Engineering Project Risk Prediction Model Based on Prairie Dog Optimizes Support Vector Regression Machine
周来俭 1陈小卫2
扫码查看
点击上方二维码区域,可以放大扫码查看
作者信息
1. 航天工程大学 航天保障系,北京 101416;中国西安卫星测控中心,陕西 西安 710043
2. 航天工程大学 航天保障系,北京 101416
折叠
摘要
在施工项目领域,有效风险预测对于施工项目的顺利完成至关重要.针对传统风险预测模型难以实现非线性条件下的风险预测问题,提出了一种基于土拨鼠优化算法支持向量回归机(Prairie Dog Optimization Algorithm Optimizes Support Vector Regression Machine,PDO-SVR)的施工项目风险预测模型.该模型利用SVR强大的非线性预测能力,对施工项目的风险进行预测,针对人工选择SVR参数存在不合理的问题,利用PDO对SVR参数进行优化.实验结果表明,PDO-SVR模型具有更低的预测误差和良好的预测效果.
Abstract
In the field of engineering projects,effective risk prediction is crucial for the smooth completion of engineering projects.To address the challenge of traditional risk prediction models not being able to achieve risk prediction under non-linear conditions,a new engineering project risk prediction model based on Prairie Dog Optimization Algorithm Optimizes Support Vector Regression Machine(PDO-SVR)is proposed.This model uses the powerful non-linear prediction ability of SVR to predict the engineering project risk.Aiming at the unreasonable problem of manual selection of SVR parameters,PDO is used to optimize SVR parameters.Experimental results demonstrate that the PDO-SVR model has lower prediction errors and good prediction performance.