AIMWIND Analytics for asset Integrity Management of Wind farms

• Sakaris, Christos; Sakellariou, John S.; Yang, Yang; Bashir, Musa & Schlanbusch, Rune (2026). 10 MW Floating Offshore Wind Turbine: Damage Detection Along with Damage Magnitude Estimation in the Tower-Base Connection Under Varying Operating Conditions. In Pavlou, Dimitrios; Adeli, Hojjat & Correia, Jose (Ed.), Artificial Intelligence Applications in Engineering and Medicine: Proceedings of the 2nd Olympiad in Engineering Science. Springer. ISSN 9783032197436. p. 255–279. doi: 10.1007/978-3-032-19744-3_21. Full text in Research Archive Show summary

  This study focuses on the damage detection and damage magnitude estimation in the critical connection between the tower and the base of a 10 MW floating offshore wind turbine (FOWT) designed during the ARCWIND project under varying operating conditions (OCs). The study constitutes the sequel of a previous work where the design of a Structural Health Monitoring (SHM) framework for damage detection and damage magnitude estimation to the tendons of the considered FOWT under varying sea and wind conditions has been presented. This SHM framework is extended in this study for exploiting the information obtained from vibration measurements from multiple points on the FOWT via the multivariate version of a data-driven method. This method employs statistical functional models representing the FOWT’s structural dynamics under varying OCs and damage magnitude. Simulated acceleration signals of properly selected directions from two points on the FOWT are obtained via the 10 MW FOWT’s numerical model. The simulations are based on healthy and damage scenarios, with the damage (localized buckling) considered at the critical connection area between the tower and the FOWT platform and implemented via stiffness reduction. The employed method’s performance is for the first time examined using models with different functional subspaces selected via a Genetic Algorithm, Particle Swarm Optimization and Bayesian Optimization. Damage detection and damage magnitude estimation are attempted for 36 and 188 test cases based on the healthy and damaged FOWT correspondingly, with the results indicating flawless damage detection and remarkable magnitude estimation with mean error of almost 3 in stiffness reduction.

• Mathew, Manuel Sathyajith; Mansouri, Mo; Kandukuri, Surya Teja & Omlin, Christian Walter Peter (2024). A Systems Perspective on the Public Perception of Wind Power in Norway. INCOSE International Symposium. 34(1), p. 1429–1446. doi: 10.1002/iis2.13217. Full text in Research Archive Show summary

  The Sustainable Development Goals, a set of ambitious targets embraced by United Nations member states, are designed to meet global challenges head-on while shaping a sustainable future. Of these, Goal 7, in particular, focuses on the critical need for affordable, reliable, sustainable, and modern energy for all. Wind energy holds a significant potential in fulfilling Goal 7 of the sustainable development goals. In Norway, there exists a unique scenario, where nearly 98% of electricity is generated from renewable resources. However, without a subsequent increase in power production, a deficit in power is projected by 2027 according to a short-term market analysis by Statnett. To prevent this, it is im-perative to increase the production of electricity from wind. However, in recent years, there has been a significant rise in opposition towards wind power projects in Norway. Some of the wind power projects have even been put on hold because of the increase in protests. In light of this, we apply systems thinking methodologies to improve our understanding of this complex problem. Initially, we identify the stakeholders in our system of interest and categorize them through stakeholder salience analysis framework. Then, we developed a systemigram to graphically represent the system of interest. Finally, we carry out causal loop analysis to find causal loops in our system of interest. Our primary focus with this work is to better understand the factors shaping public perception of wind power projects in Norway. By gaining a deeper understanding about the factors influencing public perception of wind power projects in Norway, we aim to find better solutions to improve the social acceptance of these initiatives in Norway in future works.

• Mathew, Manuel Sathyajith; Kandukuri, Surya Teja & Omlin, Christian Walter Peter (2024). Soft Ordering 1-D CNN to Estimate the Capacity Factor of Windfarms for Identifying the Age-Related Performance Degradation. Proceedings of the European Conference of the Prognostics and Health Management Society (PHME). 8(1), p. 762–770. doi: 10.36001/phme.2024.v8i1.4028. Full text in Research Archive Show summary

  Wind energy plays a vital role in meeting the sustainable development goals set forth by the United Nations. Performance of wind energy farms degrades gradually with aging. For deriving maximum benefits from these capital-intensive projects, these degradation patten should be analyzed and understood. Variations in the capacity factor over the years could be an indication of the age-related degradation of the wind farms. In this study, we propose a novel data-driven model to estimate the capacity factor of wind farms, which could then be used to estimate its age-related performance decline. For this, a 1-dimensional convolutional neural network (1-D CNN) is developed with a soft ordering mechanism under this study. The model was optimized using Huber loss to counteract the effects of outliers in data. The developed model could perform very well in capturing the underlying dynamics in the data as evidenced by a normalized root mean squared error (NRMSE) of 0.102 and a mean absolute error (MAE) of 0.035 on the test dataset.

