基于蚁群优化神经网络的路基沉降量预测

Prediction of subgrade sedimentation based on ant colony optimization neural network

原有神经网络中自变量数据输入过多时易出现拟合过度征象,从而降低展望模型的准确度。采取蚁群优化神经网络(ACOBP)模型的权值和阈值,经由实测仿真计算,结果表明ACOBP模型的精确度和效果均优于传统神经网络。

When there is too much input of independent variable data in the original neural network,it is easy to appear signs of overfitting,which reduces the accuracy of the prospect model.The weights and thresholds of the ACOBP model are taken,and the results are calculated by actual measurement simulation,and the results show that the accuracy and effect of the ACOBP model are better than those of the traditional neural network.