论文部分内容阅读
针对激光钎焊熔深难以控制的问题,选取激光焊接功率、焊接速度等激光焊接过程中所涉及的控制参数建立基于BP人工神经网络的激光钎焊模型。根据激光钎焊模拟实验的历史数据对焊接熔深进行预测,采用遗传算法对控制参数进行优化,得到目标焊接熔深。运用MATLAB软件建立了针对铝合金/镀锌钢的激光熔钎焊过程的参数的BP人工神经网络模型,并利用遗传算法的并行和群体搜索策略,对其控制参数进行了优化,使得焊接熔深能通过过程参数精确控制,提高了接头性能。
Aiming at the problem of difficult to control laser welding penetration, the laser brazing model based on BP artificial neural network is established by selecting the control parameters involved in laser welding process such as laser welding power and welding speed. According to the historical data of the laser brazing simulation experiment, the welding penetration is predicted, and the genetic algorithm is used to optimize the control parameters to obtain the target weld penetration. The BP artificial neural network model for laser welding brazing process of aluminum alloy / galvanized steel is established by using MATLAB software. By using the parallel and group search strategy of genetic algorithm, the control parameters are optimized so that the welding penetration Accurate control of process parameters improves joint performance.