基于rs与ls-svm多分类法的故障诊断方法及其应用-中南大学学报.pdfVIP

40 2 ( ) Vol.40 No.2 2009 4 Journal of Central South University (Science and Technology) Apr. 2009 RS LS-SVM 1, 2 1 1 1 (1. 410083 2. 512024) (RS) (LS-SVM)RS 90% TP277 A 1672−7207(2009)02−0447−05 Fault diagnosis method based on rough set and least squares support vector machine and its application 1, 2 1 1 1 JIANG Shao-hua , GUI Wei-hua , YANG Chun-hua , DAI Xian-jiang (1. School of Information Science and Engineering, Central South University, Changsha 410083, China; 2. School of Computer Science, Shaoguan University, Shaoguan 512024, China) Abstract Aiming at the complex and variable reaction of Pb-Zn smelting in imperial smelting furnace (ISF), a novel method for the furnace fault diagnosis based on rough set (RS) and least squares support vector machine(LS-SVM) was put forward. According to the method, the original fault examples were reduced by using the rough set theory to get a simple rule collection as eigenvectors, and then these eigenvectors were input into multiple fault classifiers of LS-SVM to identify faults. The experimental results show that the method has better classification performance and its classification precision reaches more than 90%. Key words: rough set(RS); least squares support vector machine(LS-SVM); multi-class classifiers; fault diagnosis [1−2] [4−6] (Least squares support vector machineLS-SVM)SVM (Support [7−9]SVM vector machineSVM)Vapnik