一种基于ICA-SVM的故障诊断方法

来源期刊：中南大学学报(自然科学版)2003年第4期

论文作者：郭明 谢磊 何宁 王树青

文章页码：447 - 450

关键词：支撑向量机;过程监控;故障诊断

Key words：support vector machine; process monitoring; fault diagnosis

摘    要：提出了一种基于独立分量分析和支撑向量机(ICA-SVM)对系统性能进行监控的整体框架.这一框架包括特征提取和故障识别两部分.独立分量分析被用于从当前工况的数据矩阵中提取出代表当前工况特征的投影系数矩阵,而这些投影系数矩阵则被用于训练多个支撑向量机,以实现故障类型的识别.Tennessee Eastman过程的仿真结果证明了该算法的有效性.

Abstract: A chemical process has a large number of measured variables, but it is usually driven by fewer essential ariables, which may not be measured. Extracting these essential variables and monitoring them will improve he process monitoring performance. In this paper, an integrated framework for process monitoring and fault diagnosis is presented, which combines independent component analysis (ICA) for feature extraction and support vector machine (SVM) for identification of different fault sources. ICA is used to determine the projection coefficient matrix which represents the features characterizing the current operation condition. Multiple support vector machines are trained and use the coefficient matrix as their inputs to identify the faults. The method is proved to be effective by the application to monitoring Tennessee Eastman process.