基于PSO优化BP神经网络的露天矿边坡位移预测模型

BP神经网络的初始连接权重和阈值对露天矿边坡位移预测的精度和收敛速度有重要影响。鉴于粒子群优化(PSO)算法具有全局搜索性能和收敛速度快,引入PSO算法对BP神经网络的初始连接权重和阈值进行全局优化,提出了基于PSO优化BP神经网络的露天矿边坡位移预测模型。将所提出的模型应用于实际案例中,并与BP神经网络进行对比。结果表明:该模型能够提高BP神经网络在露天矿边坡位移预测中的精度和收敛速度,预测结果的最大相对误差和平均相对误差分别是0.566 8%和0.353 0%,具有较好的精度和实际应用价值。

Slope Displacement Prediction Model of Open Pit based on PSO optimize BP Neural Network

The initial connection weights and thresholds of BP neural network have an important influence on the accuracy and convergence speed of open pit slope displacement prediction. In view of the global search performance and fast convergence of particle swarm optimization (PSO), PSO algorithm was introduced to optimize the initial connection weight and threshold of BP neural network. The displacement prediction model of open pit slope based on BP neural network optimized by PSO was proposed. The proposed model was applied to the actual case and compared with the BP neural network. The prediction results indicated that the proposed model can improve the accuracy and convergence speed of BP neural network displacement prediction in open pit slope. The maximum relative error and average relative error of the proposed model prediction were 0.5668% and 0.3530%, respectively, which have good precision and practical application value.