A Robust Approach of Multi-sensor Fusion for Fault Diagnosis Using Convolution Neural Network

Authors

  • Jiahao Sun State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University,China https://orcid.org/0000-0002-0930-2692
  • Xiwen Gu State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University,China
  • Jun He State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University,China
  • Shixi Yang State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University,China
  • Yao Tu Hangzhou Steam Turbine & Power Group Co., Ltd, China
  • Chenfang Wu State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University,China

DOI:

https://doi.org/10.37965/jdmd.2022.95

Keywords:

multi-sensor fusion, fault diagnosis, deep learning, engineering application

Abstract

Multi-sensor measurement is widely employed in rotating machinery to ensure the safety of machines. The information provided by the single sensor is not comprehensive. Multi-sensor signals can provide complementary information in characterizing the health condition of machines. This paper proposed a multi-sensor fusion convolution neural network (MF-CNN) model. The proposed model adds a 2-D convolution layer before the classical 1-D CNN to automatically extract complementary features of multi-sensor signals and minimize the loss of information. A series of experiments are carried out on a rolling bearing test rig to verify the model. Vibration and sound signals are fused to achieve higher classification accuracy than typical machine learning model. In addition, the model is further applied to gas turbine abnormal detection, and shows great robustness and generalization.

Downloads

Published

2022-06-07

How to Cite

Sun, J., Gu, X., He, J., Yang, S., Tu, Y., & Wu, C. (2022). A Robust Approach of Multi-sensor Fusion for Fault Diagnosis Using Convolution Neural Network. Journal of Dynamics, Monitoring and Diagnostics, 103–110. https://doi.org/10.37965/jdmd.2022.95

Issue

Section

Regular Article