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

• Published in: Applied energy 2013-08, Vol.108, p.137-148
• Main Authors: Nikpey, H., Assadi, M., Breuhaus, P.
• Format: Article
• Language: English
• Subjects: algorithms; ANN modeling; Applied sciences; CHP; data; diagnostic techniques; electricity; Energy; Energy. Thermal use of fuels; Engines and turbines; equations; Equipments for energy generation and conversion: thermal, electrical, mechanical energy, etc; Exact sciences and technology; Gas turbines; heat; inputs; Learning theory; Mathematical analysis; Mathematical models; Measurement; Micro gas turbine; Monitoring; Networks; Neural networks; prediction; Sensitivity analysis; turbines
• ISSN: 0306-2619; 1872-9118
• DOI: 10.1016/j.apenergy.2013.03.016

•A well instrumented test rig based on a modified micro gas turbine was set up.•A comprehensive ANN model of a micro gas turbine was developed.•The model was optimized through a systematic sensitivity analysis.•The optimized model was validated as an accurate baseline for condition monitoring.•The model can be used for monitoring at both system and component level. Micro gas turbines are considered an efficient alternative to costly generation and transmission of electricity, especially in remote areas and in combined heat and power (CHP) applications. Tools for remote monitoring and diagnostics, which are easy to apply, would be needed for the realization of distributed CHP. This paper reports the development of a validated artificial neural network (ANN) model for efficient and appropriate 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. ANNs, in contrast to mathematical models, do not require detailed and exact component characteristics, making them applicable for monitoring in many cases. The developed ANN model was based on a multi-layer feed forward network with back-propagation algorithm. Relations between the inputs and outputs of an ANN model are not implemented by physical equations but are built up during the training process. Thus, a systematic sensitivity analysis, conducted in several steps, was performed to investigate the dependency between initially selected input and output parameters. Based on sensitivity analysis results, the “optimized” set of input parameters and final outputs were concluded, taking into account prediction accuracy. The procedure of the ANN model development and sensitivity analysis are discussed in detail. The mean relative error (MRE) was used to evaluate the prediction accuracy of the developed networks with respect to experimental data which were not used during the training. The prediction results showed that the final optimum ANN model can serve as an accurate baseline model for monitoring applications.