• Mathew, Manuel Sathyajith; Kandukuri, Surya Teja & Omlin, Christian Walter Peter (2024). Fully Automated Diagnostics of Induction Motor Drives in Offshore Wind Turbine Pitch Systems Using Extended Park Vector Transform and Convolutional Neural Network. Proceedings of the European Conference of the Prognostics and Health Management Society (PHME). 8(1), p. 488–498. doi: 10.36001/phme.2024.v8i1.4030. Full text in Research Archive Show summary

  Due to their location and related complexities, the offshore wind farms (OWF) have higher downtimes and operation and maintenance (O&M) costs compared to their onshore counterparts. Condition monitoring could help in bringing down the O&M costs of OWFs. The pitch system is one of the components most prone to failure. This paper details an approach for enhanced diagnosis of the electric pitch systems especially focusing on the induction motor drives (IMD) in wind turbines. The proposed method uses an extended Park vector approach (EPVA) in conjunction with a convolutional neural network (CNN) to accurately classify the condition of an IMD and localize the faults. The method is validated on data collected from a laboratory setup. The advantage of the proposed approach is that the condition of the IMD can accurately be classified, and faults localized in operating conditions with varying load and frequency without any additional information on the instantaneous operating speed, frequency, or load on the motor drives. This results in a non-invasive diagnostic approach incurring least additional expenses to implement.

• Anastasiadis, Nikolas; Sakaris, Christos; Schlanbusch, Rune & Sakellariou, John (2024). Vibration-Based SHM in the Synthetic Mooring Lines of the Semisubmersible OO-Star Wind Floater under Varying Environmental and Operational Conditions. Sensors. 24(2). doi: 10.3390/s24020543. Full text in Research Archive Show summary

  As the industry transitions toward Floating Offshore Wind Turbines (FOWT) in greater depths, conventional chain mooring lines become impractical, prompting the adoption of synthetic fiber ropes. Despite their advantages, these mooring lines present challenges in inspection due to their exterior jacket, which prevents visual assessment. The current study focuses on vibration-based Structural Health Monitoring (SHM) in FOWT synthetic mooring lines under uncertainty arising from varying Environmental and Operational Conditions (EOCs). Six damage detection methods are assessed, utilizing either multiple models or a single functional model. The methods are based on Vector Autoregressive (VAR) or Transmittance Function Autoregressive with exogenous input (TF- ARX) models. All methods are evaluated through a Monte Carlo study involving 1100 simulations, utilizing acceleration signals generated from a finite element model of the OO-Star Wind Floater Semi 10 MW wind turbine. With signals from only two measuring positions, the methods demonstrate excellent results, detecting the stiffness reduction of a mooring line at levels 10% through 50%. The methods are also tested for healthy cases, with those utilizing TF-ARX models achieving zero false alarms, even for EOCs not encountered in the training data.

• Eid, Mahmoud Sayed Mahmoud; Ali, Ahmed Mohamed Salem; Huynh, van Khang & Robbersmyr, Kjell Gunnar (2024). A Few–Shot Open-Circuit Fault Diagnosis of F-Type Inverters Using CGAN-Based Vision Transformer. IEEE Journal of Emerging and Selected Topics in Power Electronics. ISSN 2168-6777. 13. doi: 10.1109/JESTPE.2024.3478378. Full text in Research Archive Show summary

  Multilevel inverters (MLIs) are widely adopted in various industries due to their distinctive features. However, they are susceptible to higher failure rates due to the increased number of components. Deep learning (DL) models are widely used for accurately diagnosing faults in inverters because they effectively extract features automatically. These models work on the hypothesis of the availability of a sufficient number of samples to train the diagnostic models. However, obtaining enough sample data in engineering practice is difficult, especially in fault cases. Therefore, this article proposes a fault diagnosis scheme combining a conditional generative adversarial network (CGAN) and a vision transformer (ViT) for diagnosing opencircuit (OC) faults with few fault samples (few shots). First, the measured signals are converted to time–frequency images. Afterward, CGAN generates new 2-D sample images with data distributions similar to real samples. Finally, the improved ViT uses the original and generated samples to learn and extract local and global features with a multihead self-attention mechanism and classify the faults. The proposed scheme is validated using an experimental setup of the F-type inverter, and the results show that the suggested scheme outperforms the other conventional DL methods with an accuracy of 98.46% using only six samples per class.

