{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T05:02:32Z","timestamp":1784782952995,"version":"3.55.0"},"reference-count":31,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T00:00:00Z","timestamp":1784592000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Early detection of blade structural degradation is critical for wind turbine reliability, as unplanned failures contribute to approximately 25% of operational downtime. Traditional blade condition monitoring methods based on distributed vibration, strain, or acoustic emission sensing often suffer from high hardware complexity and substantial data-processing requirements. Consequently, blade load measurements at the blade root have emerged as a promising and more practical alternative for structural health monitoring. This study introduces a physics-informed virtual sensing framework that combines high-fidelity aeroelastic simulation with machine learning trained exclusively on healthy operational data for blade degradation detection. The proposed method is based on the premise that, under healthy conditions, the relationship between flapwise and edgewise bending moments remains consistent across operating conditions, whereas structural degradation disrupts this coupling and induces measurable deviations from the learned correlation. To implement this concept, OpenFAST simulations of the NREL 5MW reference turbine are conducted under multiple operating conditions with progressively introduced stiffness degradation, forming a comprehensive dataset. A Random Forest model is trained to predict edgewise bending moments from flapwise loads and structural parameters using only healthy-condition data, achieving high predictive accuracy under healthy operating conditions (R2 = 0.98; MAPE = 3.67%). Fault detection is performed by analysing residuals between predicted and simulated edgewise bending moments, which increase systematically when degradation is present. The proposed framework achieved an overall classification accuracy of 88.9%, sensitivity of 88.9%, precision of 96.0%, F1-score of 0.923, and an AUC of 0.951 across all degradation levels and operating conditions, while achieving 100% detection of severe (20%) torsional stiffness degradation cases. Notably, degradation reduces absolute blade loads due to aeroelastic twist-to-feather coupling, yet introduces distinctive load asymmetry patterns that enable effective discrimination. The method demonstrates strong generalisation across the investigated wind speed conditions without retraining. By reconstructing unmeasured edgewise loads from readily available flapwise measurements, the proposed approach enables scalable structural health monitoring of existing wind turbine fleets without hardware retrofitting, offering a practical pathway toward physics-guided digital twin development.<\/jats:p>","DOI":"10.3390\/a19070604","type":"journal-article","created":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T15:17:52Z","timestamp":1784647072000},"page":"604","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Physics-Informed Virtual Sensing for Wind Turbine Blade Degradation Detection Using Flapwise\u2013Edgewise Load Coupling"],"prefix":"10.3390","volume":"19","author":[{"given":"Attia","family":"Bibi","sequence":"first","affiliation":[{"name":"School of Computing and Engineering, University of Huddersfield, Huddersfield HD1 3DH, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0938-9196","authenticated-orcid":false,"given":"Chiheng","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computing and Engineering, University of Huddersfield, Huddersfield HD1 3DH, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1122-2990","authenticated-orcid":false,"given":"Wenxian","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computing and Engineering, University of Huddersfield, Huddersfield HD1 3DH, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5992-5348","authenticated-orcid":false,"given":"Rakesh","family":"Mishra","sequence":"additional","affiliation":[{"name":"School of Computing and Engineering, University of Huddersfield, Huddersfield HD1 3DH, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,21]]},"reference":[{"key":"ref_1","unstructured":"(2019). Wind Energy Generation Systems-Part 1: Design Requirements (Standard No. IEC 61400-1)."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1107","DOI":"10.1002\/we.1887","article-title":"Failure rate, repair time and unscheduled O&M cost analysis of offshore wind turbines","volume":"19","author":"Carroll","year":"2016","journal-title":"Wind Energy"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"673","DOI":"10.1002\/we.1508","article-title":"Wind turbine condition monitoring: Technical and commercial challenges","volume":"17","author":"Yang","year":"2014","journal-title":"Wind Energy"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2595","DOI":"10.3390\/en7042595","article-title":"Wind turbine condition monitoring: State-of-the-art review, new trends, and future challenges","volume":"7","author":"Tchakoua","year":"2014","journal-title":"Energies"},{"key":"ref_5","first-page":"341","article-title":"Comparative analysis of neural network and regression based condition monitoring approaches for wind turbine fault detection","volume":"45","author":"Schlechtingen","year":"2014","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"382","DOI":"10.1049\/iet-rpg.2016.0248","article-title":"Using SCADA data for wind turbine condition monitoring\u2014A review","volume":"11","author":"Watson","year":"2017","journal-title":"IET Renew. Power Gener."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2242","DOI":"10.3390\/en6042242","article-title":"Torsional stiffness effects on the dynamic stability of a horizontal axis wind turbine blade","volume":"6","author":"Jeong","year":"2013","journal-title":"Energies"},{"key":"ref_8","unstructured":"National Renewable Energy Laboratory (2025, July 08). OpenFAST Documentation. OpenFAST: An Aero-Servo-Elastic Simulation Tool for Wind Turbines, Available online: https:\/\/openfast.readthedocs.io\/en\/main\/."