Acta Scientiarum Naturalium Universitatis Sunyatseni ›› 2020, Vol. 59 ›› Issue (5): 66-77.doi: 10.13471/j.cnki.acta.snus.2019.08.20.2019B081

Previous Articles     Next Articles

Early bearing fault diagnosis based on VMD-TEO window function and DBiLSTM

QIAO Meiying12YAN Shuhao1LAN Jianyi23WANG Bo1TANG Xiaxia1YANG Jinxian1   

  1. 1. School of Electrical Engineering and AutomationHenan Polytechnic UniversityJiaozuo 454000China

    2. Collaborative Innovation Center of Coal Work SafetyJiaozuo 454000China

    3. School of energy science and engineeringHenan Polytechnic University Jiaozuo 454000China

  • Received:2019-06-06 Online:2020-09-25 Published:2020-09-25

Abstract:

Aiming at the problems caused by the data increase in the early fault monitoring of modern rolling bearingsa fault diagnosis model for deep bidirectional long and short memory neural networkDBiLSTMbased on variational mode decompositionVMDand TEO energy window was put forward. Firstlythe instantaneous energy characteristics of bearing vibration signals were extracted by the VMDTEO window function that optimized by the improved fruit fly algorithm. Meanwhilethe characteristic matrix with time characteristic was constructed. SecondlyDBiLSTM network model was trained by using the training set to determine the model parameters. Finallythe trained model was applied in the test set to generate fault recognition results. The test used Case Western Reserve University bearing fault data setand the results show that this method can effectively identify vibration signals of rolling bearings with various fault types and different damage levels when dealing with large amounts of data problems.

Key words: variational modal decomposition, TEO energy window function, DBiLSTM, bearing failure diagnosis

CLC Number: