Weld Quality Prediction for Resistance Microwelding of Fine Cu Wire Based on the Back-Propagation Neural Network

Bing Hua Mo; Zi Nan Pan

doi:10.4028/www.scientific.net/AMM.217-219.1709

Paper Titles

Micro Hole Elliptical Supersonic Boring Quality Research
p.1688

Influence of Technological Parameter for Ramie Yarn Hairiness on Compact Spinning with Suction Groove
p.1695

Design and Performance Assessment of a 5-Axis Ultra-Precision Micro-Milling Machine
p.1699

Rotary Ultrasonic-Assisted Grinding of Ceramic Material
p.1705

Weld Quality Prediction for Resistance Microwelding of Fine Cu Wire Based on the Back-Propagation Neural Network
p.1709

Study on Roller Profile for Cam Forming by Cross Wedge Rolling
p.1713

Structure Design and Experimental Research on Spiral Boring Tool
p.1719

The Effect of Axial Cutting Edge Angle on the Axial Milling Force of Helical Milling
p.1723

The Effect of Welding Materials on 1Cr18Ni9Ti and 2Cr13 Steel Welding Joints Microstructure and Mechanical Properties
p.1729

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 217-219Weld Quality Prediction for Resistance...

Weld Quality Prediction for Resistance Microwelding of Fine Cu Wire Based on the Back-Propagation Neural Network

Abstract:

A neural network model is established to predict the joint quality in resistance microwelding (RMW) of fine Cu wire and stainless steel thin sheet. The preheat current, welding current, weld time and electrode force are selected as the input parameters and the tensile strength as the output parameter in the model. The prediction program is compiled in MATLAB through the detailed designing of hidden layer and the selection of the transfer function. The network performance is verified by experiment, and its accuracy meets the production requirements in the actual welding.