机构地区: 辽宁工学院材料与化学工程学院
出 处: 《材料科学与工艺》 2004年第5期489-491,共3页
摘 要: 基于人工神经网络的原理,对热爆法制备Ni-Al系金属间化合物中的控制参数进行了研究,选取了加热速率、颗粒尺寸、压坯密度三个参数,通过对此参数的调控可以影响热爆反应的点火时间及反应过程.本文采用BP算法来训练网络,对热爆反应中的过程参数与热爆点火时间的映射关系进行了函数逼近,建立了热爆点火时间的神经网络模型.根据该模型可以预测热爆的点火时间,为控制热爆反应加压过程提供了可靠的依据. Based on artificial neutral network theory, it was studied that the control parameters in thermal explosion process. The heating rate, particle size and green density was picked up. Through controlling these parameters, the ignition time and reaction process of thermal explosion was influenced. In this paper we used these data appropriately treated to train a BP algorithm neural network, which could unlimitedly approach the reality of the mapping relation between those control parameters and ignition time of thermal explosion. So a neural network model for ignition time was built. Depending on this model, we could predict ignition time of thennal explosion and provide a reliable foundation for controlling pressing process of thermal explosion.