{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T10:19:46Z","timestamp":1779358786050,"version":"3.51.4"},"reference-count":20,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:00:00Z","timestamp":1705017600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Universidad Nacional de Ingenier\u00eda, Lima-Per\u00fa"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Gas turbines are thermoelectric plants with various applications, such as large-scale electricity production, petrochemical industry, and steam generation. In order to optimize the operation of a gas turbine, it is necessary to develop system identification models that allow for the development of studies and analyses to increase the system\u2019s reliability. Current strategies for modeling complex and non-linear systems can be based on artificial intelligence techniques, using autoregressive neural networks of the NARX and LSTM type. In this context, this work aims to develop a model of a gas turbine capable of estimating the rotation speed of the turbine and simultaneously estimating the uncertainty associated with the estimation. These methodologies are based on artificial neural networks and the Monte Carlo dropout simulation method. The results were obtained from experimental data from a 215 MW gas turbine, getting the best model with a MAPE of 0.02% and an uncertainty associated with the turbine rotation speed of 2.2 RPM.<\/jats:p>","DOI":"10.3390\/s24020465","type":"journal-article","created":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T03:54:34Z","timestamp":1705031674000},"page":"465","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Uncertainty Evaluation of a Gas Turbine Model Based on a Nonlinear Autoregressive Exogenous Model and Monte Carlo Dropout"],"prefix":"10.3390","volume":"24","author":[{"given":"Armando","family":"Cajahuaringa","sequence":"first","affiliation":[{"name":"Universidad Nacional de Ingenier\u00eda, Av. Tupac Amaru 210, Rimac, Lima 150101, Peru"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rub\u00e9n Aquize","family":"Palacios","sequence":"additional","affiliation":[{"name":"Universidad Nacional de Ingenier\u00eda, Av. Tupac Amaru 210, Rimac, Lima 150101, Peru"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8760-9390","authenticated-orcid":false,"given":"Juan M.","family":"Mauricio Villanueva","sequence":"additional","affiliation":[{"name":"Universidade Federal da Para\u00edba Campus I, Joao Pessoa 58051-900, PB, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5469-4912","authenticated-orcid":false,"given":"Aurelio","family":"Morales-Villanueva","sequence":"additional","affiliation":[{"name":"Universidad Nacional de Ingenier\u00eda, Av. Tupac Amaru 210, Rimac, Lima 150101, Peru"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jos\u00e9","family":"Machuca","sequence":"additional","affiliation":[{"name":"Universidad Nacional de Ingenier\u00eda, Av. Tupac Amaru 210, Rimac, Lima 150101, Peru"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan","family":"Contreras","sequence":"additional","affiliation":[{"name":"Universidad Nacional de Ingenier\u00eda, Av. Tupac Amaru 210, Rimac, Lima 150101, Peru"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kiara","family":"Rodr\u00edguez Bautista","sequence":"additional","affiliation":[{"name":"Universidad Nacional de Ingenier\u00eda, Av. Tupac Amaru 210, Rimac, Lima 150101, Peru"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2024,1,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Ravichandran, T., Liu, Y., Kumar, A., and Srivastava, A. (2023, January 5\u20137). Convolutional Neural Networks for Gas Turbine Exhaust Gas Temperature and Power Predictions. Proceedings of the 2023 IEEE International Conference on Prognostics and Health Management (ICPHM), Montreal, QC, Canada.","DOI":"10.1109\/ICPHM57936.2023.10193965"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Marin, G., Osipov, B., Titov, A., Akhmetshin, A., Shubina, A., and Novoselova, M. (2022, January 9\u201311). Improving the Performance of Power Plants with Gas Turbine Units. Proceedings of the 2022 4th International Conference on Control Systems, Mathematical Modeling, Automation and Energy Efficiency (SUMMA), Lipetsk, Russian.","DOI":"10.1109\/SUMMA57301.2022.9974004"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Sheludko, V.N., Sokolov, P.V., Andrievsky, O.A., and Andrievskaya, N.V. (2023, January 24\u201326). Gas Turbine Selective Control System. Proceedings of the 2023 XXVI International Conference on Soft Computing and Measurements (SCM), Saint Petersburg, Russian.","DOI":"10.1109\/SCM58628.2023.10159108"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Fentaye, A.D., Baheta, A.T., Gilani, S.I., and Kyprianidis, K.G. (2019). A Review on Gas Turbine Gas-Path Diagnostics: State-of-the-Art Methods, Challenges and Opportunities. Aerospace, 6.","DOI":"10.3390\/aerospace6070083"},{"key":"ref_5","unstructured":"Mai, C.V., Spiridonakos, M.D., Chatzi, E.N., and Sudret, B. (2023, July 18). Surrogate Modelling for Stochastic Dynamical Systems by Combining NARX Models and Polynomial Chaos Expansions. Technical report RSUQ-2016-002, Eidgen\u00f6ssische Technische Hochschule Z\u00fcrich, Germany. Available online: https:\/\/ethz.ch\/content\/dam\/ethz\/special-interest\/baug\/ibk\/risk-safety-and-uncertainty-dam\/publications\/reports\/RSUQ-2016-002.pdf."