论文部分内容阅读
为解决矿井井底风流温度预测的问题,采用BP神经网络为模型,利用PSO算法优化网络权值和阈值,建立了一种新的井底风温预测模型,并用Matlab编程实现。通过对淮南某煤矿井底风温影响因素的分析得出地面入风口处风流温度、湿球温度,地面大气压力及井底湿球温度等因素的影响力较大。应用PSO-BP模型与BP模型对数据分别进行测试并分析,结果表明,该模型具有收敛速度快、预测精确度高,是求解井底风温非线性变化规律的最有效方法之一。
In order to solve the problem of forecasting the temperature of bottom hole wind flow in mine, a new model of bottom hole temperature prediction was established by using BP neural network as model and PSO algorithm to optimize network weights and thresholds. Based on the analysis of influencing factors of bottom air temperature in a coal mine in Huainan coal mine, the influence of wind temperature, wet bulb temperature, ground barometric pressure and downhole wet-bulb temperature at ground inlet is significant. The PSO-BP model and the BP model were used to test and analyze the data respectively. The results show that the model has the advantages of fast convergence rate and high prediction accuracy. It is one of the most effective methods to solve the nonlinear variation of bottom hole temperature.