Fault detection and diagnosis in process data using one-class support vector machines
Fault detection and diagnosis in process data using one-class support vector machines
复制标题
DOI：
10.1016/j.jprocont.2009.07.011
复制
发表时间：
2009-12-01
影响因子：
4.2
通讯作者：
Shah, Sirish L.
中科院分区：
文献类型：
--
作者：
Mahadevan, Sankar;Shah, Sirish L.
提出了一种基于单类支持向量机的故障检测与诊断方法。该方法是基于在特征空间中测量的非线性距离度量。正如在主成分分析（PCA）和动态主成分分析（DPCA）中一样，已经开发了用于故障检测的适当的距离度量和阈值。故障诊断，然后进行使用SVM递归特征消除（SVM-RFE）的特征选择方法。该方法的有效性证明了它的基准田纳西伊士曼问题和工业实时半导体蚀刻工艺数据集。该算法已与传统的技术，如PCA和DPCA的性能指标，如虚警率，检测延迟和故障检测率。结果表明，该算法在故障检测和诊断方面均优于PCA和DPCA。(C)2009年由Elsevier Ltd.出版
In this paper, a new approach for fault detection and diagnosis based on One-Class Support Vector Machines (I-class SVM) has been proposed. The approach is based on a non-linear distance metric measured in a feature space. just as in principal components analysis (PCA) and dynamic principal components analysis (DPCA), appropriate distance metrics and thresholds have been developed for fault detection. Fault diagnosis is then carried out using the SVM-recursive feature elimination (SVM-RFE) feature selection method. The efficacy of this method is demonstrated by applying it on the benchmark Tennessee Eastman problem and on an industrial real-time Semiconductor etch process dataset. The algorithm has been compared with conventional techniques such as PCA and DPCA in terms of performance measures such as false alarm rates, detection latency and fault detection rates. It is shown that the proposed algorithm outperformed PCA and DPCA both in terms of detection and diagnosis of faults. (C) 2009 Published by Elsevier Ltd.