Canonical residual based incipient fault detection method for industrial process
作者单位：School of Electrical EngineeringNantong University School of ZhangJianNantong University
会议名称：《第32届中国控制与决策会议》
会议日期：2020年
学科分类：08[工学] 080401[工学-精密仪器及机械] 0804[工学-仪器科学与技术] 080402[工学-测试计量技术及仪器] 0838[工学-公安技术] 0802[工学-机械工程] 080201[工学-机械制造及其自动化]
关 键 词：Canonical residual statistics incipient fault fault detection rate
摘 要：Incipient faults with low amplitudes can be easily submerged by noise and process *** these faults can slowly evolve into the serious failure of processes,early detection is increasingly becoming *** monitor incipient faults more efficiently,canonical variate analysis with two statistics indices based on canonical residuals are proposed for monitoring dynamic ***,canonical variate can be obtained by performing singular value decomposition on the Hankel matrix,which assembles with covariance and cross-covariance matrices of the past and future ***,the canonical residual can be generated by calculating the difference between projected past data and projected future ***,two weighted average statistics based on canonical residual and its control limit can be ***,with the application in the continuous stirred tank reactor(CSTR) process,the performance of the proposed detection method is verified by comparing with fault detection *** results indicate those two weighted average statistics based on canonical residual can improve the fault detection rates compared with the conventional statistics T and Q.