Affiliation:
1. Department of Energy Systems, University of Thessaly, Gaiopolis Campus, 41500 Larissa, Greece
2. Public Power Corporation, Chalkokondili 22, 10432 Athens, Greece
Abstract
The scheduled maintenance of industrial equipment is usually performed with a low frequency, as it usually leads to unpredicted downtime in business operations. Nevertheless, this confers a risk of failure in individual modules of the equipment, which may diminish its performance or even lead to its breakdown, rendering it non-operational. Lately, predictive maintenance methods have been considered for industrial systems, such as power generation stations, as a proactive measure for preventing failures. Such methods use data gathered from industrial equipment and Machine Learning (ML) algorithms to identify data patterns that indicate anomalies and may lead to potential failures. However, industrial equipment exhibits specific behavior and interactions that originate from its configuration from the manufacturer and the system that is installed, which constitutes a great challenge for the effectiveness of ML model maintenance and failure predictions. In this article, we propose a novel method for tackling this challenge based on the development of a digital twin for industrial equipment known as a Remote Terminal Unit (RTU). RTUs are used in electrical systems to provide the remote monitoring and control of critical equipment, such as power generators. The method is applied in an RTU that is connected to a real power generator within a Public Power Corporation (PPC) facility, where operational anomalies are forecasted based on measurements of its processing power, operating temperature, voltage, and storage memory.
Reference44 articles.
1. Schwab, K. (2017). The Fourth Industrial Revolution, Currency.
2. Sari, A., Lekidis, A., and Butun, I. (2020). Industrial IoT: Challenges, Design Principles, Applications, and Security, Springer.
3. Measuring community and multi-industry impacts of cascading failures in power systems;Li;IEEE Syst. J.,2017
4. van Dinter, R., Tekinerdogan, B., and Catal, C. (2022). Predictive maintenance using digital twins: A systematic literature review. Inf. Softw. Technol., 151.
5. Semi-Supervised Multiscale Permutation Entropy-Enhanced Contrastive Learning for Fault Diagnosis of Rotating Machinery;Zhou;IEEE Trans. Instrum. Meas.,2023
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Time Series Problems in the Energy Sector;2024 IEEE 40th International Conference on Data Engineering Workshops (ICDEW);2024-05-13