收稿日期: 2023-11-07
修回日期: 2024-03-27
网络出版日期: 2024-11-12
基金资助
晶科科技创新项目(JKP24.02); 江苏省碳达峰碳中和科技创新专项资金(重大科技成果转化)项目(BA2022113); 中国电建集团江西省电力建设有限公司企业创新专项科技项目(JEPCC-KYXM-2023-002)
A Quality Control Method based on Combination Deep Learning for Measurement Data of Complex Mountain Wind Farm
Received date: 2023-11-07
Revised date: 2024-03-27
Online published: 2024-11-12
山地风受地形影响呈现强烈的间隙性、 波动性和非平稳性, 观测质量差, 常规质量控制方法无法有效地提升其观测质量。针对此, 构造一种基于变分模态分解、 卷积神经网络、 门控循环单元组合深度学习的质量控制方法(VCG), 并引入粒子群智能优化策略、 风功率重构模型, 综合提升观测数据质量。为验证该方法的效果, 运用该方法对江西赣州、 四川广元、 安徽芜湖、 湖北黄石、 河南平顶山、 广西贺州某地共6座复杂山地风电场目标观测塔2016年10 min风速、 风向数据进行质量控制, 并与单一机器学习方法、 空间回归方法(SRT)、 反距离加权法(IDW)进行对比。结果表明, 该方法适用于山地风电场的观测风数据的质量控制, 相较于常规方法具有更高的可疑数据检错率; 控制后的数据能更好地还原观测背景场, 应用于风电场的发电量评估业务具有更低的误差率; 且具有地形适应性强的特点。
姚润进 , 程帅兵 , 赵乾乾 , 李文龙 , 钱栋 . 一种基于组合深度学习的复杂山地风电场测风数据质量控制方法[J]. 高原气象, 2024 , 43(6) : 1630 -1638 . DOI: 10.7522/j.issn.1000-0534.2024.00043
Mountainous winds exhibit strong intermittent, fluctuating, and non-stationary characteristics due to the influence of terrain, resulting in poor observation quality, which makes conventional quality control methods unable to effectively improve their observation quality.To address this issue, a quality control method (VCG) based on variational mode decomposition, convolutional neural networks, and deep learning of gated cyclic units is constructed, and a particle swarm optimization strategy and wind power reconstruction model are introduced to comprehensively improve the quality of observation data.To verify the effectiveness of this method, 10 minute wind speed and direction data of target wind turbines in six complex mountainous wind farms in Jiangxi Ganzhou, Sichuan Guangyuan, Anhui Wuhu, Hubei Huangshi, Henan Pingdingshan, and Guangxi Hezhou in 2016 was quality controlled by VCG and compared with single machine learning method, spatial regression method (SRT), and inverse distance weighting method (IDW).The results indicate that VCG method is suitable for quality control of observed wind data in mountainous wind farms, and has a higher error detection rate for suspicious data compared to conventional methods; The controlled data can better restore the observed background field and have a lower error rate when applied to the power generation evaluation business of wind farms; And it has the characteristics of strong terrain adaptability.
null | |
null | |
null | |
null | |
null | |
null | |
null | |
null | |
null | |
null | |
null | |
null | |
null | |
null | |
null | 陈训来, 刘军, 郑群峰, 等, 2021.基于卷积门控循环单元神经网络的临近预报方法研究[J].高原气象, 40(2): 411-423.DOI: 10.7522/j.issn.1000-0534.2020.00023.Chen X L , |
null | |
null | 李庆雷, 古丽格娜, 孔婷, 等, 2024.测风塔资料质量控制及效果检验评估[J].沙漠与绿洲气象, 18(1): 141-148. |
null | |
null | 李霄, 龙俐, 帅士章, 2014.贵州山区测风数据质量控制方法[J].贵州气象, 38(4): 32-35.DOI: 10.3969/j.issn.1003-6598.2014.04.008.Li X , |
null | |
null | 欧阳志远, 史作廷, 石敏俊, 等, 2021."碳达峰碳中和": 挑战与对策[J].河北经贸大学学报, 42(5): 1-11. |
null | |
null | 谭晓晴, 罗斯琼, 舒乐乐, 等, 2022.基于机器学习的土壤温度预估研究综述[J].高原气象, 41(2): 14.DOI: 10.7522/j.issn.1000-0534.2022.00024.Tang X Q , |
null | |
null | 唐贵基, 王晓龙, 2015.参数优化变分模态分解方法在滚动轴承早期故障诊断中的应用[J].西安交通大学学报, 49(5): 73-81.DOI: 10.7652/xjtuxb201505012.Tang G J , |
null | |
null | 屠其璞, 王俊德, 丁裕国, 等, 1984.气象应用概率统计学[M].北京: 气象出版社, 183-186.Tu Q P, Wang J D, Din Y G, et al, 1984.Probability statistics of meteorology application[M].Beijing: China Meteorological Press: 183-186. |
null | 夏侯杰, 肖安, 聂道洋, 2023.基于观测的短时强降水深度学习预报模型[J].高原气象, 42(4): 1005-1017.DOI: 10.7522/j.issn.1000-0534.Xia H J , |
null | |
null | 熊雄, 叶小岭, 张颖超, 等, 2017.基于空间观测差异的地面气温资料质量控制算法研究[J].地球物理学报, 60(3): 912-923. |
null | |
null | 叶星瑜, 叶小岭, 马伟叁, 等, 2022.基于LMD-TCN的高铁沿线风速观测资料质量控制算法研究[J].铁道科学与工程学报, 19(4): 849-856.DOI: 10.19713/j.cnki.43-1423/u.T20210363.Ye X Y , |
null | |
null | 张颖超, 姚润进, 熊雄, 2017.一种基于PSO-MEF的地面气温观测资料的质量控制方法[J].热带气象学报, 33(2): 8.DOI: 10.16032/j.issn.1004-4965.2017.02.014.Zhang Y C , |
null |
/
〈 |
|
〉 |