{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T18:25:08Z","timestamp":1792002308670,"version":"4.4.0"},"reference-count":27,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2025,7,19]],"date-time":"2025-07-19T00:00:00Z","timestamp":1752883200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003593","name":"Brazilian National Council for Scientific and Technological Development\/Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico (CNPq)","doi-asserted-by":"publisher","award":["303986\/2022-0"],"award-info":[{"award-number":["303986\/2022-0"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003593","name":"Brazilian National Council for Scientific and Technological Development\/Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico (CNPq)","doi-asserted-by":"publisher","award":["23.1.8493.1.9"],"award-info":[{"award-number":["23.1.8493.1.9"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003593","name":"Brazilian National Council for Scientific and Technological Development\/Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico (CNPq)","doi-asserted-by":"publisher","award":["2020\/15230-5"],"award-info":[{"award-number":["2020\/15230-5"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]},{"name":"University of S\u00e3o Paulo (USP)","award":["303986\/2022-0"],"award-info":[{"award-number":["303986\/2022-0"]}]},{"name":"University of S\u00e3o Paulo (USP)","award":["23.1.8493.1.9"],"award-info":[{"award-number":["23.1.8493.1.9"]}]},{"name":"University of S\u00e3o Paulo (USP)","award":["2020\/15230-5"],"award-info":[{"award-number":["2020\/15230-5"]}]},{"DOI":"10.13039\/501100001807","name":"FAPESP\u2013S\u00e3o Paulo Research Foundation","doi-asserted-by":"publisher","award":["303986\/2022-0"],"award-info":[{"award-number":["303986\/2022-0"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001807","name":"FAPESP\u2013S\u00e3o Paulo Research Foundation","doi-asserted-by":"publisher","award":["23.1.8493.1.9"],"award-info":[{"award-number":["23.1.8493.1.9"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001807","name":"FAPESP\u2013S\u00e3o Paulo Research Foundation","doi-asserted-by":"publisher","award":["2020\/15230-5"],"award-info":[{"award-number":["2020\/15230-5"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Amid the global shift toward clean energy, wind power has emerged as a critical pillar of the modern energy matrix. To improve the reliability and maintainability of wind farms, this work proposes a novel hybrid fault detection approach that combines expert-driven diagnostic knowledge with data-driven modeling. The framework integrates autoencoder-based neural networks with Failure Mode and Symptoms Analysis, leveraging the strengths of both methodologies to enhance anomaly detection, feature selection, and fault localization. The methodology comprises five main stages: (i) the identification of failure modes and their observable symptoms using FMSA, (ii) the acquisition and preprocessing of SCADA monitoring data, (iii) the development of dedicated autoencoder models trained exclusively on healthy operational data, (iv) the implementation of an anomaly detection strategy based on the reconstruction error and a persistence-based rule to reduce false positives, and (v) evaluation using performance metrics. The approach adopts a fault-specific modeling strategy, in which each turbine and failure mode is associated with a customized autoencoder. The methodology was first validated using OpenFAST 3.5 simulated data with induced faults comprising normal conditions and a 1% mass imbalance fault on a blade, enabling the verification of its effectiveness under controlled conditions. Subsequently, the methodology was applied to a real-world SCADA data case study from wind turbines operated by EDP, employing historical operational data from turbines, including thermal measurements and operational variables such as wind speed and generated power. The proposed system achieved 99% classification accuracy on simulated data detect anomalies up to 60 days before reported failures in real operational conditions, successfully identifying degradations in components such as the transformer, gearbox, generator, and hydraulic group. The integration of FMSA improves feature selection and fault localization, enhancing both the interpretability and precision of the detection system. This hybrid approach demonstrates the potential to support predictive maintenance in complex industrial environments.