中文摘要：

针对广义学习模型提出了基于PID结构的零极点配置解耦控制算法．广义学习模型由一个线性时变子模型和一个非线性学习模型组成，其中线性时变子模型的参数采用最小二乘方法进行辨识，非线性学习模型由RBF神经元网络近似．通过引入补偿多项式，使得闭环系统的零极点可任意配置，极大的改善了闭环系统的动态性能．在进行控制器参数选择时，PID结构部分参数可根据常规PID控制器选取，零极点配置部分参数可根据系统期望零极点选取．最后，通过对电弧炉电极调节系统的仿真，验证了控制器的有效性．

英文摘要：

A multivariable decoupling controller based on PID structure is proposed for generalized learning model （GLM）. The GLM assumes that the unknown complex plant is represented by an equivalent model consisting of a linear time varying sub model plus a nonlinear learning sub model. The parameters of the linear time varying sub model are identified by partial least squares （RLS） method and a RBF neural network is used to approximate the nonlinear learning sub model. The poles and zeros of the close-loop system can be assigned arbitrarily by a compensate polynomial, and the performance of the system can be improved greatly. In addition, the parameters of the PID structure can be selected according to the conventional PID controller and the parameters of the pole-zero section can be selected by the desired zeros and poles. At last, the effectiveness of the proposed controller is verified by the simulation results on the electrode regulator system.