露天矿边坡变形监测中BP神经网络模型优化设计

提出了一种提升露天矿边坡位移量预测精度和收敛速度的基于自适应混合跳跃粒子群算法(AHJPSO)改进的BP(Back Propagation)神经网络模型。传统的BP神经网络模型在位移量预测过程中存在收敛速度慢、预测精度低、易陷入局部极小值的问题,而自适应混合跳跃粒子群算法具有快速寻优能力以及能够在迭代计算的过程中有效避免陷入局部极小值的能力,所以采用自适应混合跳跃粒子群算法优化后的BP神经网络模型,能够使BP神经网络模型对露天矿边坡位移量的预测精度更高、算法收敛速度更快,并有效跳出局部极小值。

Optimal Design of BP Neural Network Model in Deformation Monitoring for Open Pit Mine Slope

It is proposed in the paper that a BP neural network model based on adaptive hybrid jump PSOalgorithm,which can promote forecasting precision and convergence speed of displacement of the open pit mine slope.The traditional BP neural network model is of slow convergence rate,low prediction accuracy and easy to fall into local minimum in the processing of displacement forecasting,while AHJPSO is with the ability to quickly find the best and can be able to effectively avoid the local minimum value.As a result,adoption of BP neural network model based on the AHJPSO optimization can make fast convergence rate,high prediction accuracy and is easy to avoid falling into local minimum.