To get simpler operation in modified fuzzy adaptive learning control network （FALCON） in some engineering application, sigmoid nonlinear function is employed as a substitute of traditional Gaussian membership functi...To get simpler operation in modified fuzzy adaptive learning control network （FALCON） in some engineering application, sigmoid nonlinear function is employed as a substitute of traditional Gaussian membership function. For making the modified FALCON learning more efficient and stable, a simulated annealing （SA） learning coefficient is introduced into learning algorithm. At first, the basic concepts and main advantages of FALCON were briefly reviewed. Subsequently, the topological structure and nodes operation were illustrated; the gradient-descent learning algorithm with SA learning coefficient was derived; and the distinctions between the archetype and the modification were analyzed. Eventually, the significance and worthiness of the modified FALCON were validated by its application to probability prediction of anode effect in aluminium electrolysis cells.展开更多
Single gimbal control moment gyroscope(SGCMG)with high precision and fast response is an important attitude control system for high precision docking,rapid maneuvering navigation and guidance system in the aerospace f...Single gimbal control moment gyroscope(SGCMG)with high precision and fast response is an important attitude control system for high precision docking,rapid maneuvering navigation and guidance system in the aerospace field.In this paper,considering the influence of multi-source disturbance,a data-based feedback relearning(FR)algorithm is designed for the robust control of SGCMG gimbal servo system.Based on adaptive dynamic programming and least-square principle,the FR algorithm is used to obtain the servo control strategy by collecting the online operation data of SGCMG system.This is a model-free learning strategy in which no prior knowledge of the SGCMG model is required.Then,combining the reinforcement learning mechanism,the servo control strategy is interacted with system dynamic of SGCMG.The adaptive evaluation and improvement of servo control strategy against the multi-source disturbance are realized.Meanwhile,a data redistribution method based on experience replay is designed to reduce data correlation to improve algorithm stability and data utilization efficiency.Finally,by comparing with other methods on the simulation model of SGCMG,the effectiveness of the proposed servo control strategy is verified.展开更多
Random vector functional ink(RVFL)networks belong to a class of single hidden layer neural networks in which some parameters are randomly selected.Their network structure in which contains the direct links between inp...Random vector functional ink(RVFL)networks belong to a class of single hidden layer neural networks in which some parameters are randomly selected.Their network structure in which contains the direct links between inputs and outputs is unique,and stability analysis and real-time performance are two difficulties of the control systems based on neural networks.In this paper,combining the advantages of RVFL and the ideas of online sequential extreme learning machine(OS-ELM)and initial-training-free online extreme learning machine(ITFOELM),a novel online learning algorithm which is named as initial-training-free online random vector functional link algo rithm(ITF-ORVFL)is investigated for training RVFL.The link vector of RVFL network can be analytically determined based on sequentially arriving data by ITF-ORVFL with a high learning speed,and the stability for nonlinear systems based on this learning algorithm is analyzed.The experiment results indicate that the proposed ITF-ORVFL is effective in coping with nonparametric uncertainty.展开更多
Designing advanced design techniques for feedback stabilization and optimization of complex systems is important to the modern control field. In this paper, a near-optimal regulation method for general nonaffine dynam...Designing advanced design techniques for feedback stabilization and optimization of complex systems is important to the modern control field. In this paper, a near-optimal regulation method for general nonaffine dynamics is developed with the help of policy learning. For addressing the nonaffine nonlinearity, a pre-compensator is constructed, so that the augmented system can be formulated as affine-like form. Different cost functions are defined for original and transformed controlled plants and then their relationship is analyzed in detail. Additionally, an adaptive critic algorithm involving stability guarantee is employed to solve the augmented optimal control problem. At last, several case studies are conducted for verifying the stability, robustness, and optimality of a torsional pendulum plant with suitable cost.展开更多
Reinforcement learning provides a cognitive science perspective to behavior and sequential decision making providedthat reinforcement learning algorithms introduce a computational concept of agency to the learning pro...Reinforcement learning provides a cognitive science perspective to behavior and sequential decision making providedthat reinforcement learning algorithms introduce a computational concept of agency to the learning problem.Hence it addresses an abstract class of problems that can be characterized as follows: An algorithm confronted withinformation from an unknown environment is supposed to find step wise an optimal way to behave based only on somesparse, delayed or noisy feedback from some environment, that changes according to the algorithm’s behavior. Hencereinforcement learning offers an abstraction to the problem of goal-directed learning from interaction. The paper offersan opinionated introduction in the algorithmic advantages and drawbacks of several algorithmic approaches to providealgorithmic design options.展开更多
In this study,We propose a compensated distributed adaptive learning algorithm for heterogeneous multi-agent systems with repetitive motion,where the leader's dynamics are unknown,and the controlled system's p...In this study,We propose a compensated distributed adaptive learning algorithm for heterogeneous multi-agent systems with repetitive motion,where the leader's dynamics are unknown,and the controlled system's parameters are uncertain.The multiagent systems are considered a kind of hybrid order nonlinear systems,which relaxes the strict requirement that all agents are of the same order in some existing work.For theoretical analyses,we design a composite energy function with virtual gain parameters to reduce the restriction that the controller gain depends on global information.Considering the stability of the controller,we introduce a smooth continuous function to improve the piecewise controller to avoid possible chattering.Theoretical analyses prove the convergence of the presented algorithm,and simulation experiments verify the effectiveness of the algorithm.展开更多
文摘To get simpler operation in modified fuzzy adaptive learning control network （FALCON） in some engineering application, sigmoid nonlinear function is employed as a substitute of traditional Gaussian membership function. For making the modified FALCON learning more efficient and stable, a simulated annealing （SA） learning coefficient is introduced into learning algorithm. At first, the basic concepts and main advantages of FALCON were briefly reviewed. Subsequently, the topological structure and nodes operation were illustrated; the gradient-descent learning algorithm with SA learning coefficient was derived; and the distinctions between the archetype and the modification were analyzed. Eventually, the significance and worthiness of the modified FALCON were validated by its application to probability prediction of anode effect in aluminium electrolysis cells.
