文献类型：期刊文献

英文题名：Fault location method of industrial Ethernet communication line based on Bayesian

作者：Liu, Yang[1]; Liu, Mingli[1]; Zhang, Ge[1]; Zhao, Shaofeng[1]; Wang, Ze[2]

第一作者：刘延光

机构：[1] Cloud Computing and Big Data Institute, Henan University of Economics and Law, Henan, Zhengzhou, 450046, China; [2] College of Electrical Engineering and Information Engineering, Lanzhou University of Technology, Lanzhou Gansu, 730050, China

第一机构：河南财经政法大学

年份：2024

卷号：10

期号：1

起止页码：1-14

外文期刊名：International Journal of Internet Manufacturing and Services

收录：EI(收录号：20240915638006);Scopus(收录号：2-s2.0-85185702036)

语种：英文

外文关键词：Discrete Fourier transforms - Ethernet

摘要：Because the traditional fault location method of industrial Ethernet network communication line has the problems of high location false alarm rate, low location accuracy rate and long location time, a Bayesian-based industrial Ethernet network communication line fault location method is proposed. First, the fault signal is measured by discrete Fourier transform algorithm. Then according to the measurement results, the fault features are extracted. Finally, the extracted features are input into Bayesian as training samples, and Bayesian is used to calculate the maximum posterior probability output corresponding to the input data, build a fault localisation model, and obtain the localisation results. The experimental results show that the fault localisation rate of the proposed method is only 0.8%, the localisation accuracy rate is as high as 98.6%, and the localisation time is 10.3 s. The fault localisation effect is good, and the fault localisation time can be effectively shortened. ? 2024 Inderscience Publishers. All rights reserved.