A support vector machine with guadratic polynomial kernel function based nonlinear model multi-step-ahead optimizing predictive controller was presented. A support vector machine based predictive model was established...A support vector machine with guadratic polynomial kernel function based nonlinear model multi-step-ahead optimizing predictive controller was presented. A support vector machine based predictive model was established by black-box identification. And a quadratic objective function with receding horizon was selected to obtain the controller output. By solving a nonlinear optimization problem with equality constraint of model output and boundary constraint of controller output using Nelder-Mead simplex direct search method, a sub-optimal control law was achieved in feature space. The effect of the controller was demonstrated on a recognized benchmark problem and a continuous-stirred tank reactor. The simulation results show that the multi-step-ahead predictive controller can be well applied to nonlinear system, with better performance in following reference trajectory and disturbance-rejection.展开更多
Support Vector Machines (SVMs) have been widely used in pattern recognition and have also drawn considerable interest in control areas. Based on a method of least squares SVM (LS-SVM) for multivariate function estimat...Support Vector Machines (SVMs) have been widely used in pattern recognition and have also drawn considerable interest in control areas. Based on a method of least squares SVM (LS-SVM) for multivariate function estimation, a generalized inverse system is developed for the linearization and decoupling control of a general nonlinear continuous system. The approach of inverse modelling via LS-SVM and parameters optimization using the Bayesian evidence framework is discussed in detail. In this paper, complex high-order nonlinear system is decoupled into a number of pseudo-linear Single Input Single Output (SISO) subsystems with linear dynamic components. The poles of pseudo-linear subsystems can be configured to desired positions. The proposed method provides an effective alternative to the controller design of plants whose accurate mathematical model is un- known or state variables are difficult or impossible to measure. Simulation results showed the efficacy of the method.展开更多
This paper provides an introduction to a support vector machine, a new kernel-based technique introduced in statistical learning theory and structural risk minimization, then presents a modeling-control framework base...This paper provides an introduction to a support vector machine, a new kernel-based technique introduced in statistical learning theory and structural risk minimization, then presents a modeling-control framework based on SVM. At last a numerical experiment is taken to demonstrate the proposed approach's correctness and effectiveness.展开更多
An inverse learning control scheme using the support vector machine (SVM) for regression was proposed. The inverse learning approach is originally researched in the neural networks. Compared with neural networks, SVMs...An inverse learning control scheme using the support vector machine (SVM) for regression was proposed. The inverse learning approach is originally researched in the neural networks. Compared with neural networks, SVMs overcome the problems of local minimum and curse of dimensionality. Additionally, the good generalization performance of SVMs increases the robustness of control system. The method of designing SVM inverse learning controller was presented. The proposed method is demonstrated on tracking problems and the performance is satisfactory.展开更多
A support vector machine (SVM) with quadratic polynomial kernel function based nonlinear model one-step-ahead predictive controller is presented. The SVM based predictive model is established with black-box identifica...A support vector machine (SVM) with quadratic polynomial kernel function based nonlinear model one-step-ahead predictive controller is presented. The SVM based predictive model is established with black-box identification method. By solving a cubic equation in the feature space, an explicit predictive control law is obtained through the predictive control mechanism. The effect of controller is demonstrated on a recognized benchmark problem and on the control of continuous-stirred tank reactor (CSTR). Simulation results show that SVM with quadratic polynomial kernel function based predictive controller can be well applied to nonlinear systems, with good performance in following reference trajectory as well as in disturbance-rejection.展开更多
This paper proposes a novel excitation controller using support vector machines (SVM) and approximate models. The nonlinear control law is derived directly based on an input-output approximation method via Taylor ex...This paper proposes a novel excitation controller using support vector machines (SVM) and approximate models. The nonlinear control law is derived directly based on an input-output approximation method via Taylor expansion, which not only avoids complex control development and intensive computation, but also avoids online learning or adjustment. Only a general SVM modelling technique is involved in both model identification and controller implementation. The robustness of the stability is rigorously established using the Lyapunov method. Several simulations demonstrate the effectiveness of the proposed excitation controller.展开更多
