This paper presents a nonlinear model predictive control(NMPC) approach based on support vector machine(SVM) and genetic algorithm(GA) for multiple-input multiple-output(MIMO) nonlinear systems.Individual SVM is used ...This paper presents a nonlinear model predictive control(NMPC) approach based on support vector machine(SVM) and genetic algorithm(GA) for multiple-input multiple-output(MIMO) nonlinear systems.Individual SVM is used to approximate each output of the controlled plant Then the model is used in MPC control scheme to predict the outputs of the controlled plant.The optimal control sequence is calculated using GA with elite preserve strategy.Simulation results of a typical MIMO nonlinear system show that this method has a good ability of set points tracking and 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
In this paper, a support vector machine-based multi-model predictive control is proposed, in which SVM classification combines well with SVM regression. At first, each working environment is modeled by SVM regression ...In this paper, a support vector machine-based multi-model predictive control is proposed, in which SVM classification combines well with SVM regression. At first, each working environment is modeled by SVM regression and the support vector machine network-based model predictive control (SVMN-MPC) algorithm corresponding to each environment is developed, and then a multi-class SVM model is established to recognize multiple operating conditions. As for control, the current environment is identified by the multi-class SVM model and then the corresponding SVMN-MPC controller is activated at each sampling instant. The proposed modeling, switching and controller design is demonstrated in simulation results.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 model control based on TS-fuzzy support vector regression( TS-fuzzy SVR) for a quadrotor aircraft is developed. The TS-kernel is the product of linear combination of input and a cluster of output correspond...An inverse model control based on TS-fuzzy support vector regression( TS-fuzzy SVR) for a quadrotor aircraft is developed. The TS-kernel is the product of linear combination of input and a cluster of output corresponding to a cluster of TS-type fuzzy rules. The output of TS-fuzzy SVR is a linear weighted sum of the TSkernels. The dynamical model of the quad-rotor aircraft is derived. A new control scheme combined with TSfuzzy SVR inverse model control and PID control is presented so that the TS-fuzzy SVR inverse model control enhances capabilities of disturbance rejection and the robustness while the PID control enhances fast responsiveness and reliability of the system. Simulation results show the capabilities of the developed control for the attitude system of quad-rotor aircraft.展开更多
A new longitudinal speed control strategy is proposed. It used the lateral jerk information as the feedback to predict the longitudinal acceleration and deceleration, which is especially beneficial to a sharp curve tu...A new longitudinal speed control strategy is proposed. It used the lateral jerk information as the feedback to predict the longitudinal acceleration and deceleration, which is especially beneficial to a sharp curve turning at a high driving speed. The performance of the controller is validated with Matlab/Simulink. The simulation results indicate that compared with the traditional vehicle, the G-vector controller can reduce the turning radius and improve the vehicle stability and agility obviously. And the proposed longitudinal speed control strategy could trade-off the longitudinal and lateral acceleration by using the tire force during the turning.展开更多
