Estimation and Comparison of Welding Performances in P- GMAW using MRA and ANN for SS 304L Material

International Conference on Advances in Manufacturing, Materials and Energy Engineering 2018

材料科学;能源学

Addamani, Rudreshi^1 ; Gurupavan, H.R.^1 ; Ravindra, H.V.^1 ; Ugrasen, G.^2

Dept. of Mechanical Engg., P.E.S. College of Engg., Mandya, Karnataka, India^1

Dept. of Mechanical Engg., BMS College of Engg., Bangalore, Karnataka, India^2

关键词: Arc welding process;    Artificial neural network modeling;    Gas metal arc welding (GMAW);    Multiple regression analysis;    Process parameters;    Pulsed gas metal arc welding;    Ultimate tensile strength;    Welding process parameters;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/376/1/012119/pdf
DOI  :  10.1088/1757-899X/376/1/012119

学科分类：材料科学（综合）

来源: IOP

【 摘 要 】

The Pulsed Gas Metal Arc Welding (P-GMAW) process is one of the most significant arc welding processes, used in high-technology industrial applications. P-GMAW welding input process parameters are the most important factors affecting the quality, productivity and cost of welding In order to understand and control the P-GMA welding process parameters, it is necessary to determine the input and output relationship of the welding processes. P-GMAW is widely used process, especially in thin sheet metal industries. It offers an improvement in quality and productivity over regular Gas Metal Arc Welding (GMAW). The process enables stable spray transfer with low mean current and low net heat input. This paper describes the estimation and comparison of welding process parameters viz., current, gas flow rate and wire feed rate on ultimate tensile strength, yield strength, percentage of elongation and hardness. Experiments have been performed based on Taguchi's L27 standard orthogonal array. Estimation of welding performances have been carried out using sophisticated mathematical models viz., MRA and ANN, and, compared. The output developed by artificial neural network model is used to compare with the output obtained through multiple regression analysis. Estimation and comparison of welding performances were carried out using MRA and ANN techniques.