论文部分内容阅读
CO_2焊在熔滴短路过渡过程中熔池附近区域的金属飞溅、光照强度变化剧烈,严重影响焊缝特征提取的实时性和可靠性。采用正交试验法和改进的BP神经网络,建立了焊接工艺参数与CO_2焊熔池附近区域图像灰度值的映射关系。结果表明:BP神经网络模型的训练结果与试验结果的误差很小,满足精度要求。该模型能很好地反映熔池附近区域图像灰度值与焊接工艺参数的关系。
The metal splashes and light intensities in the CO_2 welding near the weld pool in the process of droplet short-circuit transition greatly affect the real-time property and reliability of the weld feature extraction. The orthogonal test method and the improved BP neural network were used to establish the mapping relationship between the welding process parameters and the image gray value in the vicinity of the weld pool. The results show that the error between the BP neural network model training results and the experimental results is very small, which meets the accuracy requirements. The model can well reflect the image of the gray area near the weld pool and welding process parameters.