Abstract
The existing intelligent fault diagnosis methods of rotor-bearing system mainly focus on vibration analysis under steady operation, which has low adaptability to new scenes. In this article, a new framework for rotor-bearing system fault diagnosis under varying working conditions is proposed by using modified convolutional neural network (CNN) with transfer learning. First, infrared thermal images are collected and used to characterize the health condition of rotor-bearing system. Second, modified CNN is developed by introducing stochastic pooling and Leaky rectified linear unit to overcome the training problems in classical CNN. Finally, parameter transfer is used to enable the source modified CNN to adapt to the target domain, which solves the problem of limited available training data in the target domain. The proposed method is applied to analyze thermal images of rotor-bearing system collected under different working conditions. The results show that the proposed method outperforms other cutting edge methods in fault diagnosis of rotor-bearing system.
Highlights
Rotating machinery plays an increasing role in electric power, manufacturing, transportation, and other industries [1, 2]
More and more attention has been paid to deep learning-based approaches with automatic feature learning capability, such as deep belief network (DBN), stacked auto-encoder (SAE), convolutional neural network (CNN), long short-term memory (LSTM), etc
In order to prove the feasibility of the modifications in the proposed method, several currently popular models are utilized for comparisons, including another eight types of CNNs built with different pooling strategies and activation functions, and two unsupervised deep learning models, i.e., DBN and SAE
Summary
Rotating machinery plays an increasing role in electric power, manufacturing, transportation, and other industries [1, 2]. The current CNN-based diagnosis approaches with thermal images can only deal with the same working condition that is rarely the case in real applications These methods are all based on the availability of a large number of training samples which are difficult and expensive to acquire. How to enable the CNNs trained with limited thermal images to achieve satisfactory fault diagnosis accuracy of rotor-bearing system under varying working conditions has become an urgent task. A modified transfer CNN driven by thermal images is proposed to diagnose faults of rotor-bearing system under varying working conditions. The main contributions of this article are as follows: 1) A new framework for rotor-bearing system fault diagnosis under varying working conditions is proposed by using CNN with transfer learning.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
