遗传算法在间歇式反应釜故障诊断中的应用  

Application of Genetic Algorithm to Batch Reactor Fault Diagnosis

作　　者：宋彤[1] 齐瑞勤[1] 

机构地区：[1]大连理工大学控制科学与工程学院,辽宁大连116023

出　　处：《计算机仿真》2012年第7期218-222,共5页Computer Simulation

摘　　要：间歇式反应过程是一种重要的化工生产过程,过程自身的非线性、时滞性和不确定性等因素决定了过程操作的复杂性和危险性。随着精细化工和生物制药等工业中设备的大型化和集成化发展,不断提升了间歇式反应过程故障诊断的重要性。提出了一种改进的遗传算法优化BP神经网络的故障诊断方法。利用提取反应釜的故障特征数据,采用改进的遗传算法优化BP神经网络的权值和阈值,然后利用优化后的BP神经网络训练故障特征数据,建立故障诊断模型,输出诊断结果。应用于间歇式反应釜温度故障诊断,仿真结果表明,改进算法能够提高故障诊断精度、缩短故障诊断时间,具有良好的实用效果。The process of intermittent reaction is an important chemical production process. The nonlinear, time lag and uncertainty factors determine the complexity and the risk of operation process. The large-scale and integrated development of industrial equipment promotes the importance of intermittent reaction process＇ s fault diagnosis. This paper presented a method based on BP neural network optimized by improved genetic algorithm. The extractive fault data and improved genetic algorithm were used to optimize the weights and thresholds of BP neural network. Then we used the optimized BP neural network to train the fault data and established a fault diagnosis model. We used the al- gorithm in temperature fault diagnosis of batch reactor. The simulation results prove that the algorithm can improve the accuracy and shorten the fault diagnosis time. It has a good practical effect.

关 键 词：间歇式反应过程 故障诊断 神经网络 遗传算法 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]