期刊
NEUROCOMPUTING
卷 174, 期 -, 页码 643-650出版社
ELSEVIER SCIENCE BV
DOI: 10.1016/j.neucom.2015.09.081
关键词
Support vector machine; Fault monitoring and diagnosis; Survey
With the advancement of industrial systems, fault monitoring and diagnosis methods based on the data-driven attract much attention in recent years. This kind of methods are widely used in engineering projects, especially in those big and complicated machines, whose conditions are difficult to obtain from straight view. They can provide the administrator with effective fault information in initial phase and therefore reduce the loss caused by faults. This paper reviews the research and development of fault diagnosis and monitoring approach based on support vector machine (SVM). While many other methods, such as expert system and artificial neural network, have been used in fault monitoring and diagnosis, SVM shows its advantage in generalization performance and in case of small sample. Therefore, it should attract more attention. (C) 2015 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据