Test Entrance’s Selection for Fault Diagnosis of a Self-propelled Fire Control System Based on TC-SVM

摘要：

Due to the complexity of the selfpropelled fire control system and the difficulty of test entrance’s selection, the support vector machine combined with text categorization method (TCSVM) is applied as the first step of fault diagnosis. The text pretreatment of text representation and feature extraction are introduced first. Then the errorcorrecting code is used to reduce the multiclass classifier to several binary classifiers which are performed by the support vector machine. Finally, the methods of how to combine the output of binary classifiers as the final diagnosis result is discussed, two improved algorithms are put forward based on the basic decoding method.

关键词： fire control system test entrance support vector machine text categorization

作者: Xiusheng DUAN Ganlin SHAN Qilong ZHANG Zining ZHANG

作者单位: Dept. of Optics and Electronic EngineeringOrdnance Engineering CollegeShijiazhuang 050003, Hebei Pro Dept. of Optics and Electronic Engineering Ordnance Engineering College Shijiazhuang 050003, Hebei P

会议类型: 国际会议

会议名称: 2010 2nd IEEE International Conference on Information Management and Engineering(2010年IEEE第二届信息管理与工程国际会议 IEEE ICIME 2010)

会议地点: 成都

会议语种:英文

页码: 1-4

在线出版日期: 2010-04-16（万方平台首次上网日期，不代表论文的发表时间）