BP神经网络对含铝炸药爆热预测的研究

Prediction of Explosion Heat of Aluminiferous Explosive by BP Neural Network

该文采用已知爆热的含铝炸药对BP人工神经网络进行训练 ,建立了炸药的组成与爆热之间的定量模型 ,同时对另外几种炸药的爆热进行了预测 ,并对已知爆热的炸药进行了验证 ,结果表明该方法能较好地反映含铝混合炸药组成与爆热之间的关系 ,且所建模型预测精度高 。

Using 13 kinds of aluminiferous explosives with known explosion heat, BP neural network is trained and the relation of composition and explosion heat is built up. Subsequently, 6 kinds of explosives are predicted and 13 kinds are certificated. It proves this method has high precision and can be used to predict the explosion heat of unknown aluminiferous explosive with similar composition.