},{"key":"ref_6","unstructured":"Malmstr\u00f6m, M. (2023, July 18). Uncertainties in Neural Networks: A System Identification Approach. Swedish Licentiate\u2019s Thesis N\u00b0 1902, Department of Electrical Engineering, Link\u00f6ping University, Sweden. Available online: https:\/\/liu.diva-portal.org\/smash\/get\/diva2:1541951\/FULLTEXT01.pdf."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1994","DOI":"10.1016\/j.proeng.2017.09.317","article-title":"Uncertainty Bounds on Higher-Order FRFs from Gaussian Process NARX Models","volume":"199","author":"Worden","year":"2017","journal-title":"Procedia Eng."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"04020070","DOI":"10.1061\/(ASCE)EM.1943-7889.0001792","article-title":"A Kriging\u2013NARX Model for Uncertainty Quantification of Nonlinear Stochastic Dynamical Systems in Time Domain","volume":"146","author":"Bhattacharyya","year":"2020","journal-title":"J. Eng. Mech."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"109197","DOI":"10.1016\/j.ress.2023.109197","article-title":"A parallel GRU with dual-stage attention mechanism model integrating uncertainty quantification for probabilistic RUL prediction of wind turbine bearings","volume":"235","author":"Cao","year":"2023","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"643","DOI":"10.1016\/j.epsr.2016.10.050","article-title":"Estimating photovoltaic power generation: Performance analysis of artificial neural networks, Support Vector Machine and Kalman filter","volume":"143","author":"Monteiro","year":"2017","journal-title":"Electr. Power Syst. Res."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"877","DOI":"10.1016\/j.energy.2014.07.064","article-title":"Heating, cooling, and electrical load forecasting for a large-scale district energy system","volume":"74","author":"Powell","year":"2014","journal-title":"Energy"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1128","DOI":"10.1016\/j.energy.2017.09.006","article-title":"Prediction of the performance and exhaust emissions of a compression ignition engine using a wavelet neural network with a stochastic gradient algorithm","volume":"142","author":"Molkdaragh","year":"2018","journal-title":"Energy"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"6044","DOI":"10.3390\/app12126044","article-title":"Price Forecast for Mexican Red Spiny Lobster (Panulirus spp.) Using Artificial Neural Networks (ANNs)","volume":"12","author":"Seijo","year":"2022","journal-title":"Appl. Sci."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1016\/j.apenergy.2017.04.048","article-title":"Performance-based health monitoring, diagnostics and prognostics for condition-based maintenance of gas turbines: A review","volume":"198","author":"Tahan","year":"2017","journal-title":"Appl. Energy"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1340","DOI":"10.1109\/TR.2018.2822702","article-title":"Performance-Based Gas Turbine Health Monitoring, Diagnostics, and Prognostics: A Survey","volume":"67","author":"Hanachi","year":"2018","journal-title":"IEEE Trans. Reliab."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1016\/j.cja.2022.07.021","article-title":"Digital twin model of gas turbine and its application in warning of performance fault","volume":"36","author":"Minghui","year":"2023","journal-title":"Chin. J. Aeronaut."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"De Giorgi, M.G., Strafella, L., and Ficarella, A. (2021). Neural Nonlinear Autoregressive Model with Exogenous Input (NARX) for Turboshaft Aeroengine Fuel Control Unit Model. Aerospace, 8.","DOI":"10.3390\/aerospace8080206"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"105902","DOI":"10.1016\/j.ast.2020.105902","article-title":"Hybrid MultiGene Genetic Programming\u2014Artificial neural networks","volume":"103","author":"Quarta","year":"2020","journal-title":"Aerosp. Sci. Technol."},{"key":"ref_19","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_20","unstructured":"Gal, Y., and Ghahramani, Z. (2015). Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/2\/465\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T13:45:05Z","timestamp":1760103905000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/2\/465"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,12]]},"references-count":20,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,1]]}},"alternative-id":["s24020465"],"URL":"https:\/\/doi.org\/10.3390\/s24020465","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,12]]}}}