基于BP神经网络的沉降预测模型应用

Prediction Model of Settlement based on BP Neural Network

人工神经网络是一个拥有高度非线性映射能力的计算模型,有较强的动态处理能力,在对其进行研究的基础上,利用MATLAB建立了BP神经网络的建筑物沉降预测模型,用于指导建筑物的沉降预警工作。通过将建筑物沉降的实测数据和模型的预测数据进行对比分析发现,两者间的误差相对较小,预测模型能很好地反映出建筑物沉降的发展趋势,对于建筑物沉降预警工作有着极其重要的意义。

The artificial neural network （ANN） is a computing model that has highly nonlinear mapping ability and strong dynamic processing capabilities. In the paper, on the basis of deep research, Used MATLAB to build BP neural network of building settlement prediction model for guiding building settlement early warning. Compared with building settlement of the measured data and model forecast data, it was found that the error between the two is relatively small and the prediction model reflected the development trend of building settlement accurately. So it has an important significance for building settlement early warning