GUO Dongjie, JIA Chengzhen, ZHANG Zhi, et al. Research on Soft Sensing of Wind Turbine Static Yaw Error Based on iNNE-SGPR[J]. 2025, 53(11): 81-90. DOI: 10.20204/j.sp.2025.11010.
Research on Soft Sensing of Wind Turbine Static Yaw Error Based on iNNE-SGPR
To address the issues of low computational efficiency in outlier detection of existing soft-sensing methods and the insufficient accuracy of traditional mathematical statistics, this paper proposes a soft-sensing method for static yaw error in wind turbines based on the isolation nearest neighbor ensemble (iNNE) and sparse gaussian process regression (SGPR). Firstly, conditional judgment and the iNNE algorithm are employed to preprocess historical operational data from wind farms in different terrains. Subsequently, an SGPR model is constructed based on the fully independent training conditional (FITC) approximation, and a soft-sensing model for the yaw error angle is established combined with box-plot analysis. Three evaluation metrics—accuracy, stability, and reliability—are proposed to compare and analyze them against existing machine learning methods and Lidar measurement results. Finally, the annual energy production(AEP) of a 5 MW wind turbine is estimated. Test results demonstrate that the proposed machine learning-based soft-sensing method can estimate the yaw error more accurately, and effective error compensation can enhance the annual energy production of the turbine.
SONG D,CHANG Q,ZHENG S,et al.Adaptive model predictive control for yaw system of variable-speed wind turbines[J].Journal of Modern Power Systems and Clean Energy,2021,9(1):219-224.
SONG D,FAN X,YANG J,et al.Power extraction efficiency optimization of horizontal-axis wind turbines through optimizing control parameters of yaw control systems using an intelligent method[J].Applied Energy,2018,224(8):267-279.
JING B,QIAN Z,PEI Y,et al.Improving wind turbine efficiency through detection and calibration of yaw misalignment[J].Renewable Energy,2020,160(12):1217-1227.
DAEYOUNG C,WON S,KYUNGNAM K,et al.Static and dynamic yaw misalignments of wind turbines and machine learning based correction methods using lidar data[J].IEEE Transactions on Sustainable Energy,2019,10(2):971-982.
CHEN P,LIN Z,XIE Z,et al.Real-time yaw-misalignment calibration and field-test verification of wind turbine via machine learning methods[J].Mechanical Systems and Signal Processing,2024,208:110972.
ZHANG F,GAO S,GAO G,et al.Evaluation of aging characteristics in wind turbine performance based on yaw power loss[J].Sustainable Energy Technologies and Assessments,2024,72:104094.
DAVIDE A,RAVI P,ANDREA L,et al.Diagnosis of wind turbine systematic yaw error through nacelle anemometer measurement analysis[J].Sustainable Energy,Grids and Networks,2023,34:101071.
International Electrotechnical Commission.Wind energy generation systems-Part 12-1:power performance measurements of electricity producing wind turbines(Edition 2.0)[S].Switzerland:Geneva,2017.
QUINONERO-CANDELA J,RASMUSSEN C.A unifying view of sparse approximate gaussian process regression[J].Journal of Machine Learning Research,2005,65(6):1939−1959.
NAISH-GUZMAN A,HOLDEN S.The generalized FITC approximation[C].// The 20th International Conference on Neural Information Processing Systems.New York,USA,2007:1057-1064.