基于MATLAB下BP神经网络的边坡稳定性预测  

Slope Stability Prediction Research of the BP Neural Network Based on MATLAB

作　　者：李志刚[1] 汤博[1] 

机构地区：[1]河北省水利水电勘测设计研究院,天津300250

出　　处：《水科学与工程技术》2013年第5期25-28,共4页Water Sciences and Engineering Technology

摘　　要：将MATLAB中的BP神经网络引入到边坡稳定性研究中,但由于标准的BP算法存在收敛速度慢、容易陷入局部极小点等缺点,为此采用各种改进及优化的算法,以寻求更适合边坡稳定性预测研究的算法。本文结合了大量边坡实例,经过理论分析和实例测试,能显著提高训练速度、减少收敛周期,达到很好的边坡稳定性预测结果。This article introduces the BP neural network in MATLAB to study the slope stability, but because the standard BP algorithm has the shortcomings of slow convergence speed, easy to fall into local minimum point and so on, so adopt the improved and optimization algorithms to search for the more suitable algorithm for to study the slope stability prediction. This article presents a large amount of slope examples, through theoretical analysis and example test, it can significantly improve the training speed, reduce convergence cycles and achieve good prediction results of the slope stability.

关 键 词：BP神经网络 边坡 稳定性预测 

分 类 号：TV222.2[水利工程—水工结构工程]