电流源型脉宽调制(Pulse width modulation,PWM)整流器因其网侧存在LC滤波器,系统的控制难度增加。传统直接功率控制策略下的整流器功率波形存在脉动,因模型预测控制具有卓越的动态特性以及直观的控制规律,采用模型预测直接功率控制(Mod...电流源型脉宽调制(Pulse width modulation,PWM)整流器因其网侧存在LC滤波器,系统的控制难度增加。传统直接功率控制策略下的整流器功率波形存在脉动,因模型预测控制具有卓越的动态特性以及直观的控制规律,采用模型预测直接功率控制(Model predictive direct power control,MPDPC)对传统控制策略进行改进。首先建立了三相PWM整流器的数学模型,给出了每个采样周期内的功率变化率,并推导出相邻采样周期之间的功率关系,然后给出基于单矢量的模型预测直接功率控制策略,提出了基于双矢量的模型预测直接功率控制策略,并优选出两个电流矢量,计算在一个采样周期内的作用时间,并对其进行修正。最后,在Matlab/Simulink仿真软件验证了所提控制策略的可行性和有效性。展开更多
针对传统电压源逆变器无模型预测电流控制(model-free predictive current control,MFPCC)方法存在电流纹波大、电流梯度更新停滞以及预测性能易受采样扰动影响的问题。该文提出一种计及采样扰动的三矢量MFPCC方法。在一个控制周期应用...针对传统电压源逆变器无模型预测电流控制(model-free predictive current control,MFPCC)方法存在电流纹波大、电流梯度更新停滞以及预测性能易受采样扰动影响的问题。该文提出一种计及采样扰动的三矢量MFPCC方法。在一个控制周期应用3个基本矢量,并根据价值函数计算矢量作用时间,降低了输出电流纹波;其次,通过建立不同矢量作用下的电流梯度方程组,实现电流梯度数据的实时更新,消除了停滞现象;再次,分析采样扰动对MFPCC的影响,采用扩张状态观测器估计采样扰动以补偿预测电流控制,抑制其对输出电流的影响。最后,通过仿真和实验,对所提方法的有效性进行了验证。展开更多
针对传统永磁同步电机(permanent magnet synchronous motor,PMSM)三矢量模型预测电流控制(three-vector model predictive current control,TV-MPCC)存在开关频率不固定和计算复杂的问题,提出一种固定开关频率TV-MPCC策略。利用前一周...针对传统永磁同步电机(permanent magnet synchronous motor,PMSM)三矢量模型预测电流控制(three-vector model predictive current control,TV-MPCC)存在开关频率不固定和计算复杂的问题,提出一种固定开关频率TV-MPCC策略。利用前一周期的零电压矢量和参考电压矢量所在扇区来快速筛选所需最优电压矢量和次优电压矢量,避免了无效枚举计算,从而降低了开关频率和计算复杂度。引入系统d和q轴电流差参数,计算各电压矢量的作用时间,确保电压矢量作用时间恒大于零和开关频率固定。以三相两电平电压型逆变器驱动的表贴式PMSM为被控对象,通过仿真和实验对传统TV-MPCC策略和所提三矢量固定开关频率模型预测电流控制策略进行对比研究,仿真和实验结果表明,所提策略在保证系统稳态和动态性能的基础上,在固定和降低开关频率的同时,降低了计算复杂度。展开更多
在五相永磁同步电机(permanent-magnet synchronous motor,PMSM)中,有限集模型预测容错控制(finite control set model predictive fault tolerant control,FCS-MPFTC)存在计算量大、电流谐波含量高等问题。因此,该文提出一种简化FCS-MP...在五相永磁同步电机(permanent-magnet synchronous motor,PMSM)中,有限集模型预测容错控制(finite control set model predictive fault tolerant control,FCS-MPFTC)存在计算量大、电流谐波含量高等问题。因此,该文提出一种简化FCS-MPFTC来实现相开路和短路故障情况下的统一容错控制。首先,将模型预测电流控制的电流代价函数等效转化为电压代价函数,并采用无差拍方法通过电流模型计算出参考电压。然后,基于抑制三次谐波电流为0的原则合成虚拟电压矢量(virtual voltage vector,V^(3));通过重构V^(3)和扇区,以直接获得参考电压矢量对应的最优电压矢量。最后,对传统和简化FCS-MPFTC在开路和短路故障下进行对比实验。结果表明,所提策略能够有效减小故障后计算量、转矩脉动以及电流谐波含量。展开更多
基金Supported by the National Natural Science Foundation of China(21076179)the National Basic Research Program of China(2012CB720500)
文摘This paper presents a nonlinear model predictive control(NMPC) approach based on support vector machine(SVM) and genetic algorithm(GA) for multiple-input multiple-output(MIMO) nonlinear systems.Individual SVM is used to approximate each output of the controlled plant Then the model is used in MPC control scheme to predict the outputs of the controlled plant.The optimal control sequence is calculated using GA with elite preserve strategy.Simulation results of a typical MIMO nonlinear system show that this method has a good ability of set points tracking and 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the 973 Program of China (No.2002CB312200)the National Science Foundation of China (No.60574019)
文摘In this paper, a support vector machine-based multi-model predictive control is proposed, in which SVM classification combines well with SVM regression. At first, each working environment is modeled by SVM regression and the support vector machine network-based model predictive control (SVMN-MPC) algorithm corresponding to each environment is developed, and then a multi-class SVM model is established to recognize multiple operating conditions. As for control, the current environment is identified by the multi-class SVM model and then the corresponding SVMN-MPC controller is activated at each sampling instant. The proposed modeling, switching and controller design is demonstrated in simulation results.
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.
