A local failure identification technology of Industrial 4.0 server based on spark big data processing
by Lixia Hao
International Journal of Internet Manufacturing and Services (IJIMS), Vol. 8, No. 3, 2022

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.

Online publication date: Mon, 18-Jul-2022

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Internet Manufacturing and Services (IJIMS):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com