An improved bearing fault detection strategy based on artificial bee colony algorithm. Issue 4 (6th June 2022)

• Record Type: Journal Article
• Authors: Wang, Haiquan; Yue, Wenxuan; Wen, Shengjun; Xu, Xiaobin; Haasis, Hans‐Dietrich; Su, Menghao; liu, Ping; Zhang, Shanshan; Du, Panpan
• Is Part Of: CAAI transactions on intelligence technology. Volume 7:Issue 4(2022)
• Page Start: 570
• Page End: 581
• Publication Date: 2022-06-06
• Subjects: fault diagnosis -- feature extraction -- improved artificial bee colony algorithm -- improved one‐dimensional ternary pattern method -- shapelet transformation; Artificial intelligence -- Periodicals; Computer science -- Periodicals; Artificial intelligence; Computer science; Electronic journals; Periodicals; 006.305
• DOI: 10.1049/cit2.12105
• Languages: English
• ISSNs: 2468-6557

Abstract

Abstract: The operating state of bearing affects the performance of rotating machinery; thus, how to accurately extract features from the original vibration signals and recognise the faulty parts as early as possible is very critical. In this study, the one‐dimensional ternary model which has been proved to be an effective statistical method in feature selection is introduced and shapelet transformation is proposed to calculate the parameter of one‐dimensional ternary model that is usually selected by trial and error. Then XGBoost is used to recognise the faults from the obtained features, and artificial bee colony algorithm (ABC) is introduced to optimise the parameters of XGBoost. Moreover, for improving the performance of intelligent algorithm, an improved strategy where the evolution is guided by the probability that the optimal solution appears in certain solution space is proposed. The experimental results based on the failure vibration signal samples show that the average accuracy of fault signal recognition can reach 97%, which is much higher than the ones corresponding to traditional extraction strategies. And with the help of improved ABC algorithm, the performance of XGBoost classifier could be optimised; the accuracy could be improved from 97.02% to 98.60% compared with the traditional classification strategy.