Safety monitoring of machinery equipment and fault diagnosis method based on support vector machine and improved evidence theory
by Xingtong Zhu; Jianbin Xiong; Yeh-cheng Chen; Yongda Cai
International Journal of Information and Computer Security (IJICS), Vol. 19, No. 3/4, 2022

Abstract: Safe and reliable operation of machinery is the primary requirement of enterprise production and the basis for realising the economic benefits. Some of the fault diagnosis methods use evidence theory to determine the fault type by collecting the vibration signals. However, in a complex operating environment, the evidence of vibration signal is high-conflict, so it is difficult to obtain the correct fault type. In order to solve this problem, an improved evidence theory-based fault diagnosis method is proposed. First, vibration sensors are used to monitor operating conditions of mechanical equipment and collect vibration signals, and then the dimensionless indicators of these vibration signals are calculated to build the feature dataset. Next, the support vector machine (SVM) is applied to the preliminary fault diagnosis, and the probability of various fault types obtained by the SVM primary fault diagnosis is used as the basic probability assignment (BPA) of evidence. Finally, the improved evidence combination rule based on the Tanimoto coefficient and information entropy is used to fuse the evidence, thus forming the final diagnosis result. The experiments show that the proposed method is effective, achieving the fault diagnosis accuracy of 93.33%.

Online publication date: Wed, 23-Nov-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 Information and Computer Security (IJICS):
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