基于PSO-BP的矿井淋水井筒风温预测

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。

Prediction of Airflow Temperature of Shafts with Water Dropping Based on PSO-BP Neural Network

In order to solve the problem of forecasting airflow temperature in the bottom of the shaft,a new model of forecasting airflow temperature in the bottom of the shaft with Matlab programming is built by taking BP neural network as model and using PSO algorithm to optimize the network weights and threshold.According to the analysis of the influencing factors of airflow temperature in the bottom of the shaft in a coal mine in Huainan,it is found that the airflow temperature,wet bulb temperature,atmospheric pressure on the ground and wet bulb temperature in the bottom of the shaft have greater influence.According to the test data that analyzed by the PSO-BP model and BP model,the results show that the model with fast convergence and high prediction accuracy is one of the most effective methods of forecasting nonlinear variation of airflow temperature in the bottom of the shaft.