ORIGINAL RESEARCH article
Front. Phys.
Sec. Interdisciplinary Physics
State Evaluation of Zinc Oxide Arrester Based on Initial Probabilistic Self-learning Bayes Algorithm
Provisionally accepted
- State Grid Jiangsu Electric Power Co., LTD, Nanjing, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
In order to improve the accuracy of state evaluation of Zinc Oxide arrester, a method of state evaluation of Zinc Oxide arrester based on initial probabilistic self-learning Bayes algorithm is proposed. The method firstly uses association rules to mine the correlation of state parameters under various fault modes, and then adopts 5-level state evaluation method to establish a hierarchical criterion for quantifying the health state of arrester. The threshold and score of each parameter in the hierarchical model are determined by fuzzy membership function, and the corresponding equipment state is evaluated by using the historical, current and predicted state information of arrester. Then, considering the data characteristics of these three types of information and the correlation of state parameters, the conditional probability table self-learning was carried out, and finally a Bayesian network-based zinc oxide condition assessment model was established. The conditional probability table and transaction matrix heat map corresponding to all levels of state under comprehensive assessment were obtained, and the comprehensive condition assessment method of equipment operation was given. Finally, through a practical case, it is verified that this method achieves a condition assessment accuracy of 93.33%, which is significantly superior to the traditional single-parameter method and clustering algorithm.
Keywords: Association rules mining, Bayesian network, ConditionAssessment, Initial probability, Self-learning, Zinc oxide arrester
Received: 07 Sep 2025; Accepted: 09 Dec 2025.
Copyright: © 2025 HUANG, LU, XUE, HUANG, ZHOU, Wang and Ding. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Xiaowei HUANG
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.