Detecting Gas Turbine Combustor Anomalies Using Semi-supervised Anomaly Detection with Deep Representation Learning

• Published in: Cognitive computation Vol. 12; no. 2; pp. 398 - 411
• Main Author: Yan, Weizhong
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.03.2020; Springer Nature B.V
• Subjects: Anomalies; Artificial Intelligence; Biomedical and Life Sciences; Biomedicine; Classification; Combustion chambers; Computation by Abstract Devices; Computational Biology/Bioinformatics; Condition monitoring; Deep learning; Fault detection; Gas turbine engines; Gas turbines; High temperature; Machine learning; Neural networks; Neurosciences; Performance evaluation; Power plants; Probabilistic models; Representations; Sensors; Support vector machines; Deep learning; Extreme learning machine; Semi-supervised learning; Gas turbine; Combustor; Prognostics and health management; Anomaly detection
• ISSN: 1866-9956; 1866-9964
• DOI: 10.1007/s12559-019-09710-7

Deep learning (DL), regarded as a breakthrough machine learning technique, has proven to be effective for a variety of real-world applications. However, DL has not been actively applied to condition monitoring of industrial assets, such as gas turbine combustors. We propose a deep semi-supervised anomaly detection (deepSSAD) that has two key components: (1) using DL to learn representations or features from multivariate, time-series sensor measurements; and (2) using one-class classification to model normality in the learned feature space, thus performing anomaly detection. Both steps use normal data only; thus our anomaly detection falls into the semi-supervised anomaly detection category, which is advantageous for industrial asset condition monitoring where abnormal or faulty data is rare. Using the data collected from a real-world gas turbine combustion system, we demonstrate that our proposed approach achieved a good detection performance (AUC) of 0.9706 ± 0.0029. Furthermore, we compare the detection performance of the proposed approach against that of other different designs, including different features (i.e., the deep learned, handcrafted and PCA features) and different detection models (i.e., one-class ELM, one-class SVM, isolation forest, and Gaussian mixture model). The proposed approach significantly outperforms others. The proposed combustor anomaly detection approach is effective in detecting combustor anomalies or faults.