径向基函数网络在沥青路面使用性能评价中的应用

Pavement Performance Evaluating Model by Using RBF

为提高沥青路面使用性能评价的科学性和合理性,利用神经网络技术对处理非线性映射问题有较好适应性的特点,开发了基于径向基函数网络的路面使用性能评价模型,模型综合考虑了交通量、温度、面层厚度、PCI指标等10个参数对沥青路面使用性能的影响,选择一定的样本数据进行了网络训练,并将训练好的网络模型的输出值与测试值进行了比较。计算结果表明,径向基函数网络模型弥补了传统评价模型的狭隘性、单一性等缺点,更真实地反映了路面工作性能与各影响因素之间的本构关系,且预估精度能够很好地满足工程实际要求,具有良好的推广性和可靠性。

In order to make the performance evaluation of asphalt pavement more scientific and reasonable, taking advantage of excellent adaptability of neural network technology to deal with nonlinear mapping problem, the pavement performance evaluation model based on radial basis function neural networks was developed. This model takes comprehensive consideration of ten affecting factors including traffic volume, temperature, pavement thickness, pavement condition index （PCI）, etc. and choose certain number of samples data to train and simulate, then compare the output with the test results in networks model trained. The calculating results show that the model makes up the weaknesses of traditional evaluation model such as narrowness and uniqueness, and reflect more realistically the constitutive relations between pavement performance and affecting factors. Predicted accuracy can meet the practical engineering application greatly. This model is worth promoting and trusting.