Bearing fault diagnosis with auto-encoder extreme learning machine: A comparative study

• DOI: 10.1177/0954406216675896
• Publication Date: 2016-11-04T01:39:43Z
• Authors: Wentao Mao; Jianliang He; Yuan Li; Yunju Yan
• Keywords: Extreme Learning Machine; Discriminative model; Autoencoder; Feature Learning

Intelligent fault-diagnosis methods using machine learning techniques like support vector machines and artificial neural networks have been widely used to distinguish bearings’ health condition. However, though these generally work well, they still two potential drawbacks when facing massive fault data: (1) the feature extraction process needs prior domain knowledge, therefore lacks a universal method for various diagnosis issues, (2) much training time is needed by traditional intelligent newly presented deep methods. In this research, inspired capability of auto-encoders high speed extreme (ELMs), an auto-encoder-ELM-based proposed diagnosing faults in bearings overcome aforementioned deficiencies. This paper performs comparative analysis some state-of-the-art methods, experimental results on rolling element data set show effectiveness not only with adaptive mining discriminative characteristic but also at speed.