Anomaly Detection in Gas Turbines Using Outlet Energy Analysis with Cluster-Based Matrix Profile
Author:
Ghazvini Mina Bagherzade1ORCID, Sànchez-Marrè Miquel1ORCID, Naderi Davood2, Angulo Cecilio3ORCID
Affiliation:
1. Computer Science Department, Intelligent Data Science and Artificial Intelligence Research Centre (IDEAI), Universitat Politècnica de Catalunya, 08034 Barcelona, Spain 2. Siemens Energy S.L., Slottsvägen 2-6, 612 31 Finspang, Sweden 3. Automatic Control Department, Intelligent Data Science and Artificial Intelligence Research Centre (IDEAI), Universitat Politècnica de Catalunya, 08028 Barcelona, Spain
Abstract
Gas turbines play a key role in generating power. It is really important that they work efficiently, safely, and reliably. However, their performance can be adversely affected by factors such as component wear, vibrations, and temperature fluctuations, often leading to abnormal patterns indicative of potential failures. As a result, anomaly detection has become an area of active research. Matrix Profile (MP) methods have emerged as a promising solution for identifying significant deviations in time series data from normal operational patterns. While most existing MP methods focus on vibration analysis of gas turbines, this paper introduces a novel approach using the outlet power signal. This modified approach, termed Cluster-based Matrix Profile (CMP) analysis, facilitates the identification of abnormal patterns and subsequent anomaly detection within the gas turbine engine system. Significantly, CMP analysis not only accelerates processing speed, but also provides user-friendly support information for operators. The experimental results on real-world gas turbines demonstrate the effectiveness of our approach in the early detection of anomalies and potential system failures.
Funder
Siemens Energy under agreement Siemens-UPC Ministry of State for Digitalization and Artificial Intelligence European Union—Next Generation EU funds
Subject
Energy (miscellaneous),Energy Engineering and Power Technology,Renewable Energy, Sustainability and the Environment,Electrical and Electronic Engineering,Control and Optimization,Engineering (miscellaneous),Building and Construction
Reference72 articles.
1. Kagermann, H., Wahlster, W., and Helbig, J. (2013). Recommendations for Implementing the Strategic Initiative INDUSTRIE 4.0: Securing the Future of German Manufacturing Industry, National Academy of Science and Engineering. Final Report of the Industrie 4.0 Working Group. 2. Osmani, A., Hamidi, M., and Bouhouche, S. (2019, January 10–16). Monitoring of a Dynamic System Based on Autoencoders. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19, Macao, China. 3. Liu, Y., Banerjee, A., Ravichandran, T., Kumar, A., and Heppler, G. (2018, January 24–27). Data Analytics for Performance Monitoring of Gas Turbine Engine. Proceedings of the Annual Conference of the PHM Society, Philadelphia, PA, USA. 4. A review of novelty detection;Pimentel;Signal Process.,2014 5. Panza, M.A., Pota, M., and Esposito, M. (2023). Anomaly Detection Methods for Industrial Applications: A Comparative Study. Electronics, 12.
|
|