【摘要】 本文以水火弯板加工过程中的燃气流量、火焰移动速度、加工时间和钢板厚度作为输入参数,热源热效率和热源半径作为输出结果,建立了一种可以预测水火弯板热源模型参数的BP神经网络方法。应用神经网络预测结果设定水火弯板数值模拟时钢板表面的热流载荷参数,基于ANSYS软件得到钢板水火弯板温度场数值计算结果。经应用实例验证,以BP神经网络输出为热源参数的水火弯板数值计算结果与试验测试结果基本一致,说明本文所建立的BP神经网络方法可以用来预测水火弯板温度场热源模型参数。更多还原

【Abstract】 In the paper,assuming the gas flux,moving speed of the flame,processing time and the thickness of plate in line heating processing as input parameters,and heat efficiency and radius of the heat source as output results,a method of BP neural-network to predict the parameters of heat-source model for line heating is proposed.The prediction results of neural-network method are applied to setting the parameters of heat-flow load on the plate surface at the time of numerical simulation of line heating,the numerical results of temperature field for line heating are gained using ANSYS software.It is verified by the numerical example that the numerical calculation results of line heating by using the output of BP neural-network as parameters of heat source are in good agreement with the testing results of experiment,which shows that the method of BP neural-network built in the paper can be used to predict the heat-source parameters of temperature field for line heating.更多还原