定值和随动单闭环系统传感器故障诊断  

Sensor fault diagnosis of fixed value and servo single closed-loop system

作　　者：那文波 高宇 李明 刘甜甜 NA Wen-bo;GAO Yu;LI Ming;LIU Tian-tian(College of Mechanical and Electrical Engineering,China University of Metrology,Hangzhou Zhejiang 310000,China)

机构地区：[1]中国计量大学机电工程学院,浙江杭州310000

出　　处：《控制理论与应用》2020年第9期2054-2060,共7页Control Theory & Applications

基　　金：浙江省自然科学基金委公益技术应用工业领域项目(LGG20F030005)资助。

摘　　要：在线闭环系统传感器的故障,由于控制器的调节作用,使得其故障诊断变得复杂.本文针对定值和随动单闭环系统传感器故障,在正常系统和故障系统动态特性分析基础上,提出了一种基于系统动态趋势和数据驱动的故障诊断方法.该方法利用动态窗口残差数据实现故障监测;以数据变化最大值实现故障估计;采用二次线性回归实现故障分离;建立了系统故障监测、故障估计和故障分离的静态模型;同时给出了诊断模型在线应用的标定方法和诊断流程.通过实验验证了方法的有效性和诊断的高精度.该方法适用于一般的一阶定值和随动闭环控制系统传感器的实时故障诊断.The fault of the sensor in the online closed-loop system is complicated due to the adjustment of the controller.Based on the analysis of dynamic characteristics of normal system and fault system,this paper proposes a fault diagnosis method based on dynamic trend and data-driven for sensor fault of fixed value and servo single closed-loop system.The method uses dynamic window residual data to implement fault monitoring;the maximum value of data changes is used to implement fault estimation;quadratic linear regression is used to implement fault separation;a static model of system fault monitoring,fault estimation,and fault separation is established.Meanwhile,the calibration method and diagnosis flow of online application of diagnosis model are given.The validity of the method and the high accuracy of diagnosis are verified by experiments.The method is suitable for real-time fault diagnosis of general first-order fixed value and servo closed-loop control system sensors.

关 键 词：动态特性 传感器 故障诊断 一阶定值系统 一阶随动系统 

分 类 号：TP212[自动化与计算机技术—检测技术与自动化装置] TP277[自动化与计算机技术—控制科学与工程]