Ensemble deep transfer learning driven by multisensor signals for the fault diagnosis of bevel-gear cross-operation cond
- PDF / 7,232,414 Bytes
- 12 Pages / 595.276 x 793.701 pts Page_size
- 21 Downloads / 171 Views
semble deep transfer learning driven by multisensor signals for the fault diagnosis of bevel-gear cross-operation conditions 1
1*
DI ZiYang , SHAO HaiDong & XIANG JiaWei 1
2
State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, College of Mechanical and Vehicle Engineering, Hunan 2
University, Changsha 410082, China; College of Mechanical and Electrical Engineering, Wenzhou University, Wenzhou 325035, China
Received April 26, 2020; accepted June 8, 2020; published online September 22, 2020
The existing intelligent fault diagnosis techniques of bevel gear focus on single-sensor signal analysis under the steady operation condition. In this study, a new method is proposed based on ensemble deep transfer learning and multisensor signals to enhance the fault diagnosis adaptability and reliability of bevel gear under various operation conditions. First, a novel stacked autoencoder (NSAE) is constructed using a denoising autoencoder, batch normalization, and the Swish activation function. Second, a series of source-domain NSAEs with multisensor vibration signals is pretrained. Third, the good model parameters provided by the source-domain NSAEs are transferred to initialize the corresponding target-domain NSAEs. Finally, a modified voting fusion strategy is designed to obtain a comprehensive result. The multisensor signals collected under the different operation conditions of bevel gear are used to verify the proposed method. The comparison results show that the proposed method can diagnose different faults in an accurate and stable manner using only one target-domain sample, thereby outperforming the existing methods. ensemble deep transfer learning, bevel-gear fault diagnosis, novel stacked autoencoder, multisensor signals, modified voting fusion strategy Citation:
Di Z Y, Shao H D, Xiang J W. Ensemble deep transfer learning driven by multisensor signals for the fault diagnosis of bevel-gear cross-operation conditions. Sci China Tech Sci, 2020, 63, https://doi.org/10.1007/s11431-020-1679-x
1 Introduction The bevel gear plays an irreplaceable role in some important industrial equipment, including aeroengines, helicopters, automobiles, and high-speed trains. Different faults inevitably occur in the bevel gear during service, causing security incidents. Vibration analysis is the best-known method for bevel-gear health monitoring [1]. Compared with other gears, such as cylindrical and parallel gears, the special contact pattern and complicated transmission path make the vibration signal processing of bevel gear considerably dependent on domain knowledge and expert experience [2–4]. *Corresponding author (email: [email protected])
Intelligent diagnosis aims to automatically distinguish between different fault types and damage degrees, which have been popular topics in the field of mechanical fault diagnosis [5–7]. For some decades, shallow learning models have been extensively applied to mechanical intelligent fault diagnosis, but their performance is considerably dependent on the presence of hi
Data Loading...
