Author:
Duan Caidie,Zhang Mingchuan
Abstract
Deep learning has powerful capabilities in deep feature extraction and expression, and has been successfully applied in equipment fault diagnosis, overcoming the shortcomings of traditional diagnostic methods that rely on expert experience. It can save costs while improving diagnostic accuracy. This article briefly introduces three commonly used neural networks: Deep Belief Networks (DBN), Convolutional Neural Networks (CNN), and Long Short-Term Memory Networks (LSTM), and points out the problems in rolling bearing diagnosis and analyzes future development directions.
Publisher
Darcy & Roy Press Co. Ltd.
Reference27 articles.
1. LeCun Yann, Bengio Y, Hinton G. Deep learning[J]. nature, Vol.521(2015),p. 436-444.
2. Lopes Noel, Ribeiro Bernardete. Deep belief networks (DBNs)[J]. Machine Learning for Adaptive Many-Core Machines-A Practical Approach, Vol.7 (2015), p. 155-186.
3. Liu Dongdong. Application of Deep Learning in Bearing Fault Diagnosis[J]. Science and technology wind. Vol.2022No9, p. 91-93.
4. Tao Jie, Liu Yilun, Yang Dalian, et al. Fault diagnosis of rolling bearing using deep belief networks[C]. Energy and Environment Engineering, Proceedings of the 2015 International Symposium on Material, 2015.
5. Wang Songjin, Peng Zanxin, Yin Han. Fault diagnosis of gearbox bearing based on multi-sensor signal processing[J]. Modular Machine Tool & Automatic Manufacturing Technique, Vol.2020No11, p. 5-10.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献