基于一种继承模型的多变量非线性预测控制

提出了一种由人工神经网络与线性ＡＲＸ模型相结合的集成模型，给出了其辨识训练方法。以此模型为基础，提出了一种多变量非线性预测控制算法。它利用线性预测控制的成果，得到一解析式的非线性优化控制输入，避免了通常非线性模型（包括普通人工神经网络模型）预测控制所需的在线数值寻优计算，节约了在线计算时间。提高了算法的可靠性和稳定性。进一步给出了在ＣＳＴＲ反应器上的仿真实验结果。

Multivariable Nonlinear Predictive Control Based on an Integrating Model

An integrating model combining the artificial neural network with the linear ARX model and its identification method is proposed.Based on that model,a multivariable nonlinear predictive control algorithm is persented.The algorithm employs the result of the linear predictive control,obtains explicit nonlinear optimal controlling inputs and doesn't need on line numerical optimizing which is necessary in general nonlinear model (including ANN model) predictive control.That greatly decreases on line computing consumption,strengthens the reliability of the algorithm and the stability of the system.The simulation results in CSTR are shown.