http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : Changfeng Yan (검색결과 3 건)
- 무료
- 기관 내 무료
- 유료
-
Abdalla Babiker,Changfeng Yan,Qiang Li,Jiadong Meng,Lixiao Wu 대한기계학회 2021 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.35 No.2
Rolling bearing failure is widely regarded as a failure form of industrial machines. Owing to the poor operating circumstance with the stochastic contact between rolling elements, the performance of the bearing will deteriorate over time and cause a cascade breakdown in the mechanical system. Early fault detection has been found to be an effective strategy to avoid economic loss. Therefore, an integration method for fault diagnosis that combines backtracking strategy, improved variational mode decomposition (VMD), and infogram is proposed to tackle the challenge of the early feature extraction from the heavy noisy non-stationary signal. The backtracking strategy is adopted to track the data sample points earlier than the fault threshold determined based on the kurtosis index. The optimum parameters α and K of VMD are acquired through the particle swarm optimization (PSO) algorithm. In this way, the more accurate intrinsic mode functions (IMFs) can be gained by the improved VMD. The optimum IMFs are acquired according to the maximum values of kurtosis and correlation coefficients, and these IMFs can be reconstructed into the noise reduction signal. Since envelope analysis requires the selection of the appropriate central frequency and bandwidth, infogram is utilized to select the values of them. A simulated case is applied to demonstrate the validation of the proposed method. And to further illustrate its practicality, it is employed to perform early fault diagnosis for an experimental case. According to the diagnosis results, the proposed method has conspicuous superiority over the other existing technologies for estimating incipient fault time of the bearing.
-
Characteristics of vibration response of ball bearing with local defect considering skidding
Yu Tian,Changfeng Yan,Yaofeng Liu,Wei Luo,Jianxiong Kang,Zonggang Wang,Lixiao Wu 대한기계학회 2023 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.37 No.11
The occurrence and aggravation of local defects in ball bearings are closely linked to the skidding behavior of the ball. Previous studies have given less attention to investigating the impact of localized defects on the problem of bearing skidding. To investigate the dynamic response of defective bearings due to skidding, a dynamic model of the ball bearing is developed that considers various factors, including self-rotation, revolution, and radial motion of the ball, as well as the contact forces and friction forces of ball/cage and ball/race, time-varying displacement excitation, and elastohydrodynamic lubrication (EHL). Experimental signals collected from a machinery fault simulator test rig are used to validate the accuracy of the proposed model. The impact of race defects on the vibration characteristics of the bearing is analyzed, and the patterns of variation in contact and friction forces within one cycle of inner race rotation are described. The results indicate that the presence of defects intensifies the force fluctuation of the ball and causes it to deviate from its normal rolling condition. By comparing the skidding characteristics of a healthy bearing with a defective one under slippage, local defects will increase the skidding ratio of bearings. The proposed model can investigate the impact of race defects on the vibration response of ball bearings under the skidding condition.
-
Bin Liu,Changfeng Yan,Zonggang Wang,Yaofeng Liu,Lixiao Wu 대한기계학회 2023 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.37 No.7
Deep learning is widely used in the field of rolling bearing fault diagnosis because of its excellent advantages in data analysis. However, in practical industrial scenarios, the capability of intelligent fault diagnosis (IFD) method is still affected by two problems: (1) The signal samples provided for network learning are limited; (2) Fully extracting feature information from the original data is difficult. To address the above issues, a novel fault diagnosis method using joint learning network (JLNet) based on local-global feature perception is proposed. The method enhances the learning mechanism of fault signal through the local information dynamic perception subnetwork, which dynamically distinguishes between local impulse segment and normal signal segment. Then, a global channel attention mechanism (CAM) is used to guide the assignment of weights, which helps bidirectional gated recurrent unit (BiGRU) to learn advanced discriminative features. The feature information of the original signal is thoroughly mined through local-global comprehensive perception, thus realizing efficient diagnosis. In addition, the variation of the characteristics of each layer is analyzed by visualization, which improves the interpretability of the network. Finally, experiments are conducted using two different datasets, and the results show that JLNet has a better diagnostic effects and robustness.
연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
