GA-BP神经网络模型在稀土矿边坡位移监测中的应用

Application of GA-BP neural network model in the displacement monitoring of rare earth slope

离子型稀土原地浸矿工艺改变土体力学特性,导致山体滑坡风险提高。针对现有研究在预测稀土矿边坡位移时存在精度不高和误差较大等问题,利用遗传算法对BP神经网络初始权值和阈值进行优化,构建一种新的稀土矿边坡位移预测模型。以江西龙南某离子型稀土矿为研究对象,在矿山布置了位移计实时监测稀土矿开采全过程的位移变化。首先利用125组位移监测数据训练BP神经网络构建预测模型,5组数据进行模型验证;再通过GA-BP神经网络优化预测模型,将2种预测模型的预测值和实测值进行对比及误差分析。研究表明:GA-BP神经网络模型的平均相对误差、平均绝对误差、均方误差、平均绝对百分比误差均减小到优化前的1/3以下,可作为稀土矿边坡位移监测分析的一种辅助手段。

The ionic rare earth in situ leaching process changes the mechanical properties of the soil,leading to an increased risk of landslides.To address the problems of low accuracy and large error in predicting slope displacement of rare earth mines in existing studies,the genetic algorithm was used to optimize the initial weights and thresholds of the BP neural network to build a new slope displacement prediction model for rare earth mines.Taking an ionic rare earth mine in Longnan,Jiangxi as the research object,a displacement meter was arranged in the mine to monitor the displacement changes of the whole process of rare earth mining in real time.At first,BP neural network was trained with 125 sets displacement monitoring data to build a prediction model,which was validated with 5 sets of data.Then the prediction model was optimized by GA-BP neural network.The predicted and measured values of the two prediction models were compared and error analyzed.The study showed that GA-BP neural network model could be used as an auxiliary means for slope displacement monitoring and analysis of rare earth mines when the mean relative error,mean absolute error,mean square error and mean absolute percentage error were reduced to 1/3 of those before optimization.