面对快速变化的风速风向,传统偏航控制存在响应滞后和无效偏航等问题,为进一步提高海上风电机组发电能效,提出一种基于机器学习风速风向预测模型的海上风电机组偏航控制策略。首先,对风速风向测量数据进行预处理,采用平均化方法和变分模态分解方法（VMD）,得到不同时间尺度平均风速风向的高频项、中频项、低频项和残差项。基于此,采用基于自注意力机制的长短期记忆卷积神经网络（SA-CNN-LSTM）对风速风向的各频率项和残差项进行超短期预测,构建风速风向预测模型。进一步地,根据风电机组运行状态划分风速区间,构建优化目标函数,结合改进灰狼优化算法（IGWO）与粒子群优化算法（PSO）优化偏航控制参数,设计完成结合预测模型与参数优化的海上风电机组偏航控制策略。算例结果表明,所提偏航控制策略能够通过优化偏航误差、偏航动作和时间提高偏航效率,可有效提升海上风电机组发电能效。
Abstract
To address the issues of response lag and ineffective yaw adjustments in traditional yaw control systems under rapidly changing wind speed and direction, this study proposes a machine learning-based yaw control strategy for offshore wind turbines to further improve power generation efficiency. Firstly, the wind speed and direction measurement data are pre-processed using the averaging and variational mode decomposition （VMD） methods. The wind data is decomposed into high-frequency, mid-frequency, low-frequency, and residual components at different time scales. Based on the processed wind data, a self-attention-based convolutional neural network-long short-term memory （SA-CNN-LSTM） model is developed for ultra-short-term prediction of each frequency component and residual term, which constructs the wind prediction model. Furthermore, wind speed intervals based on turbine operating states are established and an optimal objective function is formulated. Then, the yaw control strategy integrating prediction models with parameters is optimized through the improved grey wolf optimizer （IGWO） and particle swarm optimization （PSO） algorithms. Results demonstrate that the proposed yaw control strategy enhances yaw efficiency by optimizing yaw errors, adjustment actions and timing, which improves the power generation efficiency of offshore wind turbines.
关键词
海上风电机组 /
机器学习 /
预测 /
偏航控制 /
偏航误差 /
优化算法
Key words
offshore wind turbines /
machine learning /
prediction /
yaw control /
yaw error /
optimization algorithm
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] YANG J, FANG L Q, SONG D R, et al.Review of control strategy of large horizontal-axis wind turbines yaw system[J]. Wind energy, 2021, 24(2): 97-115.
[2] 杨建, 王力, 宋冬然, 等. 基于孤立森林与稀疏高斯过程回归的风电机组偏航角零点漂移诊断方法[J]. 中国电机工程学报, 2021, 41(18): 6198-6211.
YANG J, WANG L, SONG D R, et al.Diagnostic method of zero-point shifting of wind turbine yaw angle based on isolated forest and sparse Gaussian process regression[J]. Proceedings of the CSEE, 2021, 41(18): 6198-6211.
[3] 吕松灏, 刘向民, 方超, 等. 基于实际功率曲线阈值筛选的风电机组偏航误差算法研究[J]. 动力工程学报, 2024, 44(8): 1196-1204, 1225.
LV S H, LIU X M, FANG C, et al.Research on yaw error algorithm of wind turbine based on actual power curve threshold screening[J]. Journal of Chinese Society of Power Engineering, 2024, 44(8): 1196-1204, 1225.
[4] SOLOMIN E V, TEREKHIN A A, MARTYANOV A S, et al.Horizontal axis wind turbine yaw differential error reduction approach[J]. Energy conversion and management, 2022, 254: 115255.
[5] 肖玥, 封焯文, 余子鹏, 等. 基于风向预测的新型偏航控制方法[J]. 太阳能学报, 2021, 42(2): 144-149.
XIAO Y, FENG Z W, YU Z P, et al.A novel yaw control method for wind turbines based on predicted wind directions[J]. Acta energiae solaris sinica, 2021, 42(2): 144-149.
