基于模糊聚类径向基神经网络的煤质分析模型

Coal assay analytical model based on fuzzy clustering RBF Neural Network

为了实现煤炭指标的快速智能预测,建立了基于模糊聚类的径向基函数(RBF)神经网络预测模型,将已测定的收到基全水、收到基灰分、收到基挥发分和收到基全硫的含量作为分类指标进行模糊聚类,根据分类结果分别建立了基于径向基函数神经网络的定量分析模型,对干燥无灰基挥发分、空干基全硫、收到基低位发热量和空干基高位发热量进行了预测,并与直接使用径向基神经网络模型进行比较。结果表明,该分析模型不仅精度高,且泛化能力强,鲁棒性好。

To achieve rapid and intelligent prediction of coal quality,a radial basis function（ RBF） neural network prediction model based on fuzzy clustering was established. Based on measured contents of total moisture of as received basis,ash of as received basis,volatile matter of as received basis and total sulfur of as received basis in coal,fuzzy clustering was made; according to the results,several quantitative analytical models RBF based on neural network were established. The model can predict volatile matter of dry ash- free basis,total sulfur of air dried basis,low calorific value of as received basis and gross calorific value of dry basis in coal. And the comparison between the model and the direct use of RBF neural network model was made. The experimental results showed that the analytical model has high precision,strong generalization ability and good robustness.