灰关联分析与BP人工神经网络在土石坝震害群体预测中的运用

Forecasting Seismic Damage to Buildings based on Grey Relation and Artificial Neural Network Model

利用灰关联识别方法分析各震害影响因子对土石坝抗震性能的影响程度,并筛选出关联程度大的震害影响因子。利用BP人工神经网络非线性模型对震害实例样本进行了训练。结果表明:利用灰关联分析,可得出各因子对土石坝抗震性能影响程度的大小排序,供实际的工程抗震设计参考,基于BP人工神经网络模型的土石坝的震害预测结果与震害实例的实际情况比较吻合。

The paper analyzes the influence factors that affect the earthquake-resistance performance of the earth dam and selects the damage factor with the large degree of association by grey relational analysis. And the actual damage samples are trained by BP artificial neural network model. The research shows that effect to the earthquake-resistance performance of these factors can be obtained by grey relational analysis and it can benefit the actual engineering design of earthquake-resistance of earth dam.It also can be found the prediction results are similar to the actual seismic damage of earth dam bv the grey relational analysis and BP neural network mode.