JavaScript is disabled for your browser. Some features of this site may not work without it.
| dc.contributor.author | Yilikal, Azene Zelalem | |
| dc.date.accessioned | 2022-12-31T08:25:13Z | |
| dc.date.available | 2022-12-31T08:25:13Z | |
| dc.date.issued | 2022-09 | |
| dc.identifier.uri | http://ir.bdu.edu.et/handle/123456789/14821 | |
| dc.description.abstract | Due to its high deposition rate and high welding quality, submerged arc welding (SAW) is widely implemented to join thick metals for heavy structural steelwork. In Amhara Metal Industry and Machine Technology Development Enterprise (AMMITDE), beams and columns for heavy structural steelwork were frequently welded with a submerged arc welding process. While there, different welding defects like undercut, porosity, and burn-through were encountered. Through these defects, the tensile strength, hardness, and bead geometry of the weld were dramatically impacted. since The enterprise welds without considering the optimum value of the welding parameters. As a result, the current study has provided the multi-objective process parameter optimization of submerged arc welding on mild steel AISI 1020 to optimize tensile strength, hardness, and bead width with their input process parameters of Welding current, electrode stick-out, welding voltage, and welding speed. Taguchi's 𝑀 9 an orthogonal array was employed as the design of the experiment. The experiment was conducted on an MZ-1250 automatic submerged arc welding machine using coppercoated mild steel electrode of EH12 with 4 mm diameter and basic agglomerated flux of F7A2. The objective function for the multi-objective Jaya algorithm was implemented through an Artificial neural network, and the optimal sets of design variables were obtained as welding current 417A, electrode stick-out 20.7mm, welding voltage 33.7mm, and welding speed 505.8mm/min, with their response value of ultimate tensile strength 427 MPa, hardness 73.9 HRB, and bead width 14.28882 mm were obtained. Finally, a confirmation test was carried out using the optimum process parameters, and the confirmed responses of ultimate tensile strength of 426 MPa, hardness of 74.1 HRB, and bead width of 14.0026 mm were obtained. Since the optimization was within an acceptable level of correctness with a minimum % error. Keywords- Submerged arc welding, Artificial Neