传统瓦斯涌出量预测方法存在一定的局限性,预测精度不能满足要求。为了提高瓦斯涌出量预测精度,采用RBF神经网络对瓦斯涌出量相关数据进行建模。通过训练13组样本,对5组数据进行预测,分析了隐层神经元个数对预测精度的影响,并与同结构的BP神经网络预测结果进行了对比。研究结果证明了RBF神经网络在瓦斯涌出量预测中的有效性。 The traditional method of gas emission forecasting has some limitations, the prediction accuracy can not meet the requirements. In order to improve the prediction accuracy of gas emission, RBF neural network was used to model the gas emission data. By training 13 groups of samples and predicting 5 groups of data, the influence of the number of hidden neurons on the prediction accuracy was analyzed and compared with the prediction results of the same structure of BP neural network. The results show that RBF neural network is effective in predicting gas emission.