摘要
为了提高近海短期风速的预测精度,提出了一种基于随机布谷鸟搜索算法(Random Cuckoo Search Algorithm,RCSA)和人工神经网络(Artificial Neural Network,ANN)的模型。首先通过引入随机因子改进布谷鸟搜索算法得到了RCSA,建立了预测海上短期风速的RCSA-ANN模型;其次在上海芦潮港建立了测风塔,测得了近海气象数据,并开展了模型的训练;最后与BP-ANN、CSA-ANN模型进行对比和分析,验证了RCSA-ANN模型的精度。结果表明:CSA改进方法简单、可靠且有效,解决了该算法易陷入局部最优的问题;RCSA-ANN模型的平均误差不仅低于BP-ANN模型的,而且远低于CSA-ANN模型的,三种模型的预测精度依次降低;RCSA-ANN模型预测精度高,能对较为波动的风速序列实现准确预测,具有很好的应用潜力。
In order to improve the prediction accuracy of offshore short-term wind speed,a model based on the random cuckoo search algorithm(RCSA)and artificial neural network(ANN)was proposed.Firstly,RCSA was obtained by introducing a random factor into CSA,and then a RCSA-ANN model for predicting offshore short-term wind speed was established.Secondly,the training of the model was carried out by using the offshore meteorological data measured at the wind tower in Luchao Port,Shanghai.Finally,the precision of RCSA-ANN model was verified by compariative analyses.Results show that the improved CSA method is simple,reliable,and effective.And it is not easy to fall into local optimum like other models.Moreover,the average error of the RCSA-ANN model is lower than those of the BP-ANN and CSA-ANN models.Since the RCSA-ANN model can predict fluctuating wind speed sequences with high prediction accuracy,it has a promising potential in the meteorological field.
作者
张建平
于新建
陈栋
纪海鹏
ZHANG Jianping;YU Xinjian;CHEN Dong;JI Haipeng(School of Mechanical Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China;College of Energy and Mechanical Engineering,Shanghai University of Electric Power,Shanghai 200090,China)
出处
《空气动力学学报》
CSCD
北大核心
2022年第4期110-116,共7页
Acta Aerodynamica Sinica
基金
国家自然科学基金(12172228,11572187)
上海市自然科学基金(22ZR1444400)。