Unsupervised anomaly detection of the gas turbine operation via convolutional auto-encoder

Abstract

This paper proposes a combination of convolutional neural network and auto-encoder (CAE) for unsupervised anomaly detection of industrial gas turbines. Autonomous monitoring systems protect the gas turbines, with the settings unchanged in their lifetime. Those systems can not detect any abnormal operation patterns which potentially risk the equipment after long-term exposure. Recently, machine learning and deep learning models are applied for industries to detect those anomalies under the nominal working range. However, for gas turbine protection, not much deep learning (DL) models are introduced. The proposed CAE detects irregular signals in unsupervised learning by combining a convolutional neural network (CNN) and auto-encoder (AE). CNN exponentially reduces the computational cost and decrease the amount of training data, by its extraction capabilities of essential features in spatial input data. A CAE identifies the anomalies by adapting characteristics of an AE, which identifies any errors larger than usual pre-trained, reconstructed errors. Using the Keras library, we developed an AE structure in one-dimensional convolution layer networks. We used actual plant operation data set for performance evaluation with conventional machine learning (ML) models. Compared to the isolation forest (iforest), k-means clustering (k-means), and one-class support vector machine (OCSVM), our model accurately predicts unusual signal patterns identified in the actual operation than conventional ML models.