A novel deep autoencoder and hyperparametric adaptive learning for imbalance intelligent fault diagnosis of rotating machinery. (June 2021)

• Record Type: Journal Article
• Authors: Li, Wanxiang; Shang, Zhiwu; Gao, Maosheng; Qian, Shiqi; Zhang, Baoren; Zhang, Jie
• Is Part Of: Engineering applications of artificial intelligence. Volume 102(2021)
• Publication Date: 2021-06
• Subjects: Fault diagnosis -- Rotating machinery -- Deep autoencoder -- Artificial bee colony algorithm -- Adaptively learn -- Class imbalance; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2021.104279
• Languages: English
• ISSNs: 0952-1976

Abstract

Highlights: The ORJ data augmentation strategy is designed to augmentation training samples. A deep SAE-LNC is proposed to improve the ability of capturing nonlinear features. Propose a hyperparameter adaptive learning method of deep neural network. Proposed method can capture high-quality state features and obtain higher diagnostic accuracy.