小生境蚁群-BP神经网络在大坝变形监测中的应用

Deformation Monitoring Model of Dam Based on NACA-BP Neural Network

针对BP神经网络在大坝监测数据预测模型中后期预测精度不高的问题,基于小生境蚁群算法的智能搜索能力和强鲁棒性、BP神经网络对大量的输入-输出模式的非线性映射关系的学习存贮能力,将两种方法结合,用小生境蚁群算法优化BP神经网络的建模方法建立了水平位移观测数据的预测模型,并与ACA-BP神经网络和传统BP神经网络进行了对比分析。结果表明,本文方法可加快BP神经网络收敛速度、增强局部搜索能力,具有更高的预测精度。

Aiming at the low accuracy of BP neural network for dam monitoring prediction model in middle-later period, based on the intelligent search ability and strong robustness of niche ant colony algorithm （NACA） and BP neural network which can learn and store a large number of input-output nonlinear relationship, NACA is used to optimize BP neural network for establishing prediction model of horizontal displacement monitoring data. Compared with the traditional BP neural network prediction model, the results show that NACA-BP neural network method can speed up the convergence rate of BP neural network, enhance local search ability and improve prediction accuracy.