Online fault diagnosis method based on Incremental Support Vector Data Description and Extreme Learning Machine with incremental output structure
Online fault diagnosis method based on Incremental Support Vector Data Description and Extreme Learning Machine with incremental output structure
复制标题
DOI：
10.1016/j.neucom.2013.01.061
复制
发表时间：
2014-03
期刊：
影响因子：
6
通讯作者：
Gang Yin;Yingtang Zhang;Zhining Li;Guoquan Ren;Hongbo Fan
中科院分区：
文献类型：
--
作者：
Gang Yin;Yingtang Zhang;Zhining Li;Guoquan Ren;Hongbo Fan
在线故障诊断系统应能真实的实时地检测故障、识别故障类型并自动更新自身的判别能力和知识。但故障诊断中的类数不是常数，而是随着新成员的加入而处于动态变化的。当故障模式类别数增加时，传统的识别算法不能有效地更新诊断系统。针对这一问题，提出了一种基于增量支持向量数据描述（ISVDD）和增量输出结构极限学习机（IOELM）的在线故障诊断方法。ISVDD用于设备连续状态监测中快速发现新的故障模式。将极限学习机的固定结构转化为一种弹性结构，其输出节点可以增量式增加，从而有效地识别新的故障模式。对柴油机11种不同工况的识别实验表明，基于ISVDD和IOELM的在线故障诊断方法效果良好，该方法在其他机械设备的故障诊断中也是可行的。
Online fault diagnosis system should be able to detect faults, recognize fault types and update the discriminating ability and knowledge of itself automatically in real time. But the class number in fault diagnosis is not constant and it is in a dynamic state with new members enrolled. The traditional recognition algorithms are not able to update diagnosis system efficiently when the class number of failure modes is increasing. To solve the problem, an online fault diagnosis method based on Incremental Support Vector Data Description (ISVDD) and Extreme Learning Machine with incremental output structure (IOELM) is proposed. ISVDD is used to find a new failure mode quickly in the continuous condition monitoring of the equipments. The fixed structure of Extreme Learning Machine is changed into an elastic structure whose output nodes could be added incrementally to recognize the new fault mode efficiently. Recognition experiments on the diesel engine under eleven different conditions show that the online fault diagnosis method based on ISVDD and IOELM works well, and the method is also feasible in fault diagnosis of other mechanical equipments.