Towards Predictive Maintenance of a Heavy-Duty Gas Turbine: A New Hybrid Intelligent Methodology for Performance Simulation

Abstract

As the increasing demands of global clean power for the main purpose of lowering environmental pollution, heavy-duty gas turbines are playing an increasingly important role in energy fields because of their low emission, high thermal efficiency, and flexible start-up capacity. Accurate modeling and simulation of the turbine performance is extremely needed to precisely design a large-watt industrial heavy-duty gas turbine while timely monitoring its performance degradation for fault diagnosis, optimal efficiency and predictive maintenance, which is still very challenging due to the high nonlinearity, system complexity, varying conditions, and strong coupling interaction of high-dimension parameters under the harsh operation environment of the turbine. When ambient conditions change, the major components, such as the compressor, combustor, and turbine often display performance degradation to some degree over operating time so that the performance-based maintenance is needed to maximize the productivity of a gas turbine. Generally, the reliability and effectiveness of performance-based maintenance depends on the real-time efficiency monitoring for timely diagnosis and impending deterioration prognosis for predictive maintenance. In order to improve the reliability and availability of gas turbines at various operating conditions, accurate and efficient simulation of a gas turbine performance provides the fundamental to pursue fault diagnosis and predictive maintenance. This paper presents a new physics informed machine learning methodology to achieve this purpose. The thermodynamic model of a complicated single-shaft gas turbine is first created based on the balances of both flow and power in various subsystems including inlet, compressor, turbine, combustor and exhaust. The characteristic curves of compressor and turbine are utilized to accurately represent the physical mechanism and effectively simulate the high nonlinear behaviors of subsystems. Machine learning based feature extraction are employed to preprocess the multivariate raw data of the turbine. Multilayer artificial neural network models, nonlinear autoregressive with exogenous inputs (NARX) with Bayesian regularization algorithm, are explored to efficiently simulate the start-up transient process of the turbine, thus improve the simulation efficiency and accuracy of the complicated system. Multivariate data collected from a real-world industrial heavy-duty gas turbine is employed to illustrate the effectiveness and feasibility of the proposed methodology.