基于FA-ELM深度挖掘模型的电力工程预算控制技术  

Power engineering budget control technology based on FA-ELM deep mining model

作　　者：徐宁[1,3] 张文静 周波[2,3] 董振亮 陈志宾 XU Ning;ZHANG Wenjing;ZHOU Bo;DONG Zhenliang;CHEN Zhibin(School of Electrical and Electronic Engineering,North China Electric Power University,Beijing 102206,China;School of Energy,Power and Mechanical Engineering,North China Electric Power University,Beijing 102206,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;Information Office,Hebei Education Examination Authority,Shijiazhuang 050091,Hebei,China;Department of Software Cost,Hebei SECPT Computer Consulting Service Co.,Ltd.,Shijiazhuang 050081,Hebei,China)

机构地区：[1]华北电力大学电气与电子工程学院,北京102206 [2]华北电力大学能源动力与机械工程学院,北京102206 [3]河北省电力有限公司经济技术研究院,河北石家庄050001 [4]河北省电力有限公司互联网部,河北石家庄050001 [5]河北省教育考试院信息处,河北石家庄050091 [6]河北赛克普泰计算机咨询服务有限公司软件造价部,河北石家庄050081

出　　处：《沈阳工业大学学报》2023年第6期637-642,共6页Journal of Shenyang University of Technology

基　　金：河北省教育厅科技项目(QN16214510D);河北省自然科学基金重点项目(E2018210044)。

摘　　要：针对现有预算控制方法存在目标单一,效果不理想等问题,提出了一种基于FA-ELM深度挖掘模型的电力工程预算控制技术。通过深入剖析电力工程费用的组成与影响因素,提出了工程进度与预算双目标的管控方式。利用萤火虫算法优化极限学习机网络,构建FA-ELM预测模型,将预处理后的电力数据输入FA-ELM模型中,可估计每个阶段的工程费用,便于管理人员采取相应的措施。在MATLAB仿真平台上对所提技术进行实验分析,结果表明:FA-ELM模型的预测误差均控制在6%以内,且工程总费用节约了14.09%,整体性能优于其他对比技术。Aiming at the problems of monotonous objective and unsatisfactory effect of existing budget control methods,a power project budget control technology based on FA-ELM deep mining model was proposed.The composition and influencing factors of electric power project cost were deeply analyzed,thus a dual objectives control mode for project schedule and budget was proposed.The firefly algorithm was used to optimize the limit learning machine network so as to build the FA-ELM prediction model,and the power data after data preprocessing was input into the FA-ELM model to accurately estimate the project cost at each stage,so that the management personnel could take corresponding measures.The experimental analysis on the MATLAB simulation platform shows that the prediction error of FA-ELM model is controlled within 6%,the total project cost is saved by 14.09%,and the overall performance is better than other similar technologies.

关 键 词：电力工程 预算控制 极限学习机网络 数据挖掘 工程进度 萤火虫算法 FA-ELM模型 

分 类 号：TM715[电气工程—电力系统及自动化]