<\/jats:p>","DOI":"10.3390\/s25144499","type":"journal-article","created":{"date-parts":[[2025,7,21]],"date-time":"2025-07-21T08:47:14Z","timestamp":1753087634000},"page":"4499","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Wind Turbine Fault Detection Through Autoencoder-Based Neural Network and FMSA"],"prefix":"10.3390","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3210-9434","authenticated-orcid":false,"given":"Welker Facchini","family":"Nogueira","sequence":"first","affiliation":[{"name":"Department of Mechatronics and Mechanical Systems Engineering, Polytechnic School, University of Sao Paulo, Sao Paulo 05508-010, SP, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6955-7542","authenticated-orcid":false,"given":"Arthur Henrique de Andrade","family":"Melani","sequence":"additional","affiliation":[{"name":"Department of Mechatronics and Mechanical Systems Engineering, Polytechnic School, University of Sao Paulo, Sao Paulo 05508-010, SP, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9837-7038","authenticated-orcid":false,"given":"Gilberto Francisco Martha","family":"de Souza","sequence":"additional","affiliation":[{"name":"Department of Mechatronics and Mechanical Systems Engineering, Polytechnic School, University of Sao Paulo, Sao Paulo 05508-010, SP, Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,7,19]]},"reference":[{"key":"ref_1","first-page":"21","article-title":"Energia solar fotovoltaica: Uma Revis\u00e3o Bibliogr\u00e1fica","volume":"1","author":"Lana","year":"2015","journal-title":"Eng. On-Line"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Tang, Z., Shi, X., Zou, H., Zhu, Y., Yang, Y., Zhang, Y., and He, J. (2023). Fault Diagnosis of Wind Turbine Generators Based on Stacking Integration Algorithm and Adaptive Threshold. Sensors, 23.","DOI":"10.3390\/s23136198"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Cui, Y., and Tjernberg, L.B. (2022, January 12\u201315). Fault Diagnostics of Power Transformers Using Autoencoders and Gated Recurrent Units with Applications for Sensor Failures. Proceedings of the 17th International Conference on Probabilistic Methods Applied to Power Systems (PMAPS), Manchester, UK.","DOI":"10.1109\/PMAPS53380.2022.9810620"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"103704","DOI":"10.1016\/j.dsp.2022.103704","article-title":"Time Series Anomaly Detection in Power Electronics Signals with Recurrent and ConvLSTM Autoencoders","volume":"130","author":"Radaideh","year":"2022","journal-title":"Digit. Signal Process."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Qi, X., Qiu, T., Zhu, Q., Liu, X., Chen, Y., and Cao, W. (2023, January 22\u201324). A Multiple Time-Scale Arc Fault Detection Method Based on Wavelet Transform and LSTM Autoencoders. Proceedings of the 2023 International Conference on Artificial Intelligence and Computer Systems, Xiamen, China.","DOI":"10.1007\/978-981-99-0553-9_93"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Huynh, P.K., Singh, G., Yadav, O.P., Le, T.Q., and Le, C. (2024, January 22\u201325). Unsupervised Anomaly Detection in Electric Power Networks Using Multi-Layer Auto-Encoders. Proceedings of the 2024 Annual Reliability and Maintainability Symposium (RAMS), Albuquerque, NM, USA.","DOI":"10.1109\/RAMS51492.2024.10457681"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"da Rosa, T.G., de Andrade Melani, A.H., Pereira, F.H., Kashiwagi, F.N., de Souza, G.F.M., and Salles, G.M.D.O. (2022). Semi-Supervised Framework with Autoencoder-Based Neural Networks for Fault Prognosis. Sensors, 22.","DOI":"10.3390\/s22249738"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Bindingsb, O.T., Singh, M., Ovsthus, K., and Keprate, A. (2023). Fault detection of a wind turbine generator bearing using interpretable machine learning. Front. Energy Res., 11.","DOI":"10.3389\/fenrg.2023.1284676"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Du, S., Wan, Y., Zhang, C., and Zhang, S. (2023, January 12\u201314). Anomaly Root Cause Analysis for Wind Turbines Based on Denoising Autoencoder and Sparse Estimation. Proceedings of the 2023 IEEE 12th Data Driven Control and Learning Systems Conference (DDCLS), Xiangtan, China.","DOI":"10.1109\/DDCLS58216.2023.10166052"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Chokr, B., Lemenand, T., Chatti, N., Hammoud, M., and Charki, A. (2024, January 17\u201319). Bi-LSTM Autoencoder SCADA based Unsupervised Anomaly Detection in Real Wind Farm Data. Proceedings of the 2024 IEEE International Conference on Prognostics and Health Management (ICPHM), Spokane, WA, USA.","DOI":"10.1109\/ICPHM61352.2024.10626815"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"100145","DOI":"10.1016\/j.egyai.2022.100145","article-title":"Deep anomaly detection in horizontal axis wind turbines using Graph Convolutional Autoencoders for Multivariate Time series","volume":"8","author":"Miele","year":"2022","journal-title":"Energy AI"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Nogueira, W.F., Melani, A.H.A., Custodio, L.D.R.S., and De Souza, G.F.M. (2025, January 27\u201330). Wind Turbine Fault Detection Through Autoencoder-Based Neural Networks. Proceedings of the 2025 Annual Reliability and Maintainability Symposium (RAMS), Destin, FL, USA.","DOI":"10.1109\/RAMS48127.2025.10935128"},{"key":"ref_13","unstructured":"(2012). Condition Monitoring and Diagnostics of Machines\u2014Part 1: General Guidelines (Standard No. ISO 13379:2012)."