摘要
针对传统变电工程概算方法存在工作量大且误差较大的问题,文中提出了基于BIM和粒子群(PSO)-支持向量机(SVM)的变电工程智能概算方法。推导SVM模型,分析固定的核函数参数和惩罚系数对SVM模型的影响;提出利用PSO算法优化SVM核函数参数和惩罚系数的改进方法;利用变电工程的BIM模型及特征数据作为PSO-SVM模型的输入,实现变电工程的智能化成本概算。算例分析结果表明,文中所提基于BIM和PSO-SVM的变电工程成本概算方法的误差绝对值均小于10%,相比于传统SVM算法具有更高的准确性,且通过参数优化能够满足不同实际变电工程成本概算需求。
Aiming at the problems of large workload and large errors in the traditional budgetary estimate methods of substation engineering,the article proposes an intelligent budgetary estimate for substation engineering based on BIM and Particle Swarm Optimization(PSO)Support Vector Machine(SVM)method.The SVM model is derived,and the influence of the fixed kernel function parameters and penalty coefficients on the SVM model is analyzed;an improved method of using the PSO algorithm to optimize the SVM kernel function parameters and penalty coefficients is proposed;the BIM model and characteristics of the substation engineering are used.The data is used as the input of the PSO SVM model to realize the intelligent cost estimation of the substation project.The analysis results of the calculation examples show that the absolute value of the error of the BIM and PSOSVMbased substation project cost estimation method proposed in the article is less than 10%.Compared with the traditional SVM algorithm,it has higher accuracy,and can meet the cost estimation needs of different actual substation projects through parameter optimization.
作者
吕征宇
王琼
张彤
LV Zhengyu;WANG Qiong;ZHANG Tong(Economic and Technology Research Institute of State Grid Shanghai Electric Power Company,Shanghai 200002,China)
出处
《电子设计工程》
2021年第22期123-127,共5页
Electronic Design Engineering
基金
国网上海市电力公司2019年度科技创新项目(B3090R190000)。
关键词
支持向量机
粒子群
BIM
成本概算
support vector machine
particle swarm
BIM
cost estimation
