Fault diagnosis of spur gearbox based on random forest and wavelet packet decomposition

作     者：Diego CABRERA Fernando SANCHO Rene-Vinicio SANCHEZ Grover ZURITA Mariela CERRADA Chuan LI Rafael E. VASQUEZ 

作者机构：Departamento de Ingenieria Mecainica Universidad Politecnica Salesiana Cuenca Ecuador Departamento de Ciencias de la Computaci6n e Inteligencia ArtificialUniversidad de Sevilla Espafia Departamento de Ingenieria Electro-Mechnica Universidad PrivadaBoliviana Cochabamba Bolivia Departamento de Sistemas de Control Universidad de Los AndesM6rida Venezuela Research Center of System Health Maintenance Chongqing Technologyand Business University Chongqing 400067 China Facultad de Ingenieria Mecainica Universidad Pontificia BolivarianaMedellln Colombia 

出 版 物：《Frontiers of Mechanical Engineering》 (机械工程前沿（英文版）)

年 卷 期：2015年第10卷第3期

页      面：277-286页

核心收录：

学科分类：0711[理学-系统科学] 090704[农学-森林经理学] 0907[农学-林学] 07[理学] 08[工学] 080401[工学-精密仪器及机械] 09[农学] 0804[工学-仪器科学与技术] 080402[工学-测试计量技术及仪器] 

基　　金：the Prometeo Project from the same institution  and the Project TIC-6064 from Junta de Andalucia (Spain) 

主　　题：fault diagnosis spur gearbox wavelet packet decomposition random forest 

摘      要：This paper addresses the development of a random forest classifier for the muki-class fault diagnosis in spur gearboxes. The vibration signal＇s condition parameters are first extracted by applying the wavelet packet decomposition with multiple mother wavelets, and the coefficients＇ energy content for terminal nodes is used as the input feature for the classification problem. Then, a study through the parameters＇ space to find the best values for the number of trees and the number of random features is performed. In this way, the best set of mother wavelets for the application is identified and the best features are selected through the internal ranking of the random forest classifier. The results show that the proposed method reached 98.68% in classification accuracy, and high efficiency and robustness in the models.