Application of XGboost Algorithm in Bearing Fault Diagnosis

2nd International Symposium on Application of Materials Science and Energy Materials

材料科学;能源学

Zhang, Rongtao^1 ; Li, Binbin^1 ; Jiao, Bin^1

School of Electrical Engineering, Shanghai Dianji University, Shanghai, China^1

关键词: Bearing fault diagnosis;    Fast computation;    Gradient boosting;    Rolling bearings;    Tree algorithms;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/490/7/072062/pdf
DOI  :  10.1088/1757-899X/490/7/072062

学科分类：材料科学（综合）

来源: IOP

【 摘 要 】

This paper applies the XGboost(eXtreme Gradient Boosting) algorithm to the fault diagnosis of rolling bearing. XGboost is the realization of GBDT(gradient boosting decision tree). Generally speaking, the realization of GBDT(gradient boosting decision tree) is slow. XGBoost is characterized by fast computation and good performance of the model. At the end of this paper, we compare with other tree algorithms, and the results show that the XGboost algorithm is superior to other algorithms in accuracy and time.