Learning Attention Representation with a Multi-Scale CNN for Gear Fault Diagnosis under Different Working Conditions

Abstract

The gear fault signal under different working conditions is non-linear and non-stationary, which makes it difficult to distinguish faulty signals from normal signals. Currently, gear fault diagnosis under different working conditions is mainly based on vibration signals. However, vibration signal acquisition is limited by its requirement for contact measurement, while vibration signal analysis methods relies heavily on diagnostic expertise and prior knowledge of signal processing technology. To solve this problem, a novel acoustic-based diagnosis (ABD) method for gear fault diagnosis under different working conditions based on a multi-scale convolutional learning structure and attention mechanism is proposed in this paper. The multi-scale convolutional learning structure was designed to automatically mine multiple scale features using different filter banks from raw acoustic signals. Subsequently, the novel attention mechanism, which was based on a multi-scale convolutional learning structure, was established to adaptively allow the multi-scale network to focus on relevant fault pattern information under different working conditions. Finally, a stacked convolutional neural network (CNN) model was proposed to detect the fault mode of gears. The experimental results show that our method achieved much better performance in acoustic based gear fault diagnosis under different working conditions compared with a standard CNN model (without an attention mechanism), an end-to-end CNN model based on time and frequency domain signals, and other traditional fault diagnosis methods involving feature engineering.

Neural Networks-Based Aerodynamic Data Modeling: A Comprehensive Review

“…Consequently, attention mechanism has been widely used in natural language processing [65], statistical learning [66], and computational vision [67]. There are many variations of attention mechanism, for example soft attention [68], multi-level attention [69] and multi-dimensional attention [70], etc. More details of the category of attention mechanism can be found in [71].…”

Method for Fault Diagnosis of Temperature-Related MEMS Inertial Sensors by Combining Hilbert–Huang Transform and Deep Learning

“…This FD method adopted CNNs to recognize various fault features, and the STFT is used to convert the 1-D signals to 2-D spectrums. In [ 34 ], Yao et al presented a multi-scale CNN-based gear FD method. This method designs an attention mechanism based on multi-scale CNN to mine the relevant fault information and uses multi-scale CNN to recognize the faults.…”

“…Deep learning (DL) learns features from big data [ 32 , 33 ] and avoids the complex processes stemming from handcrafted features. CNN is a powerful DL model for handling two-dimensional (2-D) images and has been used in FD research, such as mechanical systems FD [ 34 , 35 ], circuit systems FD [ 36 ], and avionics FD [ 37 ]. In FD applications, because raw data is often sampled in one-dimensional (1-D) format, researchers have turned to feature extraction operations that construct 2-D features for addressing FD problems using CNNs, such as sliding window [ 38 , 39 ], short time Fourier transform (STFT) [ 40 ], discrete wavelet transform (DWT) [ 41 , 42 ], and Hilbert–Huang transform (HHT) [ 43 , 44 ].…”

Fault Diagnosis Based on Space Mapping and Deformable Convolution Networks

“…With the rapid development of artificial intelligence, some deep learning methods, such as artificial neural networks, have achieved great results in fault diagnosis due to their strong feature extraction capability. Artificial neural networks include convolutional neural networks (CNNs), deep belief networks (DBNs), residual networks (ResNets), and deep transfer networks (DTNs) [12], [19]- [23]. The collected fault data are input into specific networks, and the result of classification or diagnosis can be directly output, which are called end-to-end methods.…”