摘要
针对矿井智能通风系统不能及时获取风速进而影响后续通风系统解算及优化的问题,利用ANSYS巷道风速分布模拟获取神经网络所需训练集,在人工测量与风速传感器监测数据的基础上,构建基于门控循环单元(Gated Recurrent Unit)神经网络的巷道平均风速预测模型。首先,提出神经网络模型,然后采用Adam优化算法对ANSYS模拟的点风速进行异常值和归一化等预处理,通过对不同形状巷道的监测点风速进行结构化处理后用于训练神经网络,找出各点风速与平均风速之间的强非线性关系,使预测风速逼近巷道实际平均风速,最后构建基于GRU神经网络的巷道平均风速预测模型。以王家岭煤矿实测数据作为测试集,将其应用于预测模型中,结果表明GRU神经网络模型具有较高精度和较强的泛化能力,能够获取巷道平均风速。矿井通风巷道平均风速预测模型在煤矿领域的成功应用,将为其他金属矿山智能通风系统及时准确获取风速参数提供新思路。
With the advent of the intelligent era,computer simulation algorithms such as machine learning and deep learning have played a role in many fields such as aerospace,medical treatment,education andcommunication. For the traditional industry of mining,the concept of smart mine has become a researchhotspot of relevant researchers in recent years. Intelligent technologies such as machine learning have been usedin pedestrian detection,gas prediction,coal rock identification has been successfully applied to practicalproduction,but the intelligent acquisition of parameters in intelligent ventilation system is still in a blank.Therefore,under the background of smart mine,aiming at the problem that the mine intelligent ventilationsystem can’t obtain the wind speed in time and then complete the subsequent ventilation system solution andoptimization,the training set required by the neural network is obtained by using the simulation of tunnel windspeed distribution in ANSYS. Based on manual measurement and wind speed sensor monitoring data,theprediction model of roadway average wind speed based on gated recurrent unit neural network was constructed.Firstly,the neural network model was proposed,and then the Adam optimization algorithm was used topreprocess the data such as outlier processing and normalization. After the structural processing of the windspeed at the monitoring points of the roadway with different shapes,it was used to train the neural network tofind out the strong nonlinear relationship between the wind speed at each point and the average wind speed,sothat the predicted wind speed is close to the actual average wind speed of the roadway. Finally,the predictionmodel of roadway average wind speed based on GRU neural network was constructed. Taking the measureddata of Wangjialing coal mine as the model test set,the results show that the GRU neural network model hashigh precision and strong generalization ability,and can obtain the average wind speed of roadway,which willprovide a roadway average wind speed prediction model with advanced technology,scientific process andaccurate results for the mine intelligent ventilation system. Moreover,the strong prediction ability of in-depthlearning will provide intelligent data for the solution and optimization of ventilation network,it can be extendedto the acquisition of ventilation parameters in other metal mines to popularize the intelligent acquisition ofventilation parameters.
作者
邵良杉
闻爽爽
SHAO Liangshan;WEN Shuangshuang(Institute of Management Science and Engineering,Liaoning Technical University,Huludao 125105,Liaoning,China;School of Business Administration,Liaoning Technical University,Huludao 125105,Liaoning,China)
出处
《黄金科学技术》
CSCD
2021年第5期709-718,共10页
Gold Science and Technology
基金
国家自然科学基金项目“基于大数据的煤与瓦斯突出的预测方法与应用研究”(编号:71771111)资助。
关键词
智慧矿山
GRU神经网络
监测监控系统
平均风速
智能通风系统
smart mine
GRU neural network
monitoring and monitoring system
average wind speed
intelligent ventilation system
