Abstract
Multi-sensor data fusion is a feasible technique to achieve accurate and robust results in fault diagnosis of rotating machinery under complex conditions. However, the problem of information losses is always ignored during the fusion process. To solve above problem, an ensemble convolutional neural network model is proposed for bearing fault diagnosis. The framework of the proposed model contains three convolutional neural network branches: one multi-channel fusion convolutional neural network branch and two 1-D convolutional neural network branches. The former branch extracts the coupling features based on multi-sensor data and the latter two branches extract the inherent features based on single-sensor data, which can collect comprehensive fault information and reduce information losses. Furthermore, the support vector machine ensemble strategy is employed to fuse the results of multiple branches, which can improve the generalization and robustness of the proposed model. The experiments show that the proposed can obtain more effective and robust results than other methods.
Highlights
Rotating machinery is widely used in modern industry
Traditional fault diagnosis methods are mainly based on model analysis or signal processing techniques
The MCF-convolutional neural network (CNN) model fuses multi-sensor data at the feature level and ensemble convolutional neural networks (ECNN) fuses the results of three CNN branches at decision level, effectively overcoming the problem of information losses during the fusion process
Summary
Rotating machinery is widely used in modern industry. Due to long-time running under complicated conditions such as high speed, heavy load and strong impact, rotating machinery will inevitably have some faults, which can result in enormous losses and serious casualties [1]. Traditional fault diagnosis methods are mainly based on model analysis or signal processing techniques. Kerschen et al [5] provide extensive reviews on model-based analysis of vibrating systems. These methods usually require the design of the explicit mathematical model to simulate the behavior of the machine, while the development of the mathematical model is almost impossible when dealing with modern machines with very complex structures. The methods based on signal processing techniques often utilize signal models, such as power spectrum [6], high order spectrum [6,7,8], composite spectrum [9,10,11], to directly extract the fault features from the measured
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
