BP Neural Network Model for Seam Tracking Offset during High-Power Fiber Laser Welding

Ling Mo; Xiang Dong Gao; Qian Wen; De Yong You

doi:10.4028/www.scientific.net/AMR.418-420.1464

Paper Titles

Optimization on Resistance Microwelding Procedure of Fine Copper Wire Based on Orthogonal Experiment Design
p.1448

Mechanical and Electrical Properties of Graphite/Carbon Fiber/Phenolic Resin Composite
p.1452

Numerical Simulation of Thixo-Diecasting Al6061 Alloy Automobile Part
p.1456

The Failure Mechanism of Cemented Carbide Milling Insert during Machining Difficult-to-Cut Metal
p.1460

BP Neural Network Model for Seam Tracking Offset during High-Power Fiber Laser Welding
p.1464

Hot Forming Behavior and Flow Stress Model of Steel 50A1300
p.1468

A New Algorithm for Solving the Best-Fit Sphere of Optical Aspherical Surface
p.1472

Design, Development & Experimental Investigation of Electro-Discharge Diamond Surface Grinding of Ti-6Al-4V
p.1478

Development of Tooling Cost Model for High Speed Hard Turning
p.1482

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 418-420BP Neural Network Model for Seam Tracking Offset...

BP Neural Network Model for Seam Tracking Offset during High-Power Fiber Laser Welding

Abstract:

Seam tracking is significant to obtain good welding quality. Aiming at establishing a model to detect and calculate the seam tracking offset during high-power fiber laser welding of Type 304 austenitic stainless steel plate butt joint welding, an infrared sensitive high-speed camera arranged off-axis orientation of laser beam was applied to capture the dynamic thermal images of molten pool. Six parameters such as the keyhole configuration parameters (include four parameters), keyhole centroid parameter and heat accumulation parameter were defined as the eigenvalues of seam tracking offset to determine the seam tracking offset between the laser beam and the desired welding trajectory. A BP neural network model was built to reflect the correlations between the defined eigenvalues and the seam tracking offset. The welding experiments confirmed that the seam tracking offset between the laser beam focus and the welding seam could be monitored and calculated by the BP neural network model effectively.