基于神经网络的三容水箱容错控制仿真研究  

Simulation Research on Fault-Tolerant Control of Three Tank Based on Neural Network

作　　者：赵峻 郭一楠 ZHAO Jun;GUO Yi-nan(Teaching Demonstration Center of Electrical and Electronic Technology,China University of Mining and Technology,Xuzhou Jiangsu 221116,China)

机构地区：[1]中国矿业大学信息与控制工程学院,江苏徐州221116

出　　处：《计算机仿真》2025年第3期381-385,543,共6页Computer Simulation

摘　　要：随着现代工程控制系统的大规模、复杂化,容错控制受到越来越多专家和学者的重视。针对过程控制实验中常用的三容水箱,考虑水箱泄露故障,应用神经网络构建系统的回归模型,根据实时输出与回归模型残差判断故障,并应用自适应控制中的自校正神经网络PID构建容错控制器,实现在系统故障状态下,根据系统参数变化,动态调节系统输入,实现系统故障下的稳定容错控制。仿真结果表明,所提方法能够有效地克服系统故障,在不降低系统性能指标的情况下安全地完成控制任务。With the large-scale and complex development of modern engineering control systems,fault-tolerant control has received increasing attention from experts and scholars.In view of the three-tank water tank commonly used in process control experiment,considering the leakage fault of the water tank,the neural network is used to construct the regression model of the system and judge the fault according to the real-time output and the residual error of the regression model,the self-tuning neural network PID controller is used to build the fault-tolerant controller,which can dynamically adjust the input of the system according to the change of the system parameters under the state of system failure,stable fault-tolerant control under system failure is realized.The simulation results show that the proposed method can effectively overcome the system fault and safely complete the control task without reducing the system performance index.

关 键 词：三容水箱 泄露故障 容错控制 神经网络 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]