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Jonkman, J., Butterfield, S., Musial, W., and Scott, G. (2009). Definition of a 5-MW Reference Wind Turbine for Offshore System Development.","DOI":"10.2172\/947422"},{"key":"ref_10","first-page":"092010","article-title":"BeamDyn: A high-fidelity wind turbine blade solver in the FAST modular framework","volume":"753","author":"Wang","year":"2016","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"21020","DOI":"10.1109\/ACCESS.2018.2818678","article-title":"A data-driven design for fault detection of wind turbines using random forests and XGBoost","volume":"6","author":"Zhang","year":"2018","journal-title":"IEEE Access"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Moriarty, P.J., and Hansen, A.C. (2005). AeroDyn Theory Manual.","DOI":"10.2172\/15014831"},{"key":"ref_14","unstructured":"Jonkman, B.J. (2026, June 14). TurbSim User\u2019s Guide: Version 2.00.00, Available online: https:\/\/www.nrel.gov\/docs\/libraries\/wind-docs\/turbsim_v2-00-pdf.pdf."},{"key":"ref_15","unstructured":"National Renewable Energy Laboratory (2016). BeamDyn User\u2019s Guide and Theory Manual."},{"key":"ref_16","unstructured":"National Renewable Energy Laboratory (2025, July 19). BeamDyn Coordinate Systems and Input\/Output Description. OpenFAST Documentation, Available online: https:\/\/openfast.readthedocs.io\/en\/main\/source\/user\/beamdyn\/index.html."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1626","DOI":"10.1002\/we.2762","article-title":"Virtual sensors for wind turbines with machine-learning-based time series models","volume":"25","author":"Dimitrov","year":"2022","journal-title":"Wind Energy"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"e70071","DOI":"10.1002\/we.70071","article-title":"Virtual sensing of wind turbine loads with multi-hidden Markov models for above-rated wind speeds","volume":"28","author":"Hassan","year":"2025","journal-title":"Wind Energy"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1155","DOI":"10.5194\/wes-5-1155-2020","article-title":"Augmented Kalman filter with a reduced mechanical model to estimate tower loads on a land-based wind turbine: A step towards digital-twin simulations","volume":"5","author":"Branlard","year":"2020","journal-title":"Wind Energy Sci."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"012032","DOI":"10.1088\/1742-6596\/1222\/1\/012032","article-title":"From SCADA to lifetime assessment and performance optimization: How to use models and machine learning to extract useful insights from limited data","volume":"1222","author":"Dimitrov","year":"2019","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_21","first-page":"1021","article-title":"Structural health monitoring of wind turbine blades using vibration and aeroelastic response analysis","volume":"189","author":"Chen","year":"2022","journal-title":"Renew. Energy"},{"key":"ref_22","first-page":"20140090","article-title":"On damage diagnosis for wind turbine blades using structural dynamics and statistical pattern recognition","volume":"373","author":"Dervilis","year":"2015","journal-title":"Philos. Trans. R. Soc. A"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"119275","DOI":"10.1016\/j.enconman.2024.119275","article-title":"Towards machine learning applications for structural load and power assessment of wind turbine: An engineering perspective","volume":"324","author":"Wang","year":"2025","journal-title":"Energy Convers. Manag."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"526","DOI":"10.1109\/TEC.2012.2189887","article-title":"Fault analysis and condition monitoring of the wind turbine gearbox","volume":"27","author":"Zhang","year":"2012","journal-title":"IEEE Trans. Energy Convers."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.renene.2010.05.014","article-title":"The prediction and diagnosis of wind turbine faults","volume":"36","author":"Kusiak","year":"2011","journal-title":"Renew. Energy"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Tang, M., Zhao, Q., Wu, H., Wang, Z., Meng, C., and Wang, Y. (2021). Review and perspectives of machine learning methods for wind turbine fault diagnosis. Front. Energy Res., 9.","DOI":"10.3389\/fenrg.2021.751066"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1261","DOI":"10.1016\/j.rser.2017.09.100","article-title":"Lifetime extension of onshore wind turbines: A review covering Germany, Spain, Denmark, and the UK","volume":"82","author":"Ziegler","year":"2018","journal-title":"Renew. Sustain. Energy Rev."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1568","DOI":"10.1016\/j.renene.2022.09.032","article-title":"A comprehensive study on structural health monitoring of wind turbine blades by instrumenting tower using machine learning methods","volume":"199","author":"Khazaee","year":"2022","journal-title":"Renew. Energy"},{"key":"ref_29","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_30","doi-asserted-by":"crossref","first-page":"893","DOI":"10.5194\/wes-8-893-2023","article-title":"Overview of normal behavior modeling approaches for SCADA-based wind turbine condition monitoring demonstrated on data from operational wind farms","volume":"8","author":"Chesterman","year":"2023","journal-title":"Wind Energy Sci."},{"key":"ref_31","first-page":"200535","article-title":"Digital twin technology in wind turbine components: A review","volume":"26","author":"Tibaduiza","year":"2025","journal-title":"Intell. Syst. Appl."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/7\/604\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T04:20:57Z","timestamp":1784780457000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/7\/604"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,21]]},"references-count":31,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["a19070604"],"URL":"https:\/\/doi.org\/10.3390\/a19070604","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,21]]}}}