粒子群算法优化BP神经网络的粉尘浓度预测

中文摘要：

对综采工作面粉尘浓度预测的方法是建立BP神经网络预测模型。为了提高算法的拟合能力及预测的准确度，使用粒子群算法对目标函数进行改进，即将粒子群算法寻到的最优权值和阈值应用于神经网络预测模型求综采工作面粉尘浓度。比较分析新的预测模型与常用的灰色模型以及标准的BP神经网络算法，结果表明粒子群优化的神经网络算法的拟合能力和预测的准确率显著提高。

Abstract:

The prediction method of dust concentration in fully mechanized coal mining face is establishing a BP neural network prediction model.In order to improve the fitting ability and prediction accuracy of the algorithm,the particle swarm optimization(PSO) algorithm was used to improve the objective function.The optimal weights and thresholds obtained by the PSO were applied to the neural network prediction model to find the dust concentration in the fully mechanized coal mining face.The comparison of the new prediction model with the commonly used gray model and the standard BP neural network algorithm results shows that the fitting ability and prediction accuracy of the PSO optimized neural network algorithm are significantly improved.