Development of an artificial neural network model for combined heat and power micro gas turbines

Micro gas turbines are considered as efficient alternative to costly centralized generation and transmission of electricity, especially in remote areas, and in combined heat and power (CHP) applications. Tools for monitoring and diagnostic, which are easy to apply, would be needed for realization of distributed CHP. This paper reports development of a validated artificial neural network (ANN) for monitoring of a micro gas turbine. This study is based on experimental data obtained from a Turbec T100 micro gas turbine. The gas turbine test rig used in this study consists of a modified engine with extended measurement points, providing extensive data suitable for data-driven modeling. The ANN model developed was based on multilayer feed forward network with back propagation algorithm. The mean relative error (MRE) has been used to evaluate the prediction accuracy of the network. The developed ANN model is validated with unseen experimental data, not used during the training, where very good accuracy was observed.