Search

Your search keyword '"WANG, JUNLI"' showing total 2,044 results
Start Over Author "WANG, JUNLI"
2,044 results on '"WANG, JUNLI"'

103. A fault diagnosis method for mine rolling bearings based on deep learning

Author

DOU Guidong, BAI Yishuo, WANG Junli, HUANG Bohao, and YANG Kang

Subjects
rolling bearings, fault diagnosis, markov transition field, capsule network, inception structure, mtf encoding, Mining engineering. Metallurgy, TN1-997
Abstract

A fault diagnosis method for mine rolling bearings based on Markov transition field(MTF) and dual-channel multi-scale convolutional capsule network (DMCCN) is proposed to address the problem of traditional convolutional neural networks being unable to fully explore data features in complex environments such as coal mines. The MTF-DMCCN fault diagnosis model is constructed. After encoding the original vibration signal based on MTF and grayscale image, a dual channel input mode is used to connect the convolutional network to obtain shallow features. The method inputs the feature maps fusion into the capsule network to improve the sensitivity of the model to spatial information. The method introduces Inception modules into the network to focus on multi-scale features and enhance the network's feature extraction capabilities. Finally, vectorization processing is carried out through the capsule layer to achieve fault diagnosis and classification of rolling bearings. The results of ablation, noise resistance, and generalization experiments show that the Inception module, grayscale image input, and MTF image input all have a positive promoting effect on bearing fault diagnosis. MTF coding has the highest improvement in diagnostic precision of the model. The MTF-DMCCN model has good robustness and noise resistance. The MTF-DMCCN model has excellent adaptability to variable speed and still exhibits good generalization performance under different operating conditions. To further validate the performance of the model, image encoding methods such as Gram angle difference field (GADF), Gram angle sum field (GASF), grayscale image, and MTF are selected and combined with different networks. Comparative experiments are conducted using the University of Cincinnati intelligent maintenance system (IMS). The results show that the MTF-DMCCN model can effectively recognize the type of rolling bearing faults, with an average fault diagnosis accuracy of 99.37%.

Published
2024
Full Text
View/download PDF

111. Constructions of quasi-twisted quantum codes

Author

Lv, Jingjie, Li, Ruihu, and Wang, Junli

Subjects
Computer Science - Information Theory
Abstract

In this work, our main objective is to construct quantum codes from quasi-twisted (QT) codes. At first, a necessary and sufficient condition for Hermitian self-orthogonality of QT codes is introduced by virtue of the Chinese Remainder Theorem (CRT). Then we utilize these self-orthogonal QT codes to provide quantum codes via the famous Hermitian Construction. Moreover, we present a new construction method of q-ary quantum codes, which can be viewed as an effective generalization of the Hermitian Construction. General QT codes that are not self-orthogonal are also employed to construct quantum codes. As the computational results, some binary, ternary and quaternary quantum codes are constructed and their parameters are determined, which all exceed the Quantum Gilbert-Varshamov (GV) Bound. In the binary case, a small number of quantum codes are derived with strictly improved parameters compared with the current records. In the ternary and quaternary cases, our codes fill some gaps or have better performances than the current results., Comment: We want to perfect this paper

Published
2019

126. Chinese College Students' Physical Activity Correlates and Behavior: A Transtheoretical Model Perspective

Author

Xiong, Shanying, Li, Xianxiong, Tao, Kun, Zeng, Nan, Ayyub, Mohammad, Peng, Qingwen, Yan, Xiaoni, Wang, Junli, Wu, Yizhong, and Lei, Mingzhi

Abstract

Guided by the Transtheoretical Model (Prochaska & DiClemente, 1982), this study investigated the differences of physical activity levels and correlates (i.e., self-efficacy, decisional balance, process of change) across different stages of change levels among Chinese college students. The relationships between students' physical activity correlates and physical activity behavior was also examined. The participants were 887 college students (365 males; M[subscript age] = 20.51, SD = ± 1.67) recruited from four universities in south and south-canter China. Participants completed a battery of established questionnaires assessing their physical activity correlates (self-efficacy, decisional balance, process of change) and 1-week physical activity levels. Results suggested that Chinese college students in the high stage of change group reported significantly higher physical activity levels and correlates than those in the low stage of change group. Pearson correlation analyses suggested that students' self-efficacy was moderately related to other correlates and physical activity behavior. Yet, decisional balance and process of change were only modestly associated with physical activity levels for both groups. Regression analyses further revealed students' self-efficacy emerged as the only significant contributor of their daily PA levels across the two groups. However, decision balance and process of change failed to predict physical activity levels. The implications for practice and direction of future research were discussed.

Published
2017

Catalog

Books, media, physical & digital resources
See catalog results