论文部分内容阅读
针对高速公路沥青路面养护管理的需求,将小波变换理论与模糊神经网络结合起来,建立用于高速公路沥青路面性能预测的小波模糊神经网络。对路面性能的原始数据列进行小波分析后,再通过样本学习训练,获取预测的数据列,最后通过重构获得路面性能的预测数据列。将小波模糊网络与一般神经网络的预测结果相比较,结果表明:采用小波模糊神经网络对高速公路沥青路面性能预测可降低人为因素影响,保证预测结果尽可能客观,提高预测效率。
Aiming at the demand of expressway asphalt pavement maintenance and management, the wavelet transform theory and fuzzy neural network are combined to establish the wavelet fuzzy neural network used to predict the performance of expressway pavement. Wavelet analysis is performed on the original data series of pavement performance, and then through the sample learning and training, the predicted data series are obtained. Finally, the predicted data series of pavement performance are obtained through reconstruction. Comparing the results of wavelet fuzzy network and general neural network, the results show that using wavelet neural network to predict the performance of expressway pavement can reduce the influence of human factors, and ensure the prediction results are as objective as possible and the prediction efficiency is improved.