基于RBF神经网络的煤矿井下带式输送机节能优化研究

Research on energy-saving optimization of coal mine underground beltconveyor based on RBF neural network

针对传统煤矿开采过程中能耗较高、污染物排放量较大的问题,利用径向基函数优化网络对输送机进行节能优化,构建了一种新的带式输送机节能优化模型。实验结果显示,研究模型在24 h内电能的平均节能率为17.3%,基于多目标优化算法的模型在24 h内的电能平均节能率为10.5%,基于粒子群算法的模型在24 h内的电能平均节能率为7.4%。研究模型下带式输送机每小时的能源消耗量为156.2 kWh,比粒子群模型和多目标模型的电用量分别减少423.53、367.5 kWh。综上可知,基于径向基函数优化网络的输送机在运行过程中可以减少能源消耗,实现节能减排,为提高煤矿生产设备的智能化水平提供了技术支持。

Aiming at the problems of high energy consumption and large pollutant emissions in traditional coal mining processes,a new energy-saving optimization model for belt conveyors was constructed by using radial basis function optimization networks for energy-saving optimization of conveyors.The results showed that the average energy-saving rate of the research model was 17.3%in 24 h.The average energy-saving rate of the model based on multi-objective optimization algorithm was 10.5%in 24 h,and the average energy-saving rate of the model based on particle swarm optimization algorithm was 7.4%in 24 h.The energy consumption per hour of the study model was 156.2 kWh,which was 423.53 kWh and 367.5 kWh less than that of the particle swarm model and the multi-objective model,respectively.To sum up,the conveyors based on the radial basis function optimized network can reduce energy consumption and achieve energy conservation and emission reduction during operation,and provide technical support for improving the intelligence of coal mine production equipment.