基于万有引力搜索算法优化BP的尾矿坝浸润线预测  

Prediction of Tailings Dam Infiltration Line Based on Gravitational Search Algorithm Optimized BP

作　　者：赵允坤 胡军[1] 杨斌 ZHAO Yun-kun;HU Jun;YANG Bin(School of Civil Engineering,University of Science and Technology LiaoNing,Anshan 114051,China)

机构地区：[1]辽宁科技大学土木工程学院,辽宁鞍山114051

出　　处：《水电能源科学》2022年第6期97-100,共4页Water Resources and Power

基　　金：辽宁省教育厅重点项目(601009877-36);辽宁科技大学校青年基金项目(2020QN10)。

摘　　要：为解决BP神经网络在尾矿坝浸润线预测中易陷入局部最小值、收敛速度慢等问题,引入全局搜索能力强的万有引力搜索算法(GSA)优化BP神经网络的权值和阈值,进而构建万有引力搜索算法优化BP神经网络(GSA-BP)模型,并以西果园南峪沟尾矿坝NJRX2-4监测点的浸润线预测为例,对比分析GSA-BP模型的预测值与BP模型和PSO-BP模型的预测值。结果表明,GSA-BP模型构建合理,预测精度最高,预测值与实测值相近,验证了GSA-BP模型在西果园南峪沟尾矿坝浸润线预测中的可行性和有效性。In order to solve the problem that application of the BP neural network in the tailings dam infiltration line prediction is easy to fall into a local minimum and the convergence speed is slow, the GSA with strong global search capability was introduced to optimize the weight and threshold of the BP neural network, and the GSA-BP model was established. The infiltration line of NJRX2-4 monitoring point in Nanyugou tailings dam of Western Orchard was predicted by the GSA-BP model. Compared with the BP model and the PSO-BP model, the results show that the GSA-BP model is reasonable with higher predicted accuracy, and the predicted value is similar to the measured value, verifying the feasibility and effectiveness of GSA-BP model in the Nanyugou Tailing dam infiltration line prediction in Western Orchard.

关 键 词：尾矿坝 浸润线 万有引力搜索算法(GSA) BP神经网络 粒子群算法(PSO) 

分 类 号：TD76[矿业工程—矿井通风与安全] TV697.2[水利工程—水利水电工程]