论文部分内容阅读
针对矿井风流温度预测工作的复杂性及各个影响因素的模糊的非线性关系,传统预测方法难以构建预测模型,导致预测精度低的特点,提出一种基于RBF神经网络的矿井风流温度预测方法;并利用粒子群算法对RBF神经网络参数进行寻优,利用煤矿历史数据对预测模型进行仿真研究。结果表明,提出的基于改进粒子群算法的RBF神经网络模型(MPSO-RBF)具有收敛速度快,预测精度高的特点,为矿井风流温度预测领域提供理论支撑。
In view of the complexity of mine airflow temperature prediction and the fuzzy nonlinear relationship among various influencing factors, it is difficult to build a prediction model by traditional prediction methods, leading to low prediction accuracy. A method of predicting airflow temperature in mines based on RBF neural network is proposed. Particle swarm optimization algorithm is used to optimize the parameters of RBF neural network, and the coal mine historical data is used to simulate the prediction model. The results show that the proposed RBF neural network model (MPSO-RBF) based on the improved particle swarm optimization algorithm has the characteristics of fast convergence and high prediction accuracy, and provides theoretical support for the field of mine airflow temperature prediction.