基于BP人工神经网络的非饱和黄土湿陷系数计算方法

Study on Artificial Neural Network Method for Calculation the Coefficient of Loess Collapsibility

在综合分析非饱和黄土湿陷系数影响因素的基础上,采用BP人工神经网络方法建立了湿陷系数的计算模型.用西安地区黄土的实测资料作为网络模型的学习训练样本和测试样本,对网络模型的计算结果与实测进行了对比.结果表明,用人工神经网络方法计算非饱和黄土湿陷系数,结果准确、可靠,更接近于实际,为湿陷系数的理论计算提供一种新方法.

Based on the analysis of the main factors influencing coefficient of loess collapsibility, model to calculate coefficient of collapsibility was established by applying the theory of artificial neural network （ANN）. A large amount of test data from Xi＇an was used as learning and training samples to train and test the artificial neural network model. The calculated results of the ANN model and the test values were compared and analyzed. The results show that it is comparatively precise to calculate the subsidence coefficient of ground surface by ANN technology.