论文部分内容阅读
为了提高毛细管流变仪加热腔温度控制效果,在研究以多变量、交叉耦合为特征的控制对象的基础上,给出了一种神经网络内模控制算法。以通过学习得到的动态神经网络作为内部模型,将直接逆系统学习法得到的神经网络作为控制器,构造了MIMO控制系统。介绍了毛细管流变仪温度控制系统软、硬件的开发。实际运行结果表明,该系统控制精度高,鲁棒性好,可靠性高。
In order to improve the temperature control effect of capillary rheometer heating chamber, an internal model control algorithm based on neural network is proposed based on the study of multi-variable and cross-coupled control objects. Taking the dynamic neural network obtained by learning as the internal model and the neural network obtained by the direct inverse system learning method as the controller, a MIMO control system is constructed. Introduced the capillary rheometer temperature control system software and hardware development. The actual operation results show that the system has high control accuracy, good robustness and high reliability.