论文部分内容阅读
提出了一种可适用于非线性过程控制系统的故障诊断方法。该方法由推广卡尔曼滤波器和人工神经网络两部分组成，其中：推广卡尔曼滤波器用于对过程系统的状态估计，而人工神经网络则用于对这些估计量进行分析、分类处理工作，并指出该系统是否处于故障状态，若处于故障状态，它还能确定故障的类型、强度和位置。最后，本文将这一方法应用到了谷氨酸发酵过程控制系统的故障诊断之中，并给出了实验研究结果。
A fault diagnosis method suitable for nonlinear process control system is proposed. The method consists of two parts: the extended Kalman filter and the artificial neural network. Among them, the extended Kalman filter is used to estimate the state of the process system, while the artificial neural network is used to analyze and classify these estimators. Indicate whether the system is in a fault state or not, and if it is in a fault state, it can also determine the type, intensity, and location of the fault. Finally, this paper applies this method to the fault diagnosis of glutamic acid fermentation process control system, and gives the experimental results.