; and S3, introducing and defining a Q function, designing a controller gain and a disturbance gain # imgabs0 #, and optimizing the # imgabs1 # in combination with a designed model-free non-strategy Q-learning output feedback algorithm to obtain an optimal controller. Through an injection molding industrial process and a depth control simulation experiment of an autonomous underwater vehicle (AUV), convergence of the algorithm and an excellent tracking control effect of a designed controller are verified.
Owner:GUANGZHOU UNIVERSITY

Model-free deadbeat predictive current control method for permanent magnet synchronous motor based on current separation

The invention belongs to the technical field of motor driving and control application, and provides a permanent magnet synchronous motor model-free and dead-beat predictive current control method based on current separation, and the main scheme is as follows: firstly, a permanent magnet synchronous motor current separation model is introduced, and the relationship between different parts in sampling current change is deduced based on the model; then, a model-free dead-beat control integral control law with extremely low parameter dependence is designed; furthermore, only a series of uncomplicated calculations need to be carried out in a control period, and more accurate predicted current and predicted voltage can be calculated without depending on motor parameters. Therefore, no observer is needed, and errors and oscillation possibly brought by the observer are avoided.
Owner:SICHUAN UNIV

Bridge crane game model-free optimal control method based on event triggering

The invention relates to a bridge crane game model-free optimal control method based on event triggering, and the method comprises the steps: collecting a state vector of a bridge crane in real time, and building a nonlinear multi-player system model of the bridge crane; estimating an unknown dynamic function and an input gain matrix on line in the input identifier neural network; according to an event triggering mechanism, whether triggering is conducted or not is judged based on the error between the current state vector and the state vector of the recently-triggered sampling; if so, triggering a dynamic updating instruction; under a non-zero sum game framework, obtaining an optimal value function gradient based on an estimation result and a current state vector through a self-adaptive evaluator network, and generating an event triggering optimal control law of each player based on a sampled state vector; and the event triggering optimal control law is processed by a zero-order retainer and then is output as a physical driving signal to control the operation of the bridge crane. Compared with the prior art, the method has the advantages of high applicability, high disturbance resistance, high accuracy and the like.
Owner:SHANGHAI UNIV

Anti-interference control method, system and equipment of photovoltaic panel cleaning unmanned aerial vehicle and medium

The invention relates to the technical field of unmanned aerial vehicle anti-interference control, and provides an anti-interference control method, system and device for a photovoltaic panel cleaning unmanned aerial vehicle, and a medium, and the method comprises the steps: constructing an unmanned aerial vehicle dynamic linearization control model based on the external unknown disturbance of the unmanned aerial vehicle and the dynamic characteristics of a four-rotor unmanned aerial vehicle; respectively carrying out system input control analysis and pseudo partial derivative estimated value control analysis by taking a balance tracking error and an input quantity change as a principle and taking a balance modeling error and a pseudo partial derivative estimated value change as a principle to obtain a corresponding model-free adaptive control law and a model-free adaptive parameter estimation law; and acquiring an external unknown disturbance monitoring quantity based on a preset disturbance observer, and generating a control signal in combination with the dynamic linearization control model of the unmanned aerial vehicle to perform attitude regulation and control. On the basis of model-free self-adaptive control scheme design considering unknown disturbance, the control modeling workload can be reduced, self-adaptive change adjustment can be achieved, the self-adaptive anti-interference and vibration suppression capacity is improved, and the attitude control precision is effectively improved.
Owner:WUHAN HUAYU ZHIFEI TECHNOLOGY CO LTD

Rotation force-based feedforward-feedback model-free adaptive tracking control method and system for jumbolter

