{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T00:55:22Z","timestamp":1783385722603,"version":"3.54.6"},"reference-count":46,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2023,6,6]],"date-time":"2023-06-06T00:00:00Z","timestamp":1686009600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The performance evaluation of wind turbines operating in real-world environments typically relies on analyzing the power curve, which shows the relationship between wind speed and power output. However, conventional univariate models that consider only wind speed as an input variable often fail to fully explain the observed performance of wind turbines, as power output depends on multiple variables, including working parameters and ambient conditions. To overcome this limitation, the use of multivariate power curves that consider multiple input variables needs to be explored. Therefore, this study advocates for the application of explainable artificial intelligence (XAI) methods in constructing data-driven power curve models that incorporate multiple input variables for condition monitoring purposes. The proposed workflow aims to establish a reproducible method for identifying the most appropriate input variables from a more comprehensive set than is usually considered in the literature. Initially, a sequential feature selection approach is employed to minimize the root-mean-square error between measurements and model estimates. Subsequently, Shapley coefficients are computed for the selected input variables to estimate their contribution towards explaining the average error. Two real-world data sets, representing wind turbines with different technologies, are discussed to illustrate the application of the proposed method. The experimental results of this study validate the effectiveness of the proposed methodology in detecting hidden anomalies. The methodology successfully identifies a new set of highly explanatory variables linked to the mechanical or electrical control of the rotor and blade pitch, which have not been previously explored in the literature. These findings highlight the novel insights provided by the methodology in uncovering crucial variables that significantly contribute to anomaly detection.<\/jats:p>","DOI":"10.3390\/s23125376","type":"journal-article","created":{"date-parts":[[2023,6,7]],"date-time":"2023-06-07T02:02:15Z","timestamp":1686103335000},"page":"5376","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":46,"title":["Condition Monitoring of Wind Turbine Systems by Explainable Artificial Intelligence Techniques"],"prefix":"10.3390","volume":"23","author":[{"given":"Davide","family":"Astolfi","sequence":"first","affiliation":[{"name":"Department of Engineering, University of Perugia, Via G. Duranti 93, 06125 Perugia, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5577-7544","authenticated-orcid":false,"given":"Fabrizio","family":"De Caro","sequence":"additional","affiliation":[{"name":"Department of Engineering, University of Sannio, Piazza Roma 21, 82100 Benevento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7256-2705","authenticated-orcid":false,"given":"Alfredo","family":"Vaccaro","sequence":"additional","affiliation":[{"name":"Department of Engineering, University of Sannio, Piazza Roma 21, 82100 Benevento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,6,6]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"122018","DOI":"10.1016\/j.energy.2021.122018","article-title":"Renewable energy and economic growth: New insight from country risks","volume":"238","author":"Wang","year":"2022","journal-title":"Energy"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1109\/TCST.2021.3056751","article-title":"Distributed demand side management with stochastic wind power forecasting","volume":"30","author":"Scarabaggio","year":"2021","journal-title":"IEEE Trans. Control Syst. Technol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"900","DOI":"10.1049\/iet-rpg.2015.0019","article-title":"Economic analysis of condition monitoring systems for offshore wind turbine sub-systems","volume":"9","author":"May","year":"2015","journal-title":"IET Renew. Power Gener."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"620","DOI":"10.1016\/j.renene.2018.10.047","article-title":"Machine learning methods for wind turbine condition monitoring: A review","volume":"133","author":"Stetco","year":"2019","journal-title":"Renew. Energy"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Maldonado-Correa, J., Mart\u00edn-Mart\u00ednez, S., Artigao, E., and G\u00f3mez-L\u00e1zaro, E. (2020). Using SCADA Data for Wind Turbine Condition Monitoring: A Systematic Literature Review. Energies, 13.","DOI":"10.3390\/en13123132"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1177\/0309524X221124031","article-title":"SCADA data for wind turbine data-driven condition\/performance monitoring: A review on state-of-art, challenges and future trends","volume":"47","author":"Pandit","year":"2023","journal-title":"Wind Eng."},{"key":"ref_7","unstructured":"IEC (2005). Power Performance Measurements of Electricity Producing Wind Turbines, International Electrotechnical Commission. Technical Report 61400-12."