autoencoders; data enhancement; denoising; mHAT cycle; micro gas turbine; systems engineering; Auto encoders; Data enhancement; De-noising; Digital solutions; Energy systems; MHAT cycle; Micro gas turbine; Micro-gas; Neural-networks; Performance management; Engineering (all)
Abstract :
[en] Globally the energy sector is being transformed by innovations based on decarbonization, decentralization, and digitalization. These encompass transitioning towards a future with distributed generation systems having an increased share of renewables, artificial intelligence, and digital solutions. Micro-gas turbines are a competitive enabling technology in distributed power generation owing to benefits like fuel flexibility, reduced operation and maintenance costs, and emissions. However, its economic performance stumbles when not running in combined heat and power mode, requiring cycle modifications to increase electrical efficiency. The humidified micro-gas turbine is one such modification that shows great potential. For its viability in digitalized future energy systems with ever-growing amounts of data, there needs to be reliable and deployable advanced tools for performance and health management. This requires access to sufficient quality data, making data quality management an essential need. Therefore, the study presented in this paper investigates the use of a special type of artificial neural network called an autoencoder for data enhancement of a humidified micro-gas turbine. Data from 15 sensors has been enhanced by denoising for use in any subsequent data-driven insight and decision. To achieve this, different neural network models have been developed and compared to predict the denoised values. The auto-encoder network model that can best produce satisfactory denoised results has been identified as having 3 bottleneck and 6 mapping layer nodes. Furthermore, a systems engineering framework has been adopted for effective information and complexity management amongst all stakeholders. The framework sets a foundation for employing model-based systems engineering concepts in developing digital solutions. The results demonstrate the functionality of deploying denoising autoencoders with a systems engineering approach for data quality management of the humidified micro-gas turbine. The outcomes from this work can be used for data-driven performance and health management of the humidified micro-gas turbine. This will improve the system’s reliability and promote its use in energy systems of the future.
Disciplines :
Energy
Author, co-author :
Jamil, Ahmad; Department of Energy and Petroleum Engineering, University of Stavanger, Stavanger, Norway
European Environmental Agency, “Share of Energy Consumption from Renewable Sources in Europe (8th EAP)” [Online]. Available: https://www.eea.europa.eu/ims/share-of-energyconsumption-from. [Accessed: 28-Aug-2023].
GE Power, 2018, “The Digital Energy Transformation,” Gen. Electr., p. 56.
Li, J., and Li, Y., 2023, “Micro Gas Turbine: Developments, Applications, and Key Technologies on Components,” Propuls. Power Res., 12(1), pp. 1–43.
Darrow, K., Tidball, R., Wang, J., and Hampson, A., 2015, “Catalog of CHP Technologies: Section 5. Technology Characterization – Microturbines,” U.S. Environmental Protection Agency Combined Heat and Power Partnership.
Banihabib, R., Lingstädt, T., Wersland, M., Kutne, P., and Assadi, M., 2024, “Development and Testing of a 100 KW Fuel-Flexible Micro Gas Turbine Running on 100% Hydrogen,” Int. J. Hydrogen Energy, 49, pp. 92–111.
Nikpey Somehsaraei, H., Mansouri Majoumerd, M., Breuhaus, P., and Assadi, M., 2014, “Performance Analysis of a Biogas-Fueled Micro Gas Turbine Using a Validated Thermodynamic Model,” Appl. Therm. Eng., 66(1–2), pp. 181–190.
De Paepe, W., Montero Carrero, M., Bram, S., Parente, A., and Contino, F., 2018, “Toward Higher Micro Gas Turbine Efficiency and Flexibility—Humidified Micro Gas Turbines: A Review,” J. Eng. Gas Turbines Power, 140(8).
Montero Carrero, M., De Paepe, W., Bram, S., Musin, F., Parente, A., and Contino, F., 2016, “Humidified Micro Gas Turbines for Domestic Users: An Economic and Primary Energy Savings Analysis,” Energy, 117, pp. 429–438.
De Paepe, W., Delattin, F., Bram, S., Contino, F., and De Ruyck, J., 2013, “A Study on the Performance of Steam Injection in a Typical Micro Gas Turbine,” Volume 5A: Industrial and Cogeneration; Manufacturing Materials and Metallurgy; Marine; Microturbines, Turbochargers, and Small Turbomachines, American Society of Mechanical Engineers.
Belokon, A. A., Khritov, K. M., Klyachko, L. A., Tschepin, S. A., Zakharov, V. M., and Opdyke, G., 2002, “Prediction of Combustion Efficiency and NOx Levels for Diffusion Flame Combustors in HAT Cycles,” Volume 1: Turbo Expo 2002, ASMEDC, pp. 791–797.
Ferrarotti, M., De Paepe, W., and Parente, A., 2021, “Reactive Structures and NOx Emissions of Methane/Hydrogen Mixtures in Flameless Combustion,” Int. J. Hydrogen Energy, 46(68), pp. 34018–34045.
De Paepe, W., Sayad, P., Bram, S., Klingmann, J., and Contino, F., 2016, “Experimental Investigation of the Effect of Steam Dilution on the Combustion of Methane for Humidified Micro Gas Turbine Applications,” Combust. Sci. Technol., 188(8), pp. 1199–1219.