The invention relates to the technical field of drilling, and provides a roofbolter feedforward-feedback model-free adaptive tracking control method and system based on rotation force. According to the method, a valve-controlled hydraulic propulsion control model for driving a hydraulic cylinder and a corresponding reversing valve in the working process of the hydraulic jumbolter is established, and a nonlinear autoregressive moving average model between the propulsion force in the working process of the hydraulic jumbolter and the output driving current of the reversing valve is obtained through the valve-controlled hydraulic propulsion control model; through a nonlinear autoregression moving average model of the hydraulic jumbolter, an output identification observer deployed with a data-driven adaptive control algorithm of the hydraulic jumbolter is established, and the output identification observer performs adaptive tracking control on the working state of the hydraulic jumbolter through the deployed data-driven adaptive control algorithm. The tracking control problem of the valve control electro-hydraulic servo unit under the complex working condition is effectively solved.
Owner:HENAN POLYTECHNIC UNIV

Data-driven modeling and control method for flexible operation of cogeneration unit

The invention discloses a data-driven modeling and control method for flexible operation of a combined heat and power generation unit. The method comprises the following steps: firstly, establishing a unit model based on an improved transform neural network framework; secondly, designing a model-free self-adaptive predictive control strategy optimized by adopting an enhanced frost ice optimization algorithm, and using the model-free self-adaptive predictive control strategy to accurately track an automatic power generation control instruction; and finally, verifying the feasibility of the modeling and control strategy based on a simulation platform. According to the method, deep learning modeling and model-free adaptive control are effectively combined, and the provided strategy can meet the flexibility requirement under deep peak regulation of the unit.
Owner:NORTH CHINA ELECTRIC POWER UNIV

Model-free robust control method and system for pantograph with external disturbance

The invention discloses a model-free robust control method and system for a pantograph with external disturbance. Collecting dynamic data in the running process of the train pantograph; establishing a train pantograph data model with external disturbance; estimating external disturbance; optimizing and updating pseudo partial derivative information in the train pantograph data model; designing a model-free robust control scheme for the train pantograph with external disturbance; optimizing and updating an error control gain and a disturbance compensation control gain in the control scheme; a model-free robust control scheme is adopted to calculate and obtain a control input signal, and the train pantograph is controlled until a control task is finished; the control method and system provided by the invention are not only suitable for the train pantograph with external disturbance, solve the disturbance compensation problem, reduce the modeling difficulty and reduce the computing resource consumption, but also have the application prospect of being popularized to other single-input single-output systems.
Owner:CHINA RAILWAY DESIGN GRP CO LTD

Permanent magnet synchronous motor model-free sliding mode control method based on novel reaching law

The invention discloses a permanent magnet synchronous motor model-free sliding mode control method based on a novel reaching law, belongs to the field of power electronics, and aims at solving the problems that traditional sliding mode control is large in buffeting and high in steady-state error and depends on an accurate model. According to the method, based on a model-free theory, a permanent magnet synchronous motor rotating speed ring super-local model is constructed, then a novel reaching law containing a dynamic parameter delta = e-x beta is designed, and the contradiction between buffeting suppression and quick response is solved; meanwhile, designing a novel sliding-mode observer, and estimating an unknown part g of the system to realize disturbance feed-forward compensation; and finally, a q-axis current reference value control law is obtained through derivation in combination with a sliding mode surface and a mechanical motion equation. The method can weaken the buffeting of the sliding mode, improves the anti-interference performance and the steady-state precision of the system, guarantees the finite time convergence of the state, and is suitable for the control of the permanent magnet synchronous motor in the fields of aerospace and new energy automobiles.
Owner:SHENZHEN HAOCHUAN FUTURE TECHNOLOGY CO LTD

Model-free adaptive control method based on UKF pseudo partial derivative estimation

