Optimal Welding Condition for the Inclined and Skewed Fillet Joints ill the Curved Block of a Ship (I)

J. Ocean Eng. Technol. 2004;18(6):79-83.

PARK JU-YONG;

Division of Oceen System Engineering, Korea Maritime University;

선박 골블록의 경사 필렛 이음부의 적정 용접조건 (I)

박주용;

한국해양대학교 해양시스템공학부;

Keywords: Optimal Welding Condition, Inclined Fillet Joint, Critical Deposited Area, Regression, ANN(Artificial Neural Network)

핵심용어: 적정 용접 조건, 경사 필렛 이음부, 한계용착면적, 회귀분석, 인공신경망

Abstract

The curved blocks which compose the bow and stem of a ship contain many skewed joints that are inclined horizontally and vertically. Most of these joints have a large fitness error and are continuously changing their form and are not easily accessible. The welding position and parameter values should be appropriately set in correspondence to the shape and the inclination of the joints. The welding parameters such as current, voltage, travel speed, and melting rate, are related to each other and their values must be in a specific limited range for the sound welding. These correlations and the ranges are dependent up on the kind and size of wire, shielding gas, joint shape and fitness. To determine these relationships, extensive welding experiments were performed. The experimental data were processed using several information processing technologies. The regression method was used to determine the relationship between current voltage, and deposition rate. When a joint is inclined, the weld bead should be confined to a the limited size, inorder to avoid undercut as well as overlap due to flowing down of molten metal by gravity. The dependency of the limited weld size which is defined as the critical deposited area on various factors such as the horizontally and vertically inclined angle of the joint, skewed angle of the joint, up or down welding direction and weaving was investigated through a number of welding experiments. On the basis of this result, an ANN system was developed to estimate the critical deposited area. The ANN system consists of a 4 layer structure and uses an error back propagation learning algorithm. The estimated values of the ANN were validated using experimental values.