Article
Green & Sustainable Science & Technology
Panagiotis Korkos, Matti Linjama, Jaakko Kleemola, Arto Lehtovaara
Summary: The performance of wind turbines can be improved by processing SCADA data, which also enhances decisions about maintenance schedules. The pitch system plays a critical role in analyzing relevant data for improving wind turbine operation. This study demonstrates the potential of the adaptive neuro fuzzy inference system technique for detecting pitch faults by gathering significant pitch faults and implementing the ANFIS technique. The proposed approach includes detailed preprocessing of SCADA data and emphasizes the labeling process.
Article
Computer Science, Artificial Intelligence
Guangyao Zhang, Yanting Li, Yu Zhao
Summary: This paper proposes a novel fault diagnosis method called adaptive multivariate time-series convolutional network (AdaMTCN) to automatically identify the operating state of wind turbines based on SCADA data. The method resamples the data with multiple time steps and uses multivariate time series convolutional networks (MTCN) to extract enriched features. The results show that AdaMTCN has excellent diagnostic performance in dealing with SCADA data with complex characteristics.
ADVANCED ENGINEERING INFORMATICS
(2023)
Article
Green & Sustainable Science & Technology
Wanqiu Chen, Yingning Qiu, Yanhui Feng, Ye Li, Andrew Kusiak
Summary: This study presents a framework for fault diagnosis of wind turbine faults using transfer learning algorithms Inception V3 and TrAdaBoost, and introduces a new evaluation index 'Comprehensive Index'. Traditional machine learning algorithms perform poorly for unbalanced and differently distributed datasets, while the novel transfer learning algorithm TrAdaBoost shows superior performance in dealing with such challenges.
Article
Chemistry, Analytical
Angel Encalada-Davila, Bryan Puruncajas, Christian Tutiven, Yolanda Vidal
Summary: The wind industry views main bearing failures as a critical issue in increasing wind turbine reliability. This study presents a data-based fault prognosis methodology that relies solely on SCADA data, allowing for predictions months in advance without the need for additional sensors. The algorithm is proven to work under different operating conditions, demonstrating its potential to help wind turbine operators plan their operations effectively.
Article
Computer Science, Information Systems
Yilong Shi, Yirong Liu, Xiang Gao
Summary: The paper focuses on wind turbine health data extraction, fault diagnosis model construction, and unit status monitoring using SCADA data, proposing anomaly data processing and optimization schemes, and designing a status monitoring scheme based on the fusion of multi-characteristic monitoring parameters.
Article
Chemistry, Multidisciplinary
Francesco Natili, Alessandro Paolo Daga, Francesco Castellani, Luigi Garibaldi
Summary: The study focuses on the supervision of wind turbine bearings and their integration into industrial practice. By analyzing historical SCADA data and using Support Vector Regression, the study aims to differentiate healthy and damaged wind turbines, with the use of a Novelty Index for identifying the damaged ones.
APPLIED SCIENCES-BASEL
(2021)
Article
Chemistry, Multidisciplinary
Francesco Castellani, Davide Astolfi, Francesco Natili
Summary: This study contributes to wind turbine generator fault diagnosis techniques through SCADA analysis, identifying changes in behavior indicative of impending faults, providing potential advancements in utilizing SCADA data for detecting electrical damage in wind energy applications.
APPLIED SCIENCES-BASEL
(2021)
Article
Green & Sustainable Science & Technology
Xiaohang Jin, Zhuangwei Xu, Wei Qiao
Summary: This article proposes an ensemble approach to detect anomalies and diagnose faults in wind turbines, based on modeling and analyzing historical SCADA data from healthy wind turbines. The method can detect anomalies and diagnose faults before wind turbines have to be shut down for maintenance.
IEEE TRANSACTIONS ON SUSTAINABLE ENERGY
(2021)
Article
Mathematics
Qian Zhang, Yifan Xu, Xueyun Wang, Zelong Yu, Tianyi Deng
Summary: This article presents an innovative method for online calibration of the pitot tube and estimation of wind field, with analysis of the observability of EKF and experimental validation showing the feasibility and effectiveness of the proposed approach.
Article
Green & Sustainable Science & Technology
Ravi Pandit, David Infield, Matilde Santos
Summary: Continuous assessment of wind turbine performance is crucial for maximizing power generation at a low cost. This study aims to quantify and analyze the impact of wind shear and turbulence intensity on wind turbine power curves. The results show that taking these factors into consideration can improve the accuracy and reduce the uncertainty of power curve models.
IEEE TRANSACTIONS ON SUSTAINABLE ENERGY
(2023)
Article
Energy & Fuels
Cristian Velandia-Cardenas, Yolanda Vidal, Francesc Pozo
Summary: Wind power is a cleaner and cheaper energy source compared to others, but challenges related to operation and maintenance of wind farms contribute to increased costs. A fault detection methodology is proposed in this paper to improve alarm detection for wind turbine gearboxes by applying data analysis and processing techniques to real SCADA data.
Article
Green & Sustainable Science & Technology
Davide Astolfi, Ravi Pandit, Ludovica Celesti, Andrea Lombardi, Ludovico Terzi
Summary: The analysis of wind turbine performance is crucial for future operation, and it is necessary to determine the machine's operation based on historical data and control optimization.
SUSTAINABLE ENERGY TECHNOLOGIES AND ASSESSMENTS
(2022)
Article
Energy & Fuels
Henrik M. Bette, Edgar Jungblut, Thomas Guhr
Summary: Modern utility-scale wind turbines utilize a SCADA system to collect vast amounts of operational data, which can be analyzed to enhance turbine maintenance and operation. In this study, we analyze high-frequency SCADA data from the Thanet offshore wind farm in the UK and evaluate Pearson correlation matrices to assess nonstationarity in data dependencies. Our findings indicate distinct correlation structures for different states, with wind speed being the main factor influencing these states. By modeling the boundary wind speeds and incorporating them into our analysis, we account for the nonstationarity and automate preprocessing for future data analysis.
Article
Green & Sustainable Science & Technology
Zakaria Zemali, Lakhmissi Cherroun, Nadji Hadroug, Ahmed Hafaifa, Abdelhamid Iratni, Obaid S. Alshammari, Ilhami Colak
Summary: A wind turbine is an electromechanical system that operates under various production conditions and plays an important role as a renewable energy source. This article proposes and develops a robust and intelligent fault diagnosis structure to ensure the safe and stable operation of the wind turbine. Kalman filters and adaptive and hybrid network-based fuzzy inference systems are used for fault detection and identification.
Article
Energy & Fuels
Davide Astolfi, Francesco Castellani, Andrea Lombardi, Ludovico Terzi
Summary: Wind turbines operate under non-stationary conditions and their power curve analysis is challenging due to the complex relationship between ambient conditions and working parameters. A data-driven approach is commonly employed for monitoring wind turbine performance. This study introduces a method for multivariate wind turbine power curve analysis based on Support Vector Regression with feature selection, showing competitive error metrics and the importance of environmental and operational variables.
Article
Energy & Fuels
Luis A. Martinez-Tossas, Philip Sakievich, Matthew J. Churchfield, Charles Meneveau
Summary: This work revisits the filtered lifting line theory and provides a more general formulation for solving flow problems with significant changes in chord, such as wind turbine blades.