摘要
为解决实际工程中带减振器斜拉索索力测试难度大、精度低的问题,提出一种基于IWPALKCNN-LSTM的带减振器斜拉索索力智能识别方法。对实际工程中的带减振器斜拉索开展动态响应试验,基于试验数据开发了一种可以智能化识别带减振器斜拉索索力的深度学习模型。模型以斜拉索索力、长度、线密度、频率和阶次作为特征输入,首先采用改进狼群算法(improved solf pack algorithm,IWPA)对LSTM神经网络中的超参数进行自适应寻优,然后利用LKCNN-LSTM(large convolutional kernel convolutional neural network-long and short-term memory)进行训练,从而实现对带减振器斜拉索索力的智能识别。训练后的网络在测试集上识别的索力值与实际索力值之间的平均误差为2.024%,均方误差值为0.099 4%,决定系数为0.980 6,索力误差均小于5%。与索力计算公式和其他机器学习算法对比结果表明,该方法可实现带减振器斜拉索索力的智能化精准识别,拥有广阔的应用前景。
In order to address the challenges posed by the complexity and imprecision inherent in assessing cable tension with a damper in practical engineering,an intelligent identification method of the cable tension with damper based on IWPA-LKCNN-LSTM is proposed.The dynamic response test of the cable with a damper in practical engineering is carried out.Based on the data obtained from the test,a deep learning model that can intelligently identify the cable tension with a damper is developed.The model takes the cable tension,length,line density,frequency,and order as the feature inputs.First,the hyperparameters in the LSTM neural network are adaptively optimized by using the IWPA.Then LKCNN-LSTM is used for training.The intelligent recognition of the cable tension with a damper is realized.The average error between the recognized cable tension value on the test set and the actual cable tension value is a mere 2.024%,the mean square error value is only 0.0994%,the coefficient of determination is 0.9806,and the cable tension error is less than 5%.In conclusion,a comparison is made with the formula of cable tension calculation and other machine learning algorithms.The results show that this method can realize the intelligent and accurate recognition of the cable tension with a damper,signifying a broad spectrum of potential applications.
作者
张玉平
姜嘉萍
吴健
储永豪
唐鑫
ZHANG Yuping;JIANG Jiaping;WU Jian;CHU Yonghao;TANG Xin(School of Civil Engineering,Changsha University of Science and Technology,Changsha 410114,P.R.China;Road and Bridge South China Engineering Co.,Ltd.,Zhongshan 528403,Guangdong,P.R.China)
出处
《土木与环境工程学报(中英文)》
北大核心
2026年第2期163-171,共9页
Journal of Civil and Environmental Engineering
基金
国家重点基础研究发展计划(973计划)(2015CB057702)
国家自然科学基金(52078059)。
关键词
斜拉索
索力识别
减振器
深度学习
改进狼群算法
stay cable
tension identification
damper
deep learning
improved wolf pack algorithm(IWPA)
