摘要
为科学合理地使用公路养护资金,需要制订与之配套的公路养护预算定额。传统的定额编制多采用现场技术测定法,虽然能够准确地确定定额的消耗量,但需要投入大量的资源。为快速、准确地确定公路养护定额的消耗量,本文提出基于SSA-BP神经网络的定额消耗量预测方法。通过SSA算法对BP神经网络的权值及阈值进行优化,结合有限的定额现场技术测定数据,对SSA-BP神经网络预测模型进行训练和检验,并和BP神经网络预测模型进行对比分析。结果表明:SSA-BP神经网络预测模型对定额消耗量的拟合效果优异,能够有效预测公路养护作业定额人工、机械的消耗量,且SSA-BP神经网络预测模型的误差显著低于传统BP神经网络预测模型。
In order to utilize road maintenance funds in a scientific and rational manner,it is necessary to formu-late matching budgetary quotas for road maintenance.The traditional quota preparation mostly adopts the on-site technical determination method,which can accurately determine the consumption of the quota,but needs to in-vest a lot of resources.In order to quickly and accurately determine the consumption of road maintenance quota,this paper proposes a quota consumption prediction method based on SSA-BP neural network.The weights and thresholds of BP neural network are optimized by SSA algorithm,and combined with limited quota field technol-ogy determination data,the SSA-BP neural network prediction model is trained and tested,and compared and analyzed with BP neural network prediction model.The results show that the SSA-BP neural network prediction model has excellent fitting effect on the quota consumption and can effectively predict the consumption of quota labor and machinery for highway maintenance operations,and the error of the SSA-BP neural network prediction model is significantly lower than that of the traditional BP neural network prediction model.
作者
赵武辉
王康
于利存
ZHAO Wuhui;WANG Kang;YU Licun(Xianyang Highway Bureau,Xianyang 712000,China;CCCC First Highway Consultants Co.,Ltd.,Xi’an 710075,China)
出处
《青海交通科技》
2025年第1期104-109,共6页
Qinghai Transportation Science and Technology
关键词
SSA优化算法
BP神经网络
定额编制
公路养护工程
SSA optimization algorithm
BP neural network
quota preparation
road maintenance works
