A data expansion based piecewise regression strategy for incrementally monitoring the wind turbine with power curve

Abstract

An accurate power curve is essential for monitoring the wind turbine because this curve can reflect the operating condition of the equipment. However, some newly installed wind turbines may not have enough training data to fit an accurate power curve and lead to poor monitoring results. In this work, considering the insufficient data, we proposed a data expansion based on piecewise regression strategy to monitor the wind turbine with an incremental monitoring strategy. The proposed method can be divided into the offline modeling stage and the online monitoring stage. During offline modeling, a novel mapping function was first designed to expand the insufficient data by mapping the data of other data sets onto the insufficient target data set. In this way, there will be enough training data for the target wind turbine. Then, a piecewise modeling strategy was designed to condense the information of the expanded data into a small number of samples and then fit the power curve. Based on this strategy, the power curve can be accurately fitted with low computational complexity. During online monitoring, the power was predicted by the power curve, and finally, the operating condition can be monitored by comparing the prediction with the observed power. Meanwhile, an incremental learning strategy was proposed to improve both the prediction and monitoring accuracy by updating the power curve model using the newly arrived data. A real case in the experiment illustrated that the proposed monitoring method can accurately detect abnormal behavior with 92.77% detection accuracy while facing insufficient data.

Keywords

power curve / insufficient data / mapping function / piecewise modeling strategy / incremental monitoring method

References

[1] CascianelliS, AstolfiD, CastellaniF, et al. . Wind turbine power curve monitoring based on environmental and operational data [J]. IEEE Transactions on Industrial Informatics, 2022, 18(8): 5209-5218

[2] LydiaM, KumarS S, SelvakumarA I, et al. . A comprehensive review on wind turbine power curve modeling techniques [J]. Renewable and Sustainable Energy Reviews, 2014, 30: 452-460

[3] MarvugliaA, MessineoA. Monitoring of wind farms’ power curves using machine learning techniques [J]. Applied Energy, 2012, 98: 574-583

[4] Taslimi-RenaniE, Modiri-DelshadM, EliasM F M, et al. . Development of an enhanced parametric model for wind turbine power curve [J]. Applied Energy, 2016, 177: 544-552

[5] ShokrzadehS, JafariJ M, BibeauE. Wind turbine power curve modeling using advanced parametric and nonparametric methods [J]. IEEE Transactions on Sustainable Energy, 2014, 5(4): 1262-1269

[6] ArtigaoE, Martín-MartínezS, Honrubia-EscribanoA, et al. . Wind turbine reliability: A comprehensive review towards effective condition monitoring development [J]. Applied Energy, 2018, 228: 1569-1583

[7] JingH, ZhaoC-hui. Adjustable piecewise regression strategy based wind turbine power forecasting for probabilistic condition monitoring [J]. Sustainable Energy Technologies and Assessments, 2022, 52: 102013

[8] PanditR K, InfieldD. SCADA-based wind turbine anomaly detection using Gaussian process models for wind turbine condition monitoring purposes [J]. IET Renewable Power Generation, 2018, 12(11): 1249-1255

[9] YanJ, LiuY-q, HanS, et al. . Wind power grouping forecasts and its uncertainty analysis using optimized relevance vector machine [J]. Renewable and Sustainable Energy Reviews, 2013, 27613-621

[10] ZhaoC-hui. Perspectives on nonstationary process monitoring in the era of industrial artificial intelligence [J]. Journal of Process Control, 2022, 116: 255-272

[11] TippingM E. Sparse Bayesian learning and the relevance vector machine [J]. Journal of Machine Learning Research, 2001, 1: 211-244

[12] BreschiV, PigaD, BemporadA. Piecewise affine regression via recursive multiple least squares and multicategory discrimination [J]. Automatica, 2016, 73: 155-162

[13] PuahB K, ChongL-W, WongY W, et al. . A regression unsupervised incremental learning algorithm for solar irradiance prediction [J]. Renewable Energy, 2021, 164: 908-925