Göke, S., Schimek, S., Terhaar, S., Reichel, T., Göckeler, K., Krüger, O., Fleck, J., Griebel, P., and Oliver Paschereit, C., 2014, “Influence of Pressure and Steam Dilution on NOx and CO Emissions in a Premixed Natural Gas Flame,” J. Eng. Gas Turbines Power, 136(9).
De Paepe, W., Montero Carrero, M., Bram, S., and Contino, F., 2014, “T100 Micro Gas Turbine Converted to Full Humid Air Operation: Test Rig Evaluation,” Volume 3A: Coal, Biomass and Alternative Fuels; Cycle Innovations; Electric Power; Industrial and Cogeneration, American Society of Mechanical Engineers.
Tahan, M., Tsoutsanis, E., Muhammad, M., and Abdul Karim, Z. A., 2017, “Performance-Based Health Monitoring, Diagnostics and Prognostics for Condition-Based Maintenance of Gas Turbines: A Review,” Appl. Energy, 198, pp. 122–144.
Dai, X., and Gao, Z., 2013, “From Model, Signal to Knowledge: A Data-Driven Perspective of Fault Detection and Diagnosis,” IEEE Trans. Ind. Informatics, 9(4), pp. 2226–2238.
Colquhoun, K., Nikpey Somehsaraei, H., and De Paepe, W., 2022, “The Application of an Artificial Neural Network As a Baseline Model For Condition Monitoring of Innovative Humidified Micro Gas Turbine Cycles,” Volume 4: Cycle Innovations; Cycle Innovations: Energy Storage, American Society of Mechanical Engineers, pp. 1–10.
Somehsaraei, H. N., Iaria, D., Al Zaili, J., Assadi, M., Sayma, A., and Ghavami, M., 2019, “Application of Artificial Neural Networks for Monitoring and Optimum Operation Prediction of Solar Hybrid MGT Systems,” Volume 3: Coal, Biomass, Hydrogen, and Alternative Fuels; Cycle Innovations; Electric Power; Industrial and Cogeneration; Organic Rankine Cycle Power Systems, American Society of Mechanical Engineers.
De Paepe, W., Pappa, A., Coppitters, D., Carrero, M. M., Tsirikoglou, P., and Contino, F., 2021, “Recuperator Performance Assessment in Humidified Micro Gas Turbine Applications Using Experimental Data Extended with Preliminary Support Vector Regression Model Analysis,” J. Eng. Gas Turbines Power, 143(7), pp. 1–11.
Aslanidou, I., Rahman, M., Zaccaria, V., and Kyprianidis, K. G., 2021, “Micro Gas Turbines in the Future Smart Energy System: Fleet Monitoring, Diagnostics, and System Level Requirements,” Front. Mech. Eng., 7.
Qu, C., Zhou, Z., Liu, Z., and Jia, S., 2022, “Predictive Anomaly Detection for Marine Diesel Engine Based on Echo State Network and Autoencoder,” Energy Reports, 8, pp. 998–1003.
Jia, X., Han, Y., Li, Y., Sang, Y., and Zhang, G., 2021, “Condition Monitoring and Performance Forecasting of Wind Turbines Based on Denoising Autoencoder and Novel Convolutional Neural Networks,” Energy Reports, 7, pp. 6354–6365.
Willett, K. D., 2020, “Systems Engineering the Conditions of the Possibility (Towards Systems Engineering v2.0),” INCOSE Int. Symp., 30(1), pp. 964–980.
De Paepe, W., Contino, F., Delattin, F., Bram, S., and De Ruyck, J., 2014, “New Concept of Spray Saturation Tower for Micro Humid Air Turbine Applications,” Appl. Energy, 130, pp. 723–737.
De Paepe, W., Carrero, M. M., Contino, F., and Bram, S., 2015, “T100 Micro Gas Turbine Converted to Full Humid Air Operation - A Thermodynamic Performance Analysis,” Proceedings of the ASME Turbo Expo, pp. 1–11.
Montero Carrero, M., De Paepe, W., Magnusson, J., Parente, A., Bram, S., and Contino, F., 2017, “Experimental Characterisation of a Micro Humid Air Turbine: Assessment of the Thermodynamic Performance,” Appl. Therm. Eng., 118, pp. 796–806.
De Paepe, W., Pappa, A., Coppitters, D., Montero Carrero, M., Tsirikoglou, P., and Contino, F., 2021, “Control Strategy Development for Optimized Operational Flexibility From Humidified Micro Gas Turbine: Saturation Tower Performance Assessment,” Volume 4: Controls, Diagnostics, and Instrumentation; Cycle Innovations; Cycle Innovations: Energy Storage; Education; Electric Power, American Society of Mechanical Engineers.
Nikpey, H., Assadi, M., and Breuhaus, P., 2013, “Development of an Optimized Artificial Neural Network Model for Combined Heat and Power Micro Gas Turbines,” Appl. Energy, 108, pp. 137–148.
Salvador, J., 2017, “Deep Learning,” Example-Based Super Resolution, Elsevier, pp. 113–127.
