BP时间序列与支持向量机对就地热再生沥青路面沥青指标老化预测对比分析

Comparative Analysis of BP Neural Network Time Series Model and Support Vector Machine Model Prediction of Asphalt Aging Index of Hot in-place Local Recycling Asphalt Pavement

为了对沥青路面在再生-使用-再生周期内沥青老化指标及下次再生时对沥青路面衰变程度进行科学监控,以沈阳至大连以及铁岭至阜新高速公路为依托,采用BP神经网络时间序列模型和支持向量机模型这两种典型的预测方法,对就地热再生沥青路面中沥青老化指标的衰变做出预测并对比分析,借助MATLAB软件实现求解。预测结果分析表明,在有限数据量情况下支持向量机模型预测方法的预测精度较高,在此基础上,并结合辽宁地方再生养护标准,评判出最佳养护时机。

In order to scientifically monitor the aging index of asphalt under the regenerating-usage- regenerating cycle of the asphalt pavement and the decay extent of asphalt pavement under next cycle of regeneration, this paper takes Shenyang to Dalian and Tieling to Fuxin Expressway as object, by means of two typical predication methods of BP neural network time series model and support vector machine model, the aging index of hot in-place recycling asphalt pavement is predicted and analyzed by MATLAB software to achieve the solution. The prediction results show that the support vector machine model has the higher prediction accuracy in the case of limited data. On the basis, the optimal maintenance time is proposed combined with the local regeneration maintenance standard in Liaoning Province.