基于证据理论与不精确概率的振动故障诊断  

Fault diagnosis of vibration based on evidence theory and imprecise probability

作　　者：王晶晶[1] 梁青[1] WANG Jing-jing;LIANG Qing(Department of Automation, University of Science and Technology of China, Hefei 230027, Chin)

机构地区：[1]中国科学技术大学自动化系,安徽合肥230027

出　　处：《传感器与微系统》2018年第6期108-111,共4页Transducer and Microsystem Technologies

基　　金：中央高校基本科研业务费专项资金资助项目(WK2100100017)

摘　　要：针对系统中振动发散类故障,提出了基于证据理论与不精确概率的诊断监测方法。利用不同传感器采集系统中的信号获取特征参数;以指数函数为证据生成函数对其处理得到故障基本信度分配,依据其大小分为高信度组与低信度组,分别采用Dempster组合规则进行融合,以融合的结果构成概率区间,计算诊断价值函数的期望区间;以不精确概率理论下2种不同决策准则决策是否发生故障。在隔振平台上实现了融合诊断监测过程,结果表明:提出的方法可以有效融合传感器信息、及时发现振动发散故障。A fault diagnosis monitoring method based on evidence theory and imprecise probabilities is proposed for vibration divergence fault in systems. Signals acquired by multi-sensors are used to obtain characteristic parameters. Basic belief assignments of fault are obtained by using exponential function as evidence generating function,and they are divided into two groups,which are high reliability group and low reliability group,and fused by Dempster combination rule respectively, the fused results make up probabilily interval,and calculate expectation interval which diagnose cost functions. Two different decision criterion under imprecise probability theory are used to decide whether fault is happened. The fusion diagnosis monitoring process is realized on platform of vibration isolation. The experimental results show that the proposed method can fuse information of sensor effectively and find vibration divergence fault in time.

关 键 词：振动发散 不精确概率 证据理论 故障诊断 多传感器 信息融合 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置]