基金Sponsored by the Science and Technology Support Program of Jiangsu Province(Grant No.SBE2014070836)
文摘An inverse model control based on TS-fuzzy support vector regression( TS-fuzzy SVR) for a quadrotor aircraft is developed. The TS-kernel is the product of linear combination of input and a cluster of output corresponding to a cluster of TS-type fuzzy rules. The output of TS-fuzzy SVR is a linear weighted sum of the TSkernels. The dynamical model of the quad-rotor aircraft is derived. A new control scheme combined with TSfuzzy SVR inverse model control and PID control is presented so that the TS-fuzzy SVR inverse model control enhances capabilities of disturbance rejection and the robustness while the PID control enhances fast responsiveness and reliability of the system. Simulation results show the capabilities of the developed control for the attitude system of quad-rotor aircraft.
基金Supported by the National Nature Science Foundation of China(5137504651205021)
文摘A new longitudinal speed control strategy is proposed. It used the lateral jerk information as the feedback to predict the longitudinal acceleration and deceleration, which is especially beneficial to a sharp curve turning at a high driving speed. The performance of the controller is validated with Matlab/Simulink. The simulation results indicate that compared with the traditional vehicle, the G-vector controller can reduce the turning radius and improve the vehicle stability and agility obviously. And the proposed longitudinal speed control strategy could trade-off the longitudinal and lateral acceleration by using the tire force during the turning.
文摘电流源型脉宽调制(Pulse width modulation,PWM)整流器因其网侧存在LC滤波器,系统的控制难度增加。传统直接功率控制策略下的整流器功率波形存在脉动,因模型预测控制具有卓越的动态特性以及直观的控制规律,采用模型预测直接功率控制(Model predictive direct power control,MPDPC)对传统控制策略进行改进。首先建立了三相PWM整流器的数学模型,给出了每个采样周期内的功率变化率,并推导出相邻采样周期之间的功率关系,然后给出基于单矢量的模型预测直接功率控制策略,提出了基于双矢量的模型预测直接功率控制策略,并优选出两个电流矢量,计算在一个采样周期内的作用时间,并对其进行修正。最后,在Matlab/Simulink仿真软件验证了所提控制策略的可行性和有效性。
文摘针对传统电压源逆变器无模型预测电流控制(model-free predictive current control,MFPCC)方法存在电流纹波大、电流梯度更新停滞以及预测性能易受采样扰动影响的问题。该文提出一种计及采样扰动的三矢量MFPCC方法。在一个控制周期应用3个基本矢量,并根据价值函数计算矢量作用时间,降低了输出电流纹波;其次,通过建立不同矢量作用下的电流梯度方程组,实现电流梯度数据的实时更新,消除了停滞现象;再次,分析采样扰动对MFPCC的影响,采用扩张状态观测器估计采样扰动以补偿预测电流控制,抑制其对输出电流的影响。最后,通过仿真和实验,对所提方法的有效性进行了验证。
文摘针对传统永磁同步电机(permanent magnet synchronous motor,PMSM)三矢量模型预测电流控制(three-vector model predictive current control,TV-MPCC)存在开关频率不固定和计算复杂的问题,提出一种固定开关频率TV-MPCC策略。利用前一周期的零电压矢量和参考电压矢量所在扇区来快速筛选所需最优电压矢量和次优电压矢量,避免了无效枚举计算,从而降低了开关频率和计算复杂度。引入系统d和q轴电流差参数,计算各电压矢量的作用时间,确保电压矢量作用时间恒大于零和开关频率固定。以三相两电平电压型逆变器驱动的表贴式PMSM为被控对象,通过仿真和实验对传统TV-MPCC策略和所提三矢量固定开关频率模型预测电流控制策略进行对比研究,仿真和实验结果表明,所提策略在保证系统稳态和动态性能的基础上,在固定和降低开关频率的同时,降低了计算复杂度。
文摘在五相永磁同步电机(permanent-magnet synchronous motor,PMSM)中,有限集模型预测容错控制(finite control set model predictive fault tolerant control,FCS-MPFTC)存在计算量大、电流谐波含量高等问题。因此,该文提出一种简化FCS-MPFTC来实现相开路和短路故障情况下的统一容错控制。首先,将模型预测电流控制的电流代价函数等效转化为电压代价函数,并采用无差拍方法通过电流模型计算出参考电压。然后,基于抑制三次谐波电流为0的原则合成虚拟电压矢量(virtual voltage vector,V^(3));通过重构V^(3)和扇区,以直接获得参考电压矢量对应的最优电压矢量。最后,对传统和简化FCS-MPFTC在开路和短路故障下进行对比实验。结果表明,所提策略能够有效减小故障后计算量、转矩脉动以及电流谐波含量。