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
给出一种最小二乘支持向量机(Least Square Support Vector Machine,LS-SVM)广义逆内模控制方法。利用LS-SVM辨识这类系统的广义逆,再与原被控系统串联成具有近线性伪线性的开环控制系统,引入内模控制使其变成稳定的闭环控制回路,将这...给出一种最小二乘支持向量机(Least Square Support Vector Machine,LS-SVM)广义逆内模控制方法。利用LS-SVM辨识这类系统的广义逆,再与原被控系统串联成具有近线性伪线性的开环控制系统,引入内模控制使其变成稳定的闭环控制回路,将这种方法应用在球磨机控制系统中。经仿真分析,该方法不依赖于被控系统精确的数学模型,实现了小样本训练的准确辨识,提高了系统的动态响应,并与内模控制相结合,使其闭环控制系统鲁棒稳定性增强。展开更多
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.
文摘给出一种最小二乘支持向量机(Least Square Support Vector Machine,LS-SVM)广义逆内模控制方法。利用LS-SVM辨识这类系统的广义逆,再与原被控系统串联成具有近线性伪线性的开环控制系统,引入内模控制使其变成稳定的闭环控制回路,将这种方法应用在球磨机控制系统中。经仿真分析,该方法不依赖于被控系统精确的数学模型,实现了小样本训练的准确辨识,提高了系统的动态响应,并与内模控制相结合,使其闭环控制系统鲁棒稳定性增强。
