本文已被:浏览 729次 下载 595次
投稿时间:2021-01-15 修订日期:2021-01-21
投稿时间:2021-01-15 修订日期:2021-01-21
中文摘要: 在探究充填体强度值大小时为了减少人力、物力的损耗,尝试利用BP神经网络模型对某矿山的四种尾砂材料浇筑的充填体试块进行预测。建立了输入层为8,隐含层为9,输出层为2的BP神经网络模型,并用该模型对某矿山四种不同尾砂材料浇筑的充填体试块进行预测试验。在随机选择的8种试块预测试验结果中,去除误差较大的情况后,充填体27天强度预测平均误差5.8%,充填体60天强度预测平均误差为5%,其中最优预测值与实际偏差值仅为1%。实利了利用BP神经网络模型在不同胶凝材料、不同灰砂比、不同浓度等多个条件下对充填体强度的预测。为其它矿山充填体强度的预测提供一种新的思路。
Abstract:In order to reduce the loss of human and material resources when investigating the strength value of the filler, a BP neural network model was attempted to predict the filler specimens cast with four different tailings materials from a mine. A BP neural network model with 8 input layers, 9 implied layers and 2 output layers was developed and used to predict the strength of the filler blocks cast with four different tailings materials in a mine. Among the eight randomly selected test blocks, the average error in predicting the 27-day strength of the filler was 5.8% and the average error in predicting the 60-day strength of the filler was 5% after removing the cases with large errors, where the deviation between the best prediction and the actual value was only 1%. The BP neural network model was used to predict the strength of the fill under various conditions such as different cementitious materials, different ash-sand ratios and different concentrations. It provides a new way of thinking for the prediction of the strength of fillers in other mines.
keywords: filler strength filling BP neural network prediction tailings materials cementitious materials ash-sand ratios concentration
文章编号: 中图分类号: 文献标志码:
基金项目:“十三五”国家重点研发计划课题(2017YFC0602903)
引用文本:
胡 凡,彭 亮,仵峰峰,张 峰.基于BP神经网络模型的充填体强度值预测[J].有色金属(矿山部分),2021,73(6):60-65.
HU Fan,PENG Liang,WU Fengfeng,ZHANG Feng.Prediction of filler strength values based on BP neural network models[J].NONFERROUS METALS(Mining Section),2021,73(6):60-65.
胡 凡,彭 亮,仵峰峰,张 峰.基于BP神经网络模型的充填体强度值预测[J].有色金属(矿山部分),2021,73(6):60-65.
HU Fan,PENG Liang,WU Fengfeng,ZHANG Feng.Prediction of filler strength values based on BP neural network models[J].NONFERROUS METALS(Mining Section),2021,73(6):60-65.