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"452","DOI":"10.1016\/j.rser.2013.10.030","article-title":"A comprehensive review on wind turbine power curve modeling techniques","volume":"30","author":"Lydia","year":"2014","journal-title":"Renew. Sustain. Energy Rev."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"109422","DOI":"10.1016\/j.rser.2019.109422","article-title":"Approaches to wind power curve modeling: A review and discussion","volume":"116","author":"Wang","year":"2019","journal-title":"Renew. Sustain. Energy Rev."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"021102","DOI":"10.1115\/1.4053513","article-title":"Improving site-dependent wind turbine performance prediction accuracy using machine learning","volume":"8","author":"Barber","year":"2022","journal-title":"ASCE-ASME J. Risk Uncertain. Eng. Syst. Part B Mech. Eng."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"5209","DOI":"10.1109\/TII.2021.3128205","article-title":"Wind turbine power curve monitoring based on environmental and operational data","volume":"18","author":"Cascianelli","year":"2021","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1658","DOI":"10.1016\/j.egyr.2020.06.018","article-title":"Gaussian process power curve models incorporating wind turbine operational variables","volume":"6","author":"Pandit","year":"2020","journal-title":"Energy Rep."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"e1391","DOI":"10.1002\/widm.1391","article-title":"A historical perspective of explainable Artificial Intelligence","volume":"11","author":"Confalonieri","year":"2021","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"eaay7120","DOI":"10.1126\/scirobotics.aay7120","article-title":"XAI\u2014Explainable artificial intelligence","volume":"4","author":"Gunning","year":"2019","journal-title":"Sci. Robot."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1080\/01621459.2014.977385","article-title":"Power curve estimation with multivariate environmental factors for inland and offshore wind farms","volume":"110","author":"Lee","year":"2015","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"735","DOI":"10.1016\/j.renene.2021.02.136","article-title":"A case study of space-time performance comparison of wind turbines on a wind farm","volume":"171","author":"Ding","year":"2021","journal-title":"Renew. Energy"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1016\/j.renene.2022.11.081","article-title":"Numerical evaluation of multivariate power curves for wind turbines in wakes using nacelle lidars","volume":"202","author":"Sebastiani","year":"2022","journal-title":"Renew. Energy"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"671","DOI":"10.1109\/TSTE.2013.2241797","article-title":"Using data-mining approaches for wind turbine power curve monitoring: A comparative study","volume":"4","author":"Schlechtingen","year":"2013","journal-title":"IEEE Trans. Sustain. Energy"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"032083","DOI":"10.1088\/1742-6596\/2265\/3\/032083","article-title":"Wind Turbine Power Curve Modelling using Gaussian Mixture Copula, ANN Regressive and BANN","volume":"2265","author":"Melero","year":"2022","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1016\/j.engappai.2016.08.003","article-title":"Data-driven multivariate power curve modeling of offshore wind turbines","volume":"55","author":"Janssens","year":"2016","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1007\/s11708-018-0553-3","article-title":"Comparison of modeling methods for wind power prediction: A critical study","volume":"14","author":"Shetty","year":"2020","journal-title":"Front. Energy"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Ackermann, T. (2005). Wind Power in Power Systems, John Wiley & Sons.","DOI":"10.1002\/0470012684"},{"key":"ref_23","first-page":"102013","article-title":"Adjustable piecewise regression strategy based wind turbine power forecasting for probabilistic condition monitoring","volume":"52","author":"Jing","year":"2022","journal-title":"Sustain. Energy Technol. Assess."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"013306","DOI":"10.1063\/5.0074657","article-title":"Wind turbine power prediction based on wind energy utilization coefficient and multivariate polynomial regression","volume":"14","author":"Niu","year":"2022","journal-title":"J. Renew. Sustain. Energy"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1368","DOI":"10.1016\/j.renene.2022.12.001","article-title":"Yaw-adjusted wind power curve modeling: A local regression approach","volume":"202","author":"Nasery","year":"2023","journal-title":"Renew. Energy"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Bilendo, F., Meyer, A., Badihi, H., Lu, N., Cambron, P., and Jiang, B. (2023). Applications and Modeling Techniques of Wind Turbine Power Curve for Wind Farms\u2014A Review. Energies, 16.","DOI":"10.3390\/en16010180"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Astolfi, D., Castellani, F., Lombardi, A., and Terzi, L. (2021). Multivariate SCADA Data Analysis Methods for Real-World Wind Turbine Power Curve Monitoring. Energies, 14.","DOI":"10.3390\/en14041105"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Astolfi, D., and Pandit, R. (2022). Multivariate wind turbine power curve model based on data clustering and polynomial LASSO regression. Appl. Sci., 12.","DOI":"10.3390\/app12010072"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1049\/esi2.12022","article-title":"Correlation analysis of factors affecting wind power based on machine learning and Shapley value","volume":"3","author":"Pang","year":"2021","journal-title":"IET Energy Syst. Integr."