生产过程早期故障检测与诊断的一种新方法

在分析了生产过程两类故障的特点和常规故障诊断方法的缺陷基础上,提出了生产过程早期故障检测与诊断方法,利用故障发生过程系统中相关变量或征兆信息之间的解析冗余关系,将它们的动态趋势信息通过人工神经网络进行融合,将它们的动态趋势信息通过人工神经网络进行融合,避免了常规方法故障检测与诊断的滞后性。

A NOVEL METHOD OF EARLY FAULT DETECTION AND DIAGNOSIS FOR TECHNICAL PROCESS

Based on the analysis ofcharacteristics of two classes of technical process fault and defects of two familiarfault detection and diagnosis methods , this paper introduced an early fault detection anddiagnosis method for technical process. Taking advantage of quatitative redundantrelationship of some dependent variables or symptoms in the process system after faulthappened , the method avoid the lag which often appeared in familiar fault detection anddiagnosis methods by utilization of dynamic tread information of the variables or symptomswhich is fused through artificial neural network. Theoretical analysis and simulationexamples demonstrated that this method could achieve early fault detection and diagnosisfor technical process.