Prediction of weld bead geometry and penetration in shielded metal-are welding using artificial neural networks
Prediction of weld bead geometry and penetration in shielded metal-are welding using artificial neural networks
复制标题
DOI：
10.1016/s0924-0136(02)00101-2
复制
发表时间：
2002-04-30
影响因子：
6.3
通讯作者：
Datta, GL
中科院分区：
文献类型：
--
作者：
Nagesh, DS;Datta, GL
焊道几何形状（焊道高度和宽度）和熔深（深度和面积）是焊件的重要物理特性。几个焊接参数似乎会影响焊道的几何形状和熔深。据观察，高电弧移动速率或低电弧功率通常产生不良熔合。电流、电压和弧移速率对熔深有影响。影响熔深的其他因素有导热系数、弧长和弧力。弧长越长，穿透越浅。在电弧功率很低的情况下，电弧长度过小也会导致熔透不良。本文探讨了用人工神经网络建立电弧焊过程的数学模型。反向传播神经网络被用来关联焊接工艺变量与焊缝几何形状和熔深的特征。这些网络与训练数据取得了良好的一致性，并取得了令人满意的概括性。神经网络可以有效地实现焊缝和熔透几何参数的估计。这些实验的结果表明，估计值和实验值之间的误差百分比差异很小。(C)2002 Elsevier Science B.V.保留所有权利。
Bead geometry (bead height and width) and penetration (depth and area) are important physical characteristics of a weldment. Several welding parameters seem to affect the bead geometry and penetration. It was observed that high are-travel rate or low arc-power normally produced poor fusion. Higher electrode feed rate produced higher bead width making the bead flatter.Current, voltage and are-travel rate influence the depth of penetration. The other factors that influence the penetration are heat conductivity, arc-length and arc-force. Longer are-length produces shallower penetration. Too small arc-length may also give rise to poor penetration, if the arc-power is very low.Use of artificial neural networks to model the shielded metal-are welding process is explored in this paper. Back-propagation neural networks are used to associate the welding process variables with the features of the bead geometry and penetration. These networks have achieved good agreement with the training data and have yielded satisfactory generalisation. A neural network could be effectively implemented for estimating the weld bead and penetration geometric parameters. The results of these experiments show a small error percentage difference between the estimated and experimental values. (C) 2002 Elsevier Science B.V. All rights reserved.