http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Study on logarithmic crowning of cylindrical roller profile considering angular misalignment
Zhenghai Wu,Yingqiang Xu,Sier Deng,Kaian Liu 대한기계학회 2020 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.34 No.5
The angular misalignment of cylindrical rollers causes the stress edge effect at roller ends to be aggravated, which would affect bearing capacity and fatigue life of bearings. Therefore, based on the roller angular misalignment, the geometric interference model of the cylindrical contact pair was established in this paper. Thereafter, two types of logarithmic crowning models were theoretically deduced, in which design redundancy was considered through special treatment of pre-pressure. Taking the aero-engine main shaft bearing as an example, contact characteristics of the cylindrical roller with these two logarithmic profiles were studied by the DC-FFT method and the conjugate gradient method (CGM). The results show that two profiles can effectively eliminate the stress edge effect, improve contact pressure distribution and subsurface stress field of the roller in misalignment state, and at the same time ensure fine contact characteristics in alignment state. The research can provide a theoretical basis and reference for finite line contact pairs under angular misalignment.
A novel HB-SC-MCCNN model for intelligent fault diagnosis of rolling bearing
Hui Liao,Pengfei Xie,Yan Zhao,Jinfang Gu,Lei Shi,Sier Deng,Hengdi Wang 대한기계학회 2023 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.37 No.12
The incompleteness and lack of bearing fault data have become important problems in bearing fault diagnosis. This paper presents an intelligent fault diagnosis method for rolling bearings based on a similarity clustering multi-channel convolution neural network with the hierarchical branch (HB-SC-MCCNN). First, the relevant features are extracted by MCCNN, and combined with the similarity clustering principle, the accurate binary classification is realized in the case of insufficient labeled data. Second, the similarity clustering module and additional loss are added to the SC-MCCNN network to form a hierarchical-branch network, which simplifies the problem of fault multi-classification into binary classification with multiple steps, and to reduces the dependence on the amount of label data in multi-classification. Finally, based on the self-learning characteristics of HB-SC-MCCNN, the unlabeled data and the missing fault types in the training set are re-labeled to realize the re-training of the network. On the benchmark dataset, the comparison experiment results with several salient deep learning models show that the method proposed in this paper successfully realizes the hierarchical diagnosis of bearing faults and presents more substantial competitiveness in the case of insufficient labeled data and missing fault types.