基于双重控制策略的故障检测方法  

Fault Detection Method Based on Dual Control Strategy

作　　者：刘晓强 李飞 李雨婷[1] LIU Xiaoqiang;LI Fei;LI Yuting(School of Electrical&Information Engineering,Anhui University of Technology,Maanshan 243032,China;Anhui Province Engineering Laboratory of Intelligent Demolition Equipment,Anhui University of Technology,Maanshan 243032,China;Anhui Key Laboratory of Special Heavy Haul Robots,Anhui University of Technology,Maanshan 243032,China)

机构地区：[1]安徽工业大学电气与信息工程学院,安徽马鞍山243032 [2]安徽工业大学安徽省智能破拆装备工程实验室,安徽马鞍山243032 [3]安徽工业大学安徽省特种重载机器人重点实验室,安徽马鞍山243032

出　　处：《安徽工业大学学报（自然科学版）》2024年第1期58-64,共7页Journal of Anhui University of Technology（Natural Science）

基　　金：国家自然科学基金项目(61903003);安徽省智能破拆装备工程实验室开放基金资助项(APELIDE2022A007);安徽省特种重载机器人重点实验室开放项目(TZJQR001–2021);安徽省高校科研计划项目(KJ2019A0051);安徽省自然科学基金青年项目(2008085QE227)。

摘　　要：针对复杂工业过程中变量故障信息统计不完全和故障检测性能不佳的问题,提出一种基于双重控制策略的故障检测方法。对输入数据进行标准化处理并获得数据的偏差变量来揭示数据的故障信息,实现第一重控制;对偏差变量进行处理生成新的辅助监控统计量,实现第二重控制;针对辅助监控统计量阈值难以确定的现象,基于一种反馈调节的参数自适应策略设置阈值。使用提出的方法对田纳西伊斯曼过程(TE过程)进行故障检测,且与改进欧氏距离控制(IEDC)和传统主成分分析(PCA)的故障检测方法进行比较验证。结果表明:与IEDC和PCA方法相比,所提方法能监控TE过程中变量更多的故障信息,在多组类型的故障检测中具有更高的故障检测率与较低的误报率,可有效应用于复杂的工业过程。A fault detection method based on dual control strategy was proposed to address the issue of incomplete statistics of variable fault information and poor fault detection performance in complex industrial processes.The input data was standardized and the deviation variables were obtained to reveal fault information and achieve first level control.The deviation variables were processed to generate new auxiliary monitoring statistics,achieving secondary control.A parameter adaptive method based on feedback adjustment was adopted to set the threshold for the difficulty in determining the threshold of auxiliary monitoring statistics.The proposed method was used to detect faults of the Tennessee Eastman process(TE process),and was compared and validated with the fault detection methods of the improved Euclidean distance control(IEDC)and traditional principal component analysis(PCA)method.The results show that compared with the IEDC and PCA methods,the proposed method can monitor more fault information of variables in the TE process,and has a higher fault detection rate and lower false alarm rate in fault detection of multiple types,which can be effectively applied to complex industrial processes.

关 键 词：偏差变量 双重控制 故障检测率 误报率 TE过程 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置]