},{"key":"ref_14","first-page":"031001","article-title":"Fuzzy-FMSA: Evaluating Fault Monitoring and Detection Strategies Based on Failure Mode and Symptom Analysis and Fuzzy Logic","volume":"6","author":"Murad","year":"2020","journal-title":"ASCE-ASME J. Risk Uncertain. Eng. Syst. Part Mech. Eng."},{"key":"ref_15","unstructured":"Gonzalez, E., Glaessgen, E., and Brecher, C. (November, January 28). Symptom-based risk assessment for feed drives: A FMSA and FMECA approach for evaluating monitoring techniques. Proceedings of the European Conference of the Prognostics and Health Management Society, Salt Lake City, UT, USA."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"103678","DOI":"10.1016\/j.engappai.2020.103678","article-title":"Potential, challenges and future directions for deep learning in prognostics and health management applications","volume":"92","author":"Fink","year":"2020","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_17","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press Book."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"100065","DOI":"10.1016\/j.egyai.2021.100065","article-title":"Autoencoder-based anomaly root cause analysis for wind turbines","volume":"4","author":"Roelofs","year":"2021","journal-title":"Energy AI"},{"key":"ref_19","unstructured":"da Rosa, T.G. (2023). A Fault Prognostic Framework for Complex Engineering Systems Using Autoencoder Type Deep Learning Techniques. [Master\u2019s Thesis, Escola Polit\u00e9cnica da Universidade de S\u00e3o Paulo]."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"da Silva, R.F., de Andrade Melani, A.H., de Carvalho Michalski, M.A., and de Souza, G.F.M. (September, January 28). Failure Mode and Observability Analysis (FMOA): An FMEA-based method to support fault detection and diagnosis. Proceedings of the 32nd European Safety and Reliability Conference (ESREL 2022), Dublin, Ireland.","DOI":"10.3850\/978-981-18-5183-4_R22-03-072"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"107837","DOI":"10.1016\/j.ress.2021.107837","article-title":"A framework to automate fault detection and diagnosis based on moving window principal component analysis and Bayesian network","volume":"215","year":"2021","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Tidriri, K., Braydi, A., and Kazmi, H. (2021, January 25\u201326). Data-driven Decision Making Methodology for Prognostic and Health Management of Wind Turbines. Proceedings of the 2021 Australian & New Zealand Control Conference (ANZCC), Gold Coast, Australia.","DOI":"10.1109\/ANZCC53563.2021.9628240"},{"key":"ref_23","unstructured":"Custodio, L.D.R.S., Melani, A.H.A., Nogueira, W.F., Zachariadis, D.C., and De Souza, G.F.M. (2025, January 15\u201319). Synthetic Monitoring Data Generation for Fault Detection in Wind Turbines. Proceedings of the European Safety and Reliability Conference, Stavanger, Norway. Available online: https:\/\/rpsonline.com.sg\/proceedings\/esrel-sra-e2025\/html\/ESREL-SRA-E2025-P1572.html."},{"key":"ref_24","unstructured":"(2019). Wind Turbines Part 1: Design Requirements (Standard No. IEC 61400)."},{"key":"ref_25","unstructured":"(2022). Condition Monitoring and Diagnostics of Wind Turbines (Standard No. ISO 16079)."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1016\/j.renene.2012.03.003","article-title":"Condition monitoring of wind turbines: Techniques and methods","volume":"46","author":"Tobias","year":"2012","journal-title":"Renew. Energy"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"012005","DOI":"10.1088\/1755-1315\/1073\/1\/012005","article-title":"On the use of Artificial Intelligence for Condition Monitoring in Horizontal-Axis Wind Turbines","volume":"1073","author":"Bonacina","year":"2022","journal-title":"Iop Conf. Ser. Earth Environ. Sci."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/14\/4499\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:12:39Z","timestamp":1760033559000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/14\/4499"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,19]]},"references-count":27,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["s25144499"],"URL":"https:\/\/doi.org\/10.3390\/s25144499","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,19]]}}}