摘要
针对大数据环境下电力工程造价在精准化、动态化等方面存在的不足,提出了一种基于BIM与CNN的电力工程造价优化算法。利用BIM技术的特点进行电力工程全生命周期的造价管理,实现了造价的动态化管控。并且采用Levenberg-Marquardt规则算法改进卷积神经网络,通过改进后的CNN网络对每个工程环节的造价完成预测,从而优化整个工程的施工方案。结合相关的电力工程造价数据,基于Matlab对所提算法进行实验测试。结果表明,当学习率为0.010时CNN网络的性能最佳,所提算法的预测准确率为94%,并且与造价的真实值最为接近。
In view of the shortcomings of power engineering cost optimization in precision and dynamic aspects of big data environment,a power engineering cost optimization algorithm based on BIM and CNN was proposed.The characteristics of BIM technology were used to carry out the whole-life-cycle cost management of power engineering and realize the dynamic control of its cost.The Levenberg-Marquardt rule algorithm was used to improve the convolutional neural network(CNN),and the cost of each engineering link was predicted by the improved CNN network,so as to optimize the construction scheme for entire project.Combined with the relevant power engineering cost data,the as-proposed algorithm was tested by using Matlab.The results show that the performance of CNN network is the best when the learning rate is 0.010,and the prediction accuracy of the as-proposed algorithm is 94%,which is the most close to the real cost value.
作者
王林峰
张文静
刘云
陈志宾
王立功
WANG Linfeng;ZHANG Wenjing;LIU Yun;CHEN Zhibin;WANG Ligong(School of Electrical and Electronic Engineering,Huazhong University of Science and Technology,Wuhan 430074,Hubei,China;Economic and Technological Research Institute,State Grid Hebei Electric Power Co.,Ltd.,Shijiazhuang 050001,Hebei,China;Department of Internet,State Grid Hebei Electric Power Co.,Ltd.,Shijiazhuang 050001,Hebei,China;School of Electrical and Electronic Engineering,North China Electric Power University,Baoding 071003,Hebei,China;School of Electrical and Automation,Wuhan University,Wuhan 430072,Hubei,China;Department of Software Cost,Hebei SECPT Computer Consulting Service Co.,Ltd.,Shijiazhuang 050081,Hebei,China)
出处
《沈阳工业大学学报》
CAS
北大核心
2024年第1期7-12,共6页
Journal of Shenyang University of Technology
基金
河北省自然科学基金重点项目(E2018210044)
河北省教育厅科技项目(QN16214510D)。