[6] 韩兵, 周腊吾, 陈浩, 等. 大型风电机组激光雷达辅助模型预测控制方法[J]. 中国电机工程学报, 2016, 36(18): 5062-5069.
HAN B, ZHOU L W, CHEN H, et al.Approach to model predictive control of large wind turbine using light detection and ranging measurements[J]. Proceedings of the CSEE, 2016, 36(18): 5062-5069.
[7] TANG Z H, ZHAO G N, OUYANG T H.Two-phase deep learning model for short-term wind direction forecasting[J]. Renewable energy, 2021, 173: 1005-1016.
[8] HARBOLA S, COORS V.One dimensional convolutional neural network architectures for wind prediction[J]. Energy conversion and management, 2019, 195: 70-75.
[9] CHEN W T, LIU H, LIN Y G, et al.LSTM-NN yaw control of wind turbines based on upstream wind information[J]. Energies, 2020, 13(6): 1482.
[10] QU C Z, LIN Z W, CHEN P, et al.An improved data-driven methodology and field-test verification of yaw misalignment calibration on wind turbines[J]. Energy conversion and management, 2022, 266: 115786.
[11] 张东东, 崔新维. BP神经网络在风力发电机风向预测中的应用[J]. 太阳能, 2015(3): 47-49.
ZHANG D D, CUI X W.Application of BP neural network in wind direction forecast of wind turbine[J]. Solar energy, 2015(3): 47-49.
[12] 唐振浩, 赵赓楠, 曹生现, 等. 基于SWLSTM算法的超短期风向预测[J]. 中国电机工程学报, 2019, 39(15): 4459-4467.
TANG Z H, ZHAO G N, CAO S X, et al.Very short-term wind direction prediction via self-tuning wavelet long-short term memory neural network[J]. Proceedings of the CSEE, 2019, 39(15): 4459-4467.
[13] 刘诗意, 张超宇, 王桐. 基于风向预测的风电机组偏航优化控制方法[J]. 风机技术, 2023, 65(4): 55-59.
LIU S Y, ZHANG C Y, WANG T.Optimal yaw control method for wind turbine based on wind direction prediction[J]. Compressor, blower & fan technology, 2023, 65(4): 55-59.
[14] XU L, OU Y X, CAI J J, et al.Offshore wind speed assessment with statistical and attention-based neural network methods based on STL decomposition[J]. Renewable energy, 2023, 216: 119097.
[15] SONG D R, YANG J, FAN X Y, et al.Maximum power extraction for wind turbines through a novel yaw control solution using predicted wind directions[J]. Energy conversion and management, 2018, 157: 587-599.
[16] SONG D R, FAN X Y, 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: 267-279.
[17] 魏德, 杨志凌, 张劲草, 等. 一种基于风况预测的优化偏航策略[J]. 风机技术, 2023, 65(2): 85-91.
WEI D, YANG Z L, ZHANG J C, et al.An optimized yaw strategy based on wind speed and direction prediction[J]. Chinese journal of turbomachinery, 2023, 65(2): 85-91.
[18] 陈思, 郭鹏. 基于综合经济效益目标的风电机组偏航控制策略研究[J]. 动力工程学报, 2019, 39(4): 286-292.
CHEN S, GUO P.Study on yaw control strategy for wind turbines based on the target of comprehensive economic efficiency[J]. Journal of Chinese Society of Power Engineering, 2019, 39(4): 286-292.
[19] NADIMI-SHAHRAKI M H, TAGHIAN S, MIRJALILI S. An improved grey wolf optimizer for solving engineering problems[J]. Expert systems with applications, 2021, 166: 113917.
[20] 宋文静, 谢源, 黄文君, 等. 改进灰狼优化算法在变桨距自抗扰控制中的应用[J]. 可再生能源, 2020, 38(7): 905-910.
SONG W J, XIE Y, HUANG W J, et al.Application of improved grey wolf optimization algorithm in variable pitch auto disturbance rejection control[J]. Renewable energy resources, 2020, 38(7): 905-910.
基金
新能源电力系统全国重点实验室开放课题（LAPS24009）; 广东省基础与应用基础研究基金（2021A1515110016）
PDF(4273 KB)
