JavaScript is disabled for your browser. Some features of this site may not work without it.
| dc.contributor.author | Amanuel, Kassa Mengistie | |
| dc.date.accessioned | 2022-11-29T07:38:43Z | |
| dc.date.available | 2022-11-29T07:38:43Z | |
| dc.date.issued | 2022-08 | |
| dc.identifier.uri | http://ir.bdu.edu.et/handle/123456789/14587 | |
| dc.description.abstract | Welding of pipes and tubes is employed in practically every engineering application. In Amhara Metal Industry and Machine Technology Development Enterprise (AMIMTDE) pipes, pressure vessels, and any cylindrical components are welded manually which is slower and vulnerable to human error, resulting in non-uniform, less-quality, and inconsistent weldments. This study developed an automated orbital pipe welding system, that automatically holds and moves the welding gun at constant speed on a circular rail fixed near the pipe joint after adjusting its arc length automatically to overcome the problems in AMIMTDE. After the development, this study optimized the welding process parameters (i.e welding current, arc voltage, welding speed, and arc length) of the automated orbital MIG welding process on welding AISI 1020 mild steel grade pipe by demonstrating the impact of various input parameter levels on the tensile strength and hardness of the welded joint. Three levels of variation were applied to the four input parameters that were chosen. Nine experiments were carried out using Taguchi's L9 orthogonal array approach. For modeling the orbital pipe MIG welding process experimental input parameters and response results, an Artificial Neural Network (ANN) was constructed. During modeling the results indicated that, a 4-9-2 network trained by Bayesian Regularization (BR) approach was determined to have the greatest prediction capability, with a mean squared error (MSE) of 5.06e-05. Then this model was taken to the genetic algorithm (GA) to determine the combination of optimal process parameters that yields maximum hardness and tensile strength. The feasible optimal process parameter of a combined artificial neural network and a genetic algorithm (ANN-GA) was identified as welding current 94.14143 A, welding voltage 23.98961 V, welding speed 31.84924 cm/min, and arclength 2.766681 mm resulting in maximum tensile strength and hardness of 417.857 MPa and 96.5364 HR respectively. Finally, a confirmation test was conducted with the optimum parameters. The predicted and confirmation test results percentage error was 1.23 % for tensile strength and 1.59 % for hardness. Thus, it has been concluded that the confirmation experimental results are within the acceptable range of percentage error as per the reviewed literature. Keywords: Orbital pipe welding, ANN, GA, process parameters optimization, Tensile strength. | en_US |
| dc.language.iso | en_US | en_US |
| dc.subject | MECHANICAL AND INDUSTRIAL ENGINEERING | en_US |
| dc.title | Development and Process Parameters Optimization of Automatic Orbital MIG Welding System of AISI 1020 Mild Steel Pipe Using Hybrid Artificial Neural Network and Genetic Algorithm (Case Study of Amhara Metal Industry and Machine Technology Development Enterprise, Bahir Dar, Ethiopia) | en_US |
| dc.type | Thesis | en_US |
