基于MMAS-BP神经网络的粉煤灰膏体管道输送水力坡度预测  

Prediction of Hydraulic Gradient of Fly Ash Paste Pipeline Transportation Based on MMAS-BP Neural Network

作　　者：何荣军[1] 杜运夯 吴再生[1] HE Rongjun;DU Yunhang;WU Zaisheng(Chongqing Vocational Institute of Engineering,Chongqing 402260,China;Yunnan Vocational Institute of Energy Technology,Qujing 655001,China)

机构地区：[1]重庆工程职业技术学院,重庆402260 [2]云南能源职业技术学院,云南曲靖655001

出　　处：《煤矿安全》2018年第6期217-220,共4页Safety in Coal Mines

基　　金：国家重点基础研究发展计划(973计划)资助项目(2015CB251600)

摘　　要：水力坡度是粉煤灰膏体井下处理系统设计的重要参数,决定着能耗大小和运行成本。为掌握水力坡度的精确结果,将最大最小蚁群算法(MMAS)和BP神经网络结合应用于水力坡度的预测中,建立了水力坡度预测模型。经实践应用表明,该预测模型具有最大最小蚁群算法的快速收敛和全局性,又具有BP神经网络强大的映照效果,预测结果完全满足实际应用需要。Hydraulic gradient is an important parameter in the design of coal ash paste underground treatment system, which determines the energy consumption and operation cost. In order to master the accurate results of hydraulic gradient, MAX-MIN ant system（MMAS） and BP neural network are applied to the prediction of hydraulic gradient. The prediction model of hydraulic gradient is established. The practical application shows that the model has fast convergence and global prediction of MAX-MIN ant system, and the strong mapping effect of BP neural network. The prediction results completely meet the needs of practical applications.

关 键 词：最大最小蚁群算法 BP神经网络 粉煤灰膏体 管道输送 水力坡度 预测 

分 类 号：TD823.7[矿业工程—煤矿开采]