Method of extracting gear fault feature based on stacked autoencoder

Abstract

Gear and its transmission are widely used in different transmission systems, and its complicated and changeable condition brings a series of problems to the fault feature extraction and diagnosis. In recent years, deep learning techniques have been gradually applied to feature extraction and pattern recognition, and the features of feature extraction and fault diagnosis in complex working environments have shown certain advantages. This study is based on stacked autoencoder under deep learning model, and improve training network performance by modified activation function. Through the network training before and after the experiment done, and to extract the fault feature data comparison in testing, improving network after activation function to extract fault features showed a greater advantage, can be a very good application in practical fault feature extraction.

Keywords

• mechanical engineering computing
• fault diagnosis
• gears
• feature extraction
• neural nets
• learning (artificial intelligence)
• practical fault feature extraction
• fault features
• network training
• modified activation function
• training network performance
• deep learning model
• complex working environments
• pattern recognition
• deep learning techniques
• changeable condition
• complicated condition
• different transmission systems
• stacked autoencoder
• gear fault feature