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1109\/TSTE.2022.3204453","article-title":"Accounting for environmental conditions in data-driven wind turbine power models","volume":"14","author":"Pandit","year":"2022","journal-title":"IEEE Trans. Sustain. Energy"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Shapley, L. (1953). A value for n-person games. Contributions to the theory of games. Ann. Math. Stud., 307\u2013318.","DOI":"10.1515\/9781400881970-018"},{"key":"ref_32","unstructured":"Sundararajan, M., and Najmi, A. (2020). The many Shapley values for model explanation. arXiv."},{"key":"ref_33","unstructured":"Rasmussen, C.E. (2003). Summer School on Machine Learning, Springer."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1007\/s40095-018-0287-3","article-title":"Comparative assessments of binned and support vector regression-based blade pitch curve of a wind turbine for the purpose of condition monitoring","volume":"10","author":"Pandit","year":"2019","journal-title":"Int. J. Energy Environ. Eng."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.jmp.2018.03.001","article-title":"A tutorial on Gaussian process regression: Modelling, exploring, and exploiting functions","volume":"85","author":"Schulz","year":"2018","journal-title":"J. Math. Psychol."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"100049","DOI":"10.1016\/j.simpa.2020.100049","article-title":"The t-digest: Efficient estimates of distributions","volume":"7","author":"Dunning","year":"2021","journal-title":"Softw. Impacts"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"3273","DOI":"10.1016\/j.egyr.2023.02.007","article-title":"Reliability of electrical and hydraulic pitch systems in wind turbines based on field-data analysis","volume":"9","author":"Walgern","year":"2023","journal-title":"Energy Rep."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"46","DOI":"10.21014\/acta_imeko.v10i2.1037","article-title":"An Innovative Correction Method of Wind Speed for Efficiency Evaluation of Wind Turbines","volume":"10","author":"Carullo","year":"2021","journal-title":"Acta IMEKO"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Amato, A., Heiba, B., Spertino, F., Malgaroli, G., Ciocia, A., Yahya, A.M., and Mahmoud, A.K. (2021, January 8\u201311). An Innovative Method to Evaluate the Real Performance of Wind Turbines with Respect to the Manufacturer Power Curve: Case Study from Mauritania. Proceedings of the 2021 IEEE International Conference on Environment and Electrical Engineering and 2021 IEEE Industrial and Commercial Power Systems Europe (EEEIC\/I&CPS Europe), Piscataway, NJ, USA.","DOI":"10.1109\/EEEIC\/ICPSEurope51590.2021.9584790"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"395","DOI":"10.5194\/wes-3-395-2018","article-title":"Determination of optimal wind turbine alignment into the wind and detection of alignment changes with SCADA data","volume":"3","author":"Mittelmeier","year":"2018","journal-title":"Wind. Energy Sci."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"De Caro, F., Vaccaro, A., and Villacci, D. (2018). Adaptive wind generation modeling by fuzzy clustering of experimental data. Electronics, 7.","DOI":"10.3390\/electronics7040047"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1002\/we.2285","article-title":"Incorporating air density into a Gaussian process wind turbine power curve model for improving fitting accuracy","volume":"22","author":"Pandit","year":"2019","journal-title":"Wind Energy"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Astolfi, D., Pandit, R., Celesti, L., Vedovelli, M., Lombardi, A., and Terzi, L. (2022). Data-Driven assessment of wind turbine performance decline with age and interpretation based on comparative test case analysis. Sensors, 22.","DOI":"10.3390\/s22093180"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Encalada-D\u00e1vila, \u00c1., Puruncajas, B., Tutiv\u00e9n, C., and Vidal, Y. (2021). Wind turbine main bearing fault prognosis based solely on scada data. Sensors, 21.","DOI":"10.3390\/s21062228"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Turnbull, A., Carroll, J., and McDonald, A. (2022). A comparative analysis on the variability of temperature thresholds through time for wind turbine generators using normal behaviour modelling. Energies, 15.","DOI":"10.3390\/en15145298"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"117342","DOI":"10.1016\/j.apenergy.2021.117342","article-title":"Multi-target normal behaviour models for wind farm condition monitoring","volume":"300","author":"Meyer","year":"2021","journal-title":"Appl. Energy"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/12\/5376\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:49:20Z","timestamp":1760125760000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/12\/5376"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,6]]},"references-count":46,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2023,6]]}},"alternative-id":["s23125376"],"URL":"https:\/\/doi.org\/10.3390\/s23125376","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,6]]}}}