A learning controller of nonhonolomic robot in real-time based on support vector machine(SVM)is presented.The controller includes two parts:one is kinematic controller based on nonlinear law,and the other is dynamic c...A learning controller of nonhonolomic robot in real-time based on support vector machine(SVM)is presented.The controller includes two parts:one is kinematic controller based on nonlinear law,and the other is dynamic controller based on SVM.The kinematic controller is aimed to provide desired velocity which can make the steering system stable.The dynamic controller is aimed to transform the desired velocity to control torque.The parameters of the dynamic system of the robot are estimated through SVM learning algorithm according to the training data of sliding windows in real time.The proposed controller can adapt to the changes in the robot model and uncertainties in the environment.Compared with artificial neural network(ANN)controller,SVM controller can converge to the reference trajectory more quickly and the tracking error is smaller.The simulation results verify the effectiveness of the method proposed.展开更多
This paper describes a nonlinear model predictive controller for regulating a molten carbonate fuel cell (MCFC). In order to improve MCFC’s generating performance, prolong its life and guarantee safety, it must be co...This paper describes a nonlinear model predictive controller for regulating a molten carbonate fuel cell (MCFC). In order to improve MCFC’s generating performance, prolong its life and guarantee safety, it must be controlled efficiently. First, the output voltage of an MCFC stack is identified by a least squares support vector machine (LS-SVM) method with radial basis function (RBF) kernel so as to implement nonlinear predictive control. And then, the optimal control sequences are obtained by applying genetic algorithm (GA). The model and controller have been realized in the MATLAB environment. Simulation results indicated that the proposed controller exhibits satisfying control effect.展开更多
In this paper, a nonlinear model predictive control strategy which utilizes a probabilistic sparse kernel learning technique called relevance vector regression (RVR) and particle swarm optimization with controllable...In this paper, a nonlinear model predictive control strategy which utilizes a probabilistic sparse kernel learning technique called relevance vector regression (RVR) and particle swarm optimization with controllable random exploration velocity (PSO-CREV) is applied to a catalytic continuous stirred tank reactor (CSTR) process. An accurate reliable nonlinear model is first identified by RVR with a radial basis function (RBF) kernel and then the optimization of control sequence is speeded up by PSO-CREV. Additional stochastic behavior in PSO-CREV is omitted for faster convergence of nonlinear optimization. An improved system performance is guaranteed by an accurate sparse predictive model and an efficient and fast optimization algorithm. To compare the performance, model predictive control (MPC) using a deterministic sparse kernel learning technique called Least squares support vector machines (LS-SVM) regression is done on a CSTR. Relevance vector regression shows improved tracking performance with very less computation time which is much essential for real time control.展开更多
设计了自适应逆控制的永磁同步电机(PMSM)控制系统,控制系统采用双闭环结构的矢量控制,将自适应逆控制方法引入速度控制。运用非线性自适应滤波器,实现系统的建模与逆建模,并引入滤波器构成了速度控制器,采用最小均方差(Least Mean Squa...设计了自适应逆控制的永磁同步电机(PMSM)控制系统,控制系统采用双闭环结构的矢量控制,将自适应逆控制方法引入速度控制。运用非线性自适应滤波器,实现系统的建模与逆建模,并引入滤波器构成了速度控制器,采用最小均方差(Least Mean Square,LMS)自适应滤波算法在线调整其权函数,实现速度的精确控制。在基于DSP的永磁同步电机速度控制系统平台上的实验结果表明,非线性滤波器能够建立电流环模型,提出的非线性自适应逆控制方法能够实现精确的速度控制。与PID控制方法相比,具有更精确的速度跟踪性及更快的响应速度。展开更多
文摘A support vector machine with guadratic polynomial kernel function based nonlinear model multi-step-ahead optimizing predictive controller was presented. A support vector machine based predictive model was established by black-box identification. And a quadratic objective function with receding horizon was selected to obtain the controller output. By solving a nonlinear optimization problem with equality constraint of model output and boundary constraint of controller output using Nelder-Mead simplex direct search method, a sub-optimal control law was achieved in feature space. The effect of the controller was demonstrated on a recognized benchmark problem and a continuous-stirred tank reactor. The simulation results show that the multi-step-ahead predictive controller can be well applied to nonlinear system, with better performance in following reference trajectory and disturbance-rejection.
基金Supported by the State Key Development Program for Basic Research of China (No.2002CB312200) and the National Natural Science Foundation of China (No.60574019).
基金Project supported by the National Basic Research Program (973) of China (No. 2002CB312200), and the Hi-Tech Research and Devel-opment Program (863) of China (No. 2002AA412010)
文摘Support Vector Machines (SVMs) have been widely used in pattern recognition and have also drawn considerable interest in control areas. Based on a method of least squares SVM (LS-SVM) for multivariate function estimation, a generalized inverse system is developed for the linearization and decoupling control of a general nonlinear continuous system. The approach of inverse modelling via LS-SVM and parameters optimization using the Bayesian evidence framework is discussed in detail. In this paper, complex high-order nonlinear system is decoupled into a number of pseudo-linear Single Input Single Output (SISO) subsystems with linear dynamic components. The poles of pseudo-linear subsystems can be configured to desired positions. The proposed method provides an effective alternative to the controller design of plants whose accurate mathematical model is un- known or state variables are difficult or impossible to measure. Simulation results showed the efficacy of the method.