[14] YuW-k, ZhaoC-h, HuangBiao. Recursive cointegration analytics for adaptive monitoring of nonstationary industrial processes with both static and dynamic variations [J]. Journal of Process Control, 2020, 92: 319-332

[15] JungC, SchindlerD. A global wind farm potential index to increase energy yields and accessibility [J]. Energy, 2021, 231: 120923

[16] KimD Y, KimB S. Differences in wind farm energy production based on the atmospheric stability dissipation rate: Case study of a 30 MW onshore wind farm [J]. Energy, 2022, 239122380

[17] ZhengY-q, ZhaoR-zhen. Characteristics for wind energy and wind turbines by considering vertical wind shear [J]. Journal of Central South University, 2015, 22(6): 2393-2398

[18] ZhangL-x, LiangY-b, LiuX-h, et al. . Effect of blade pitch angle on aerodynamic performance of straight-bladed vertical axis wind turbine [J]. Journal of Central South University, 2014, 21(4): 1417-1427

[19] ZhuY-c, ZhuC-c, TanJ-j, et al. . Anomaly detection and condition monitoring of wind turbine gearbox based on LSTM-FS and transfer learning [J]. Renewable Energy, 2022, 18990-103

[20] ChaiZ, ZhaoC-h, HuangB, et al. . A deep probabilistic transfer learning framework for soft sensor modeling with missing data [J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(12): 7598-7609

[21] ChaiZ, ZhaoC-hui. Multiclass oblique random forests with dual-incremental learning capacity [J]. IEEE Transactions on Neural Networks and Learning Systems, 2020, 31(12): 5192-5203

[22] JingH, ZhaoC-h, GaoF-rong. Non-stationary data reorganization for weighted wind turbine icing monitoring with Gaussian mixture model [J]. Computers & Chemical Engineering, 2021, 147: 107241

[23] ChenJ-h, ZhaoC-hui. Exponential stationary subspace analysis for stationary feature analytics and adaptive nonstationary process monitoring [J]. IEEE Transactions on Industrial Informatics, 2021, 17(12): 8345-8356

[24] WangY-l, ZhuC-c, LiY, et al. . The effect of reduced power operation of faulty wind turbines on the total power generation for different wind speeds [J]. Sustainable Energy Technologies and Assessments, 2021, 45101178

[25] WangY, HuQ-h, LiL-h, et al. . Approaches to wind power curve modeling: A review and discussion [J]. Renewable and Sustainable Energy Reviews, 2019, 116109422

[26] WangR-s, PeethambaranJ, ChenDong. LiDAR point clouds to 3-D urban models: A review [J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, 11(2): 606-627

[27] BIBER P, STRASSER W. The normal distributions transform: A new approach to taser scan matching [C]//Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. IROS’ 96. November 8, 1996, Osaka, Japan. IEEE, 2002: 3. DOI: https://doi.org/10.1109/IROS.1996.570603.

[28] DíezY, RoureF, LladóX, et al. . A qualitative review on 3D coarse registration methods [J]. ACM Computing Surveys, 2015, 47(3): 45

[29] FixE, HodgesJ L. Discriminatory analysis, nonparametric discrimination [J]. International Statistical Review, 1989, 573238-247

[30] SamuiP, DixonB. Application of support vector machine and relevance vector machine to determine evaporative losses in reservoirs [J]. Hydrological Processes, 2012, 26(9): 1361-1369

[31] ChristopherM BChristopher pattern recognition and machine learning [M], 2006, U.K., Springer

[32] van der MaatenL, HintonG. Visualizing data using T-SNE [J]. Journal of Machine Learning Research, 2008, 92579-2625

[33] YuW-k, ZhaoC-hui. Robust monitoring and fault isolation of nonlinear industrial processes using denoising autoencoder and elastic net [J]. IEEE Transactions on Control Systems Technology, 2020, 28(3): 1083-1091