摘要
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。
There are some limitations in traditional gas emission prediction method and the prediction accuracy can＇t meet the requirement.To improve the accuracy of gas emission prediction,RBF neural network is used to modeling the gas emission data.By training 13 groups of samples,then predicts 5 groups of data,the relation of the number of hidden layer neurons and the prediction accuracy is analyzed.Finally,the prediction results are compared with the BP neural new with the same structure.The results show the effectiveness of the RBF neural network for gas emission prediction.
出处
《煤炭技术》
CAS
北大核心
2012年第4期118-120,共3页
Coal Technology
基金
河北省教育厅计划项目(Z2006439)
关键词
瓦斯涌出量
RBF神经网络
预测
精度
amount of gas emission
RBF neural network
prediction
accuracy
