Opt-TCAE: Optimal temporal convolutional auto-encoder for boiler tube leakage detection in a thermal power plant using multi-sensor data. (1st April 2023)

• Record Type: Journal Article
• Authors: Kim, Hyeongmin; Ko, Jin Uk; Na, Kyumin; Lee, Hyeonchan; Kim, Hee-soo; Son, Jong-duk; Yoon, Heonjun; Youn, Byeng D.
• Is Part Of: Expert systems with applications. Volume 215(2023)
• Publication Date: 2023-04-01
• Subjects: Boiler tube leakage -- Anomaly detection -- Unsupervised learning -- Latent dimension optimization -- Inter-sensor relationship -- Temporal relationship; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2022.119377
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: A novel auto-encoder based method is proposed for boiler tube leakage detection. Temporal and inter-sensor relationships of the multi-sensor signals are considered. The method contains way to optimize latent dimension of the auto-encoder model. The effectiveness of the method is validated via real thermal power plant data. Abstract: Accurate and timely detection of boiler tube leakage in a thermal power plant is essential to maintain a stable power supply and prevent catastrophic failures. This paper proposes a novel, unsupervised learning-based leakage detection method, namely optimal temporal convolutional auto-encoder, which uses both acoustic emission signals and operating (i.e., temperature and pressure) signals. The proposed optimal temporal convolutional auto-encoder learns the characteristics of normal operating conditions by reconstructing input data and detects tube leakage by calculating its reconstruction error. Unlike conventional methods that mainly focus on modeling only inter-sensor relationships, the proposed method offers a deep learning structure that can effectively capture temporal as well as inter-sensor relationships. This paper also proposes a method to optimize the latent dimension of the auto-encoder structure by minimizing the entropy of the trained normal reconstruction errors. In a preprocessing step, the moving average filtering is used to reduce the effect of external noises in acoustic emission signals, thereby decreasing the number of false alarms. Kernel density estimation is adopted to automatically set the threshold. The effectiveness of the proposed method is verified through datasets acquired from real operating power plant. The results show that the proposed method can detect leakage more accurately than conventional methods.