基于BP神经网络的烟煤类型识别研究

为了对烟煤进行快速分类,建立了BP神经网络识别法。以烟煤中的气煤、肥煤、焦煤为对象,选择煤的发热量、挥发分、灰分、硫分这些影响烟煤分类的主要参数作为BP神经网络的输入量,建立了能反映烟煤类型与这些参数指标关系的BP神经网络模型,对烟煤的类别进行识别。结果表明,该BP神经网络模型具有极强的非线性逼近能力,能真实反映烟煤的类型与相关参数之间的非线性关系,可快速准确地对烟煤的类型进行识别。

Study of Soft Coal Variety Recognition Based on BP Neural Network

In order to recognize soft coal variety quickly,a BP neural network recognition method was established.Based on gas coal,fat coal and coking coal,the main parameters including calorific value of coal,volatile matter,ash and sulfur content was taken as the input of the BP neural network,the BP neural network model was established which can reflect the connection between soft coal variety and the main parameters,and the model was used to recognize soft coal variety.The result show that the BP neural network model has strong ability for nonlinear approach which can actually reflect he connection between soft coal variety and the main parameters,and the model can recognize soft coal variety quickly.