基于BP神经网络模型的矿井通风可靠性研究

Research on Mine Ventilation Reliability Based on BP Neural Network

在MATLAB 7.0神经网络工具箱的基础上,通过采用快速的Levenberg Marquart算法,提高神经网络训练的速度与精度,实现矿井通风系统可靠性的研究和预测。旨在以一种相对简单的途径实现人工神经网络这种复杂而有效的非线性预测方法。实验结果显示了L M算法的优越性,网络具有良好的收敛特性。

Based on the neural network toolbox of MATLAB 7.0, the training speed and precision of neural networks can be improved and the research of mine ventilation reliability can be carried out by using levenberg-marquart arithmetic. The nonlinear forecasting method is realized by a relative simple method. The results show the advantage of L- M arithmetic and good converge property.