• Konstantinou, Xenophon; Kritikakos, Kyriakos; Lee, Chern Fong; Sakaris, Christos; Sakellariou, John & Schlanbusch, Rune [Show all 7 contributors for this article] (2024). Vibration-based structural health monitoring of the mooring lines in a floating offshore wind turbine under varying environmental conditions: NN vs STS based methods, ISMA2024 - USD2024 Conference proceedings. Curran Associates, Inc.. ISSN 9798331308124. doi: http:/past.isma-isaac.be/downloads/isma2024/proceedings/Contribution_384_proceeding_3.pdf. Full text in Research Archive Show summary

  This study presents a systematic comparison between a Statistical Time Series (STS) and two Neural Network (NN) based methods for the detection of damage in a mooring line of a Floating Offshore Wind Turbine (FOWT) under varying environmental conditions. The comparison investigates the methods’ detection performance, their sensitivity with respect to the selected hyperparameters, and the methods’ computational complexity for a different number of sensors and baseline experiments. The comparison is performed through numerous Monte Carlo numerical experiments under varying wind speed and wave height using vibration signals from a FOWT model including scenarios with the healthy and damaged mooring line. The results indicate the superiority of the STS-based method that achieves perfect detection using only 9 experiments for its training and a single accelerometer, exhibiting additionally lower sensitivity with respect to the selected hyperparameters and computational complexity compared with their NN-based counterparts

View all works in NVA

• Sakaris, Christos & Schlanbusch, Rune (2024). Detecting damages in chain and synthetic mooring lines of Floating Wind Turbines. Full text in Research Archive
• Sakaris, Christos; Schlanbusch, Rune; Anastasiadis, Nikolaos & Kandukuri, Surya Teja (2024). Structural Health Monitoring of synthetic mooring lines for semi-submersible wind floaters under varying environmental conditions. Full text in Research Archive
• Mathew, Manuel Sathyajith (2026). Aging-Aware Multi-Scale Analytics for Wind Farm Asset Management and Performance Monitoring. Universitetet i Agder. ISSN 9788284273150. Full text in Research Archive Show summary

  Vindenergi spiller en avgjørende rolle i den globale overgangen til ren energi. I de siste årene har det blitt bygget ut en betydelig vindkraftkapasitet i kraftsystemene, men et stort antall vindparker i Europa og ellers i verden nærmer seg slutten på sin designede levetid. Når levetiden nærmer seg slutten, står vindparkoperatører i praksis overfor tre valg: (1) levetidsforlengelse, (2) fornyelse/oppgradering av anlegget (repowering), eller (3) demontering og tilbakeføring av anlegget. En effektiv strategi for forvaltning av vindkraftanlegg kan støtte slike beslutninger og bidra til minst mulig tap av verdifulle ressurser, slik som fortsatt levedyktige komponenter og gode lokasjoner. Dette arbeidet utvikler et aldringsbevisst rammeverk for flerskala analyse som legger til rette for effektiv forvaltning av vindparkaktiva. I motsetning til den tradisjonelle, siloorganiserte tilnærmingen til teknisk anleggsforvaltning, foreslås et rammeverk som integrerer både tekniske og sosiale dimensjoner av forvaltningen. Den tekniske dimensjonen behandles på flere skalaer: (1) et automatisk system for feildeteksjon og lokalisering utviklet med en dyp-læringsbasert modell og med minimal utplassering av nye sensorer, (2) en ny dyp-læringsbasert metode for å estimere aldersrelatert ytelsesdegradering i en vindturbin, og (3) en metodikk for å estimere vindparkers kapasitetsfaktor ved hjelp av SCADA-data og en dyplæringsbasert modell, som videre kan utvides til å analysere degradering på parknivå. Samtidig, med utgangspunkt i at selv en teknisk avansert forvaltningsstrategi alene kan være utilstrekkelig gjennom livsløpet til et vindkraftprosjekt, benytter arbeidet også verktøy fra systemtenkning som rammeverk for å analysere hvordan offentlig oppfatning av disse kapitalintensive anleggene formes i en norsk kontekst. Til sammen utgjør disse fire pilarene en verktøykasse for en helhetlig og effektiv forvaltningsstrategi for vindkraftprosjekter, som ivaretar både tekniske og sosiale dimensjoner.

View all works in NVA