基于EMD-SSA-BiLSTM的桥址区短期风速预测  

Short-Term Wind Speed Prediction in Bridge Area Based on EMD-SSA-BiLSTM Method

作　　者：王少钦 林婧姝 郭明浩 WANG Shao-qin;LIN Jing-shu;GUO Ming-hao(School of Science,Beijing University of Civil Engineering and Architecture,Beijing 100044,China;School of Civil and Transportation Engineering,Beijing University of Civil Engineering and Architecture,Beijing 100044,China)

机构地区：[1]北京建筑大学理学院,北京100044 [2]北京建筑大学土木与交通工程学院,北京100044

出　　处：《计算机仿真》2025年第3期549-555,共7页Computer Simulation

摘　　要：为精准、高效的预测桥梁短期风速,提出一种可适于工程推广的短期风速预测方法。即采用经验模态分解法(EMD)将原始风速序列进行分解,得到不同尺度的分解分量(IMF),对每个IMF分量分别建立双向长短期记忆网络模型(BiLSTM),通过麻雀搜索算法(SSA)对其超参数的设置进行优化,从而实现短期风速预测。以青洲大桥风速监测数据作为仿真对象展开建模试验并与其它预测模型进行对比,以均方根误差(RMSE)、平均绝对误差(MAE)和平均绝对百分位数误差(MAPE)作为性能评价指标。研究结果表明:EMD-SSA-BiLSTM模型的RMSE、MAE和MAPE分别为0.13、0.09、3.15%,显著低于其余预测模型。说明该模型预测精准性较高,可为桥梁的运营、防灾减灾提供可靠参考。In order to accurately and efficiently predict the short-term wind speed of bridges,a short-term wind speed prediction method is proposed that is suitable for engineering extension.The empirical modal decomposition(EMD)method is used to decompose the original wind speed series to obtain decomposition components(IMF)at different scales.A bidirectional long short-term memory network model(BiLSTM)is established for each IMF component,and its hyperparameters are optimized by the sparrow search algorithm(SSA)to achieve short-term wind speed prediction.The wind speed monitoring data from the Qingzhou Bridge were used as the simulation object for the modeling experiments and compared with other forecasting models,and the root mean square error(RMSE),mean absolute error(MAE)and percentile mean absolute error(MAPE)were used as performance evaluation indicators.The results show that the RMSE,MAE,and MAPE of the EMD-SSA-BiLSTM model are 0.13,0.09,and 3.15%,respectively,which is significantly lower than other prediction models.This indicates that the model has high predictive accuracy and can provide a reliable reference for bridge operation,disaster prevention and mitigation.

关 键 词：风速预测 麻雀搜索算法 经验模态分解 双向长短期记忆网络 桥梁 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]