A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load

By Wei Zhang, Chuanhao Li, Gaoliang Peng, Yuanhang Chen, Zhujun Zhang. Mechanical systems and signal processing, 2018

1,261 citations recorded by the source corpus.

Abstract In recent years, intelligent fault diagnosis algorithms using machine learning technique have achieved much success. However, due to the fact that in real world industrial applications, the working load is changing all the time and noise from the working environment is inevitable, degradation of the performance of intelligent fault diagnosis methods is very serious. In this paper, a new model based on deep learning is proposed to address the problem. Our contributions of include: First, we proposed an end-to-end method that takes raw temporal signals as inputs and thus doesn’t need any time consuming denoising preprocessing. The model can achieve pretty high accuracy under noisy environment. Second, the model does not rely on any domain adaptation algorithm or require information of the target domain. It can achieve high accuracy when working load is changed. To understand the proposed model, we will visualize the learned features, and try to analyze the reasons behind the high performance of the model.

Subfields: Control and Systems Engineering, Mechanics of Materials

View Paper: https://www.semanticscholar.org/paper/d4efae32628a9a4808ee19bf3067c31984e2299c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Control and Systems Engineering

In Mechanics of Materials

Citations in the corpus

A Review of Vibration-Based Damage Detection in Civil Structures: From Traditional Methods to Machine Learning and Deep Learning Applications (2020, background): “The high efficiency of vibration-based SDD systems via SHM of rotating machines [35] is based on the fact that the vibration response of such machines is minimally affected by the operational and environmental conditions [36–38].”
1-D Convolutional Neural Networks for Signal Processing Applications (2019, methodology): “In the study [26] more than 96% of the total data is used to train the deep network.”
Deep Learning Algorithms for Bearing Fault Diagnosticsx—A Comprehensive Review (2019, methodology): “Moreover, a very deep CNN of 14 layers with training interference is used in [112], which is able to maintain a high accuracy in noisy environments or during load shifts.”
Understanding and Learning Discriminant Features based on Multiattention 1DCNN for Wheelset Bearing Fault Diagnosis (2020, positive): “D) CNN (1DCNN) [12]–[14], [16], [17], [19], [23], [24]; the other converts the 1-”
1D Convolutional Neural Networks and Applications: A Survey (2019, methodology): “In the study [58], more than 96% of the total data is used to train the deep network.”