BFGS-BP法在变形监测数据处理中的应用

针对传统的BP神经网络算法计算精度低、收敛速度慢的缺点,本文将求解无约束极值问题的非线性最优化方法—BFGS法引入到BP神经网络模型,构建适用于带有不确定性和非线性的结构变形监测数据的处理和预测的BFGS-BP网络模型。并以某隧道施工过程中的拱顶下沉观测数据为例,进行BFGS-BP与传统BP算法的训练和预测对比试验。试验结果表明,与传统的BP算法相比,BFGS-BP模型具有更高的计算精度、更快的收敛速度。

Application of BFGS-BP in tunnel deformation monitoring data processing

In order to overcome the disadvantages such as low calculation precision and convergence rate of traditional BP neural network algorithm,a kind of nonlinear optimization method-BFGS method for unconstrained extreme problem was introduced into BP neural network algorithm in the paper,and a BFGS-BP neural network model was developed,which was applied well in tunnel deformation monitoring data processing and forecasting with uncertainty and nonlinearity.With the example of the observation data of vault crown settlement of some tunnel construction process,the test of training and forecast experiments of BFGS-BP was developed.The result showed that BFGS-BP model has higher calculation precision and convergence rate than the traditional one.