摘要
通过测得的熔化极气体保护焊 (GMAW )过程中的电参数 ,利用Kohonen神经网络 ,直接依据不同焊接工艺条件下焊接电压和焊接电流的概率密度分布 (PDD)曲线以及短路过渡时间和燃弧时间等的时间频数分布 (CFD)曲线 ,可以自动识别焊接过程中的各种干扰信号 ,从而实现焊接质量监测。实验验证了该方法的可行性。
By the measured and statistically processed electrical parameters of GMAW, we can use Kohonen neural network to recognize and classify the process disturbances during welding and monitor the welding quality. The system developed is based on the probability density distributions (PDD) of welding voltage and current, and the class frequency distributions (CFD) of short circuiting time and burning arc time. Experimental result shows the feasibility of the method.
出处
《无损检测》
2002年第4期159-161,共3页
Nondestructive Testing
基金
高校重点实验室访问学者基金资助项目 (2 0 0 10 5 0 2 )