文摘This paper provides an introduction to a support vector machine, a new kernel-based technique introduced in statistical learning theory and structural risk minimization, then presents a modeling-control framework based on SVM. At last a numerical experiment is taken to demonstrate the proposed approach's correctness and effectiveness.
文摘An inverse learning control scheme using the support vector machine (SVM) for regression was proposed. The inverse learning approach is originally researched in the neural networks. Compared with neural networks, SVMs overcome the problems of local minimum and curse of dimensionality. Additionally, the good generalization performance of SVMs increases the robustness of control system. The method of designing SVM inverse learning controller was presented. The proposed method is demonstrated on tracking problems and the performance is satisfactory.
基金Support by China 973 Project (No. 2002CB312200).
文摘A support vector machine (SVM) with quadratic polynomial kernel function based nonlinear model one-step-ahead predictive controller is presented. The SVM based predictive model is established with black-box identification method. By solving a cubic equation in the feature space, an explicit predictive control law is obtained through the predictive control mechanism. The effect of controller is demonstrated on a recognized benchmark problem and on the control of continuous-stirred tank reactor (CSTR). Simulation results show that SVM with quadratic polynomial kernel function based predictive controller can be well applied to nonlinear systems, with good performance in following reference trajectory as well as in disturbance-rejection.
基金the National Natural Science Foundation of China (No.60375001,60775047,60402024).
文摘This paper proposes a novel excitation controller using support vector machines (SVM) and approximate models. The nonlinear control law is derived directly based on an input-output approximation method via Taylor expansion, which not only avoids complex control development and intensive computation, but also avoids online learning or adjustment. Only a general SVM modelling technique is involved in both model identification and controller implementation. The robustness of the stability is rigorously established using the Lyapunov method. Several simulations demonstrate the effectiveness of the proposed excitation controller.
基金Project(60910005)supported by the National Natural Science Foundation of China
文摘A learning controller of nonhonolomic robot in real-time based on support vector machine(SVM)is presented.The controller includes two parts:one is kinematic controller based on nonlinear law,and the other is dynamic controller based on SVM.The kinematic controller is aimed to provide desired velocity which can make the steering system stable.The dynamic controller is aimed to transform the desired velocity to control torque.The parameters of the dynamic system of the robot are estimated through SVM learning algorithm according to the training data of sliding windows in real time.The proposed controller can adapt to the changes in the robot model and uncertainties in the environment.Compared with artificial neural network(ANN)controller,SVM controller can converge to the reference trajectory more quickly and the tracking error is smaller.The simulation results verify the effectiveness of the method proposed.
基金Project (No. 2003 AA517020) supported by the Hi-Tech Researchand Development Program (863) of China
文摘This paper describes a nonlinear model predictive controller for regulating a molten carbonate fuel cell (MCFC). In order to improve MCFC’s generating performance, prolong its life and guarantee safety, it must be controlled efficiently. First, the output voltage of an MCFC stack is identified by a least squares support vector machine (LS-SVM) method with radial basis function (RBF) kernel so as to implement nonlinear predictive control. And then, the optimal control sequences are obtained by applying genetic algorithm (GA). The model and controller have been realized in the MATLAB environment. Simulation results indicated that the proposed controller exhibits satisfying control effect.
文摘In this paper, a nonlinear model predictive control strategy which utilizes a probabilistic sparse kernel learning technique called relevance vector regression (RVR) and particle swarm optimization with controllable random exploration velocity (PSO-CREV) is applied to a catalytic continuous stirred tank reactor (CSTR) process. An accurate reliable nonlinear model is first identified by RVR with a radial basis function (RBF) kernel and then the optimization of control sequence is speeded up by PSO-CREV. Additional stochastic behavior in PSO-CREV is omitted for faster convergence of nonlinear optimization. An improved system performance is guaranteed by an accurate sparse predictive model and an efficient and fast optimization algorithm. To compare the performance, model predictive control (MPC) using a deterministic sparse kernel learning technique called Least squares support vector machines (LS-SVM) regression is done on a CSTR. Relevance vector regression shows improved tracking performance with very less computation time which is much essential for real time control.
文摘设计了自适应逆控制的永磁同步电机(PMSM)控制系统,控制系统采用双闭环结构的矢量控制,将自适应逆控制方法引入速度控制。运用非线性自适应滤波器,实现系统的建模与逆建模,并引入滤波器构成了速度控制器,采用最小均方差(Least Mean Square,LMS)自适应滤波算法在线调整其权函数,实现速度的精确控制。在基于DSP的永磁同步电机速度控制系统平台上的实验结果表明,非线性滤波器能够建立电流环模型,提出的非线性自适应逆控制方法能够实现精确的速度控制。与PID控制方法相比,具有更精确的速度跟踪性及更快的响应速度。