The invention discloses a model-free adaptive control method based on UKF pseudo partial derivative estimation, and belongs to the technical field of automatic control. The method mainly solves the problems that an accurate mathematical model is difficult to establish in a nonlinear control system in the actual industry, and various uncertainties, complex unknown disturbances and the like influence the control accuracy. The control scheme comprises the following steps: designing a model-free adaptive controller based on input and output data; designing an unscented Kalman filter (UKF) to estimate a pseudo partial derivative; establishing a model-free adaptive control scheme based on UKF pseudo partial derivative estimation; according to the model-free adaptive control method based on UKF pseudo partial derivative estimation disclosed by the invention, better control precision and stronger anti-interference capability can be realized in an industrial nonlinear process under the influence of unknown disturbance, and the control precision requirement of industrial production is met.
Owner:QINGDAO UNIV OF SCI & TECH

Model-free AUV depth control method based on reinforcement learning

The invention particularly relates to a model-free AUV depth control method based on reinforcement learning. The method comprises the following steps: establishing an AUV kinetic model; based on an AUV dynamical model, establishing an interaction model of the AUV and the environment by adopting a Markov decision process, determining an action space variable and a state space variable of an AUV control system, and establishing an AUV depth control objective function and a sectional reward function; establishing a neural network model, respectively establishing a strategy network and an evaluation network, and performing model training on the control strategy by adopting a continuous PPO algorithm to obtain control strategy parameters of the AUV; the control strategy parameters of the AUV are used for realizing vertical plane depth-keeping control of the AUV; and through reinforcement learning, enabling the AUV to update the training network at each fixed step length in the set depth control training until convergence, and obtaining a final strategy network at a predetermined depth. The method has high real-time control capability and self-adaptive control characteristics, can effectively cope with environmental changes, and shows depth control robustness and depth control adaptability.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Model-free self-adaptive control method for electro-hydraulic servo system of drilling machine based on data driving

The invention discloses a model-free self-adaptive control drilling machine electro-hydraulic servo system method and system based on data driving, and relates to the technical field of self-adaptive control drilling machine electro-hydraulic servo, and the method comprises the steps: obtaining real-time data of a drilling machine electro-hydraulic servo system, and carrying out the preprocessing; finding out the correlation between the environmental parameters and the system performance indexes by using a data mining and statistical analysis method; adjusting system control parameters in real time according to the real-time data collected in real time and the association obtained through analysis; and according to the actual operation effect of the system and the new real-time data, the strategy of environment adaptation and fault prevention is continuously optimized and adjusted. The control parameters are adjusted based on real-time data and correlation obtained through analysis, compared with a traditional method, the drilling machine electro-hydraulic servo system can be controlled more accurately, the maintenance and replacement frequency of equipment is reduced, and therefore the operation cost is reduced, the strategy is optimized continuously according to the actual operation effect and new data, and the operation efficiency is improved. And the conditions of accidental shutdown and production interruption are reduced.
Owner:SHAOXING DAMING ELECTRICITY CONSTRUCT CO LTD +2

Data-driven specified time performance control method applied to model-free unmanned ship

The invention discloses a specified time performance control method applied to model-free unmanned ship data driving. The method comprises the following steps: acquiring an error conversion function based on a constructed specified time performance function; driving a neural predictor based on the constructed unmanned ship data so as to realize estimation of model uncertain items and unknown control input gains, and obtaining an unmanned ship dynamic model; on the basis of the error conversion function, a model-free data driving virtual control law is constructed according to the unmanned ship dynamics model, so that a data driving controller is constructed; and designing a switching dynamic event triggering mechanism for switching the fixed threshold triggering mechanism and the dynamic event triggering mechanism according to the data driving controller, and realizing data-driven specified time performance control of the unmanned ship according to the switching dynamic event triggering mechanism. The problems that in the existing unmanned ship control process, the control performance of the underactuated unmanned ship cannot be effectively improved through data driving, it is ensured that the precision of reaching the specified track within the preset time is poor are solved, in addition, most of existing methods based on a neural network depend on a large number of sample training fixed models, and when facing new tasks or environment changes, the control performance of the underactuated unmanned ship cannot be effectively improved. The problem that the adaptability of a training model is limited exists.
Owner:DALIAN MARITIME UNIVERSITY