Intelligent fault diagnosis of machine under noisy environment using ensemble orthogonal contractive auto-encoder
作者：
Highlights：
• A novel EOCA approach for noisy signal is proposed.
• Sixteen OCA models with complementary characteristics are developed.
• A new cost function is designed and partial derivative is derived for training.
• Theory analysis is conducted to compute the error bound of EOCA.
• Effectiveness of EOCA is demonstrated in 3 case studies.
摘要
•A novel EOCA approach for noisy signal is proposed.•Sixteen OCA models with complementary characteristics are developed.•A new cost function is designed and partial derivative is derived for training.•Theory analysis is conducted to compute the error bound of EOCA.•Effectiveness of EOCA is demonstrated in 3 case studies.
论文关键词：Intelligent fault diagnosis,Orthogonal contractive auto-encoder,Ensemble learning,Deep learning
论文评审过程：Received 22 November 2021, Revised 6 February 2022, Accepted 25 April 2022, Available online 2 May 2022, Version of Record 10 May 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.117408
