山东建筑大学学报2026，Vol.41Issue(2)：21-32,12.DOI:10.12077/sdjz.2026.02.003
基于LMA的桩式可调风机基础沉降预测研究
Research on settlement prediction of pile-based adjustable wind turbine foundations based on LMA
摘要
Abstract
To mitigate the risks posed by differential settlement in foundations,a novel pile-type adjustable wind turbine foundation was developed.A multi-timescale settlement prediction LSTM-MLP-attention(LMA)model was developed by preprocessing the data using variational mode decomposition(VMD)combined with principal component analysis(PCA),and utilizing long short-term memory networks(LSTM),multilayer perceptron(MLP),and an Attention mechanisms.The results indicate that the preprocessed monitoring data of the wind turbine foundation exhibited a significant correlation with settlement and effectively preserved the core information.The LMA model performed excellently in both short-term(6 h)and long-term(12、24 h)predictions,accurately capturing settlement trends for the next 24 h.关键词
风机基础/神经网络/沉降预测/现场监测/深度学习Key words
wind turbine foundation/neural network/settlement prediction/on-site monitoring/deep learning分类
建筑与水利引用本文复制引用
魏焕卫,刘中华,郑晓,徐强,张昴辉..基于LMA的桩式可调风机基础沉降预测研究[J].山东建筑大学学报,2026,41(2):21-32,12.基金项目
国家自然科学基金项目(41272281) （41272281）