基金This work was supported by the National Natural Science Foundation of China(No.62022061)Tianjin Natural Science Foundation(No.20JCYBJC00880)Beijing Key Laboratory Open Fund of Long-Life Technology of Precise Rotation and Transmission Mechanisms.
文摘Single gimbal control moment gyroscope(SGCMG)with high precision and fast response is an important attitude control system for high precision docking,rapid maneuvering navigation and guidance system in the aerospace field.In this paper,considering the influence of multi-source disturbance,a data-based feedback relearning(FR)algorithm is designed for the robust control of SGCMG gimbal servo system.Based on adaptive dynamic programming and least-square principle,the FR algorithm is used to obtain the servo control strategy by collecting the online operation data of SGCMG system.This is a model-free learning strategy in which no prior knowledge of the SGCMG model is required.Then,combining the reinforcement learning mechanism,the servo control strategy is interacted with system dynamic of SGCMG.The adaptive evaluation and improvement of servo control strategy against the multi-source disturbance are realized.Meanwhile,a data redistribution method based on experience replay is designed to reduce data correlation to improve algorithm stability and data utilization efficiency.Finally,by comparing with other methods on the simulation model of SGCMG,the effectiveness of the proposed servo control strategy is verified.
基金supported by the Ministry of Science and Technology of China(2018AAA0101000,2017YFF0205306,WQ20141100198)the National Natural Science Foundation of China(91648117)。
文摘Random vector functional ink(RVFL)networks belong to a class of single hidden layer neural networks in which some parameters are randomly selected.Their network structure in which contains the direct links between inputs and outputs is unique,and stability analysis and real-time performance are two difficulties of the control systems based on neural networks.In this paper,combining the advantages of RVFL and the ideas of online sequential extreme learning machine(OS-ELM)and initial-training-free online extreme learning machine(ITFOELM),a novel online learning algorithm which is named as initial-training-free online random vector functional link algo rithm(ITF-ORVFL)is investigated for training RVFL.The link vector of RVFL network can be analytically determined based on sequentially arriving data by ITF-ORVFL with a high learning speed,and the stability for nonlinear systems based on this learning algorithm is analyzed.The experiment results indicate that the proposed ITF-ORVFL is effective in coping with nonparametric uncertainty.
基金supported in part by the National Natural Science Foundation of China(61773373,U1501251,61533017)in part by the Young Elite Scientists Sponsorship Program by the China Association for Science and Technologyin part by the Youth Innovation Promotion Association of the Chinese Academy of Sciences
文摘Designing advanced design techniques for feedback stabilization and optimization of complex systems is important to the modern control field. In this paper, a near-optimal regulation method for general nonaffine dynamics is developed with the help of policy learning. For addressing the nonaffine nonlinearity, a pre-compensator is constructed, so that the augmented system can be formulated as affine-like form. Different cost functions are defined for original and transformed controlled plants and then their relationship is analyzed in detail. Additionally, an adaptive critic algorithm involving stability guarantee is employed to solve the augmented optimal control problem. At last, several case studies are conducted for verifying the stability, robustness, and optimality of a torsional pendulum plant with suitable cost.
文摘Reinforcement learning provides a cognitive science perspective to behavior and sequential decision making providedthat reinforcement learning algorithms introduce a computational concept of agency to the learning problem.Hence it addresses an abstract class of problems that can be characterized as follows: An algorithm confronted withinformation from an unknown environment is supposed to find step wise an optimal way to behave based only on somesparse, delayed or noisy feedback from some environment, that changes according to the algorithm’s behavior. Hencereinforcement learning offers an abstraction to the problem of goal-directed learning from interaction. The paper offersan opinionated introduction in the algorithmic advantages and drawbacks of several algorithmic approaches to providealgorithmic design options.
基金the National Natural Science Foundation of China(Grant Nos.62203342,62073254,92271101,62106186,and 62103136)the Fundamental Research Funds for the Central Universities(Grant Nos.XJS220704,QTZX23003,and ZYTS23046)+1 种基金the Project Funded by China Postdoctoral Science Foundation(Grant No.2022M712489)the Natural Science Basic Research Program of Shaanxi(Grant No.2023-JC-YB-585)。
文摘In this study,We propose a compensated distributed adaptive learning algorithm for heterogeneous multi-agent systems with repetitive motion,where the leader's dynamics are unknown,and the controlled system's parameters are uncertain.The multiagent systems are considered a kind of hybrid order nonlinear systems,which relaxes the strict requirement that all agents are of the same order in some existing work.For theoretical analyses,we design a composite energy function with virtual gain parameters to reduce the restriction that the controller gain depends on global information.Considering the stability of the controller,we introduce a smooth continuous function to improve the piecewise controller to avoid possible chattering.Theoretical analyses prove the convergence of the presented algorithm,and simulation experiments verify the effectiveness of the algorithm.
