To ensure the safety of train operation in strong wind environment, a combined prediction model based on VMD (variational mode decomposition), LSTM (long short-term memory neural network) and RIME (frost and ice optimization algorithm) was proposed. Firstly, VMD was used to decompose the original wind speed time series on a multi-scale to obtain modal components with different frequency characteristics. Then, RIME algorithm was used to optimize the hyperparameters of LSTM model to improve the performance of the model. Finally, the experimental verification was carried out based on the wind speed data of several groups along the railway. The results were compared with those predicted by LSTM, EMD-LSTM, VMD-LSTM and VMD-RIME-LSTM models, and a number of error evaluation indexes were obtained. The VMD-RIME-LSTM combined model proposed in this study shows significant advantages in forecasting accuracy and stability. The research results can provide theoretical basis and technical support for wind speed monitoring and early warning along railway lines, and have important practical significance for improving railway running safety.
MENG Jian-jun, WANG Zong-hui, LI Yi-xuan, ZHANG Tong-jian, LÜ Shi-long, MENG Gao-yang.
Wind Speed Prediction along Railway Lines Based on VMD-RIME-LSTM Algorithm[J].
Science Technology and Engineering, 2026, 26(6): 2601-2609 DOI:10.12404/j.issn.1671-1815.2502804
ZhaoChuanhui, LiDecang, LiWenhao, et al. Research on the safety of high-speed trains running in crosswind environment[J]. Science Technology and Engineering, 2024, 24(30): 13136-13144.
JiangXiangjun. Research on wind speed prediction algorithm and early warning system along high-speed railway lines in strong wind environment[D]. Lanzhou: Lanzhou Jiaotong University, 2024.
FengShuanglei, WangZheng, WangWeisheng, et al. Regional wind speed grid prediction method based on CycleGAN[J/OL]. [2025-12-04]. Proceedings of the CSEE. https://link.cnki.net/urlid/11.2107.TM.20250819.1601.004.
GuoShunning, MaXue, YangFan, et al. Short-term wind speed prediction method based on optimal copula correlation analysis[J]. Power System and Clean Energy, 2024, 40(2): 63-72.
NiuZhaoji, LiDecang, XuRuxun, et al. Short-term wind speed prediction method along high-speed railway line based on SABO-LSTM[J]. Science Technology and Engineering, 2025, 25(9): 3880-3887.
JiangJianguo, YangXiaoyan, BiHongbo. Short-term photovoltaic power generation power prediction based on VMD-FE-CNN-BiLSTM[J]. Acta Energiae Solaris Sinica, 2024, 45(7): 462-473.
LiZheng, ZhangJie, XuRuosi, et al. Short-term photovoltaic power prediction based on similar day clustering and PCC-VMD-SSA-KELM model[J]. ActaEnergiae Solaris Sinica, 2024, 45(2): 460-468.
[15]
FenfenL, Bin H, Yunxiao Z. Short-term load forecasting based on CEEMDAN-VMD-GLT model[J]. The Journal of China Universities of Posts and Telecommunications, 2024, 31(6): 1-15.
XiangLing, LiuJianing, SuHao, et al. Research on multi-step prediction of wind speed based on CEEMDAN quadratic decomposition and LSTM[J]. ActaEnergiae Solaris Sinica, 2022, 43(8): 334-339.
DingXinhu, PanXueping, HeDazhuang, et al. Dynamic equivalent modeling of wind farms based on GA-optimized GRU-LSTM-FC combined network[J]. Electric Power Automation Equipment, 2023, 43(8): 119-125.
WangHuabiao, LuGuanjun, LiXiaoyong. Research on the application of space-time fusion mechanism based on convolution and shared weight coefficient long short-term memory network in wind speed prediction[J]. Journal of Solar Energy, 2022, 43(11): 156-165.
XiaoJie, WangZhiyong, YuShuiqin, et al. Thermal error prediction of the feed system of gear grinding machine based on RIME-BP neural network[J]. Journal of Scientific Instrument, 2024, 45(11): 277-286.
HeYibo, JinHong, ZhouChun, et al. Research on non-invasive blood glucose prediction model based on RIME and 1DCNN-LSTM-Attention[J]. Modern Electronic Technology, 2024, 47(18): 83-88.
ZhuTing, YanQisheng. Wind speed prediction method based on modal decomposition and RIME-CNN-BiLSTM-AM[J]. Science Technology and Engineering, 2025, 25(20): 8514-8525.
QinYongfeng, LiGang, QiJinping, et al. Fault diagnosis of lateral shock absorbers for high-speed trains based on RIME-VMD[J]. Journal of Railway Science and Engineering, 2025, 22(3): 942-953.
YangBo, ZhangRui, HuYuanweiji, et al. Array optimization of hybrid wind-solar-wave integrated system based on improved frost and ice optimization algorithm[J]. Southern Power System Technology, 2025, 19(7): 50-61.
XiaoJianhua, YaoZhengyi, QuJianjun, et al. Characteristics and formation mechanism of extreme wind conditions in the 100-mile wind area of Lanzhou-Xinjiang railway[J]. China Railway Science, 2016, 37(3): 130-137.