多输入多输出非线性系统的最小二乘支持向量机广义逆控制

Least squares support vector machines generalized inverse control for a class of multi-input and multi-output nonlinear systems

中文关键词  非线性系统  广义逆  辨识  最小二乘支持向量机  双电机变频调速系统

英文关键词  nonlinear systems  generalized inverse  identification  least squares support vector machines  two-motor variable-frequency speed-regulating system

中文摘要

      针对神经网络逆控制存在的不足, 对一类模型未知且某些状态量较难测得的多输入多输出(MIMO)非线性系统, 在状态软测量函数存在的前提下, 提出一种最小二乘支持向量机(LSSVM)广义逆辨识控制策略. 通过广义逆将原被控系统转化为伪线性复合系统, 并可使其极点任意配置, 采用LSSVM代替神经网络拟合广义逆系统中的静态非线性映射. 将系统的状态量辨识与LSSVM逆模型辨识结合, 通过LSSVM训练拟合同时实现软测量功能. 最后以双电机变频调速系统为对象, 采用该控制策略进行仿真研究, 结果验证了本文算法的有效性.

英文摘要

      Considering the deficiency of neural network inverse control method, for a class of multi-input and multioutput (MIMO) nonlinear systems with unknown model, when soft-sensing functions for immeasurable states are available, we propose a new identification and control strategy based on the generalized inverse control of least squares support vector machines (LSSVM). The generalized inverse converts the controlled nonlinear system into a pseudo linear system with expected pole placement. In place of the neural network, LSSVM is employed to fit the static nonlinear mapping of the generalized inverse system. The identification of state variables is combined with the identification of LSSVM inverse model. Meanwhile, the soft-sensing is implemented through LSSVM training and fitting. Simulation is performed on a two-motor variable-frequency speed-regulating system. Results show that the proposed control strategy is feasible and efficient.