Title: A local failure identification technology of Industrial 4.0 server based on spark big data processing
Authors: Lixia Hao
Addresses: Department of Information Engineering, Hebei Chemical and Pharmaceutical College, Shijiazhuang 050026, China
Abstract: The traditional server local failure identification method has the problems of long identification time and high identification error rate. Therefore, this paper proposes the Industrial 4.0 server local failure identification technology based on spark big data processing. Firstly, the spark programming model is used to obtain the server node data distribution, and the LMD method is used to extract the local features of Industrial 4.0 server. Secondly, the redundant parameters of failure characteristics are eliminated by PF component screening. Then, the type of failure fault is determined by judging the threshold selection. Finally, the current sensor is used to determine the fault location and complete the local failure identification of the server. The results show that the total recognition time of this method is no more than 16 s, and the recognition error rate is 0.025, which shows that this method has good recognition performance.
Keywords: Industry 4.0 theory; local failure; spark programming model; big data processing.
International Journal of Internet Manufacturing and Services, 2022 Vol.8 No.3, pp.195 - 207
Received: 04 Nov 2021
Accepted: 14 Feb 2022
Published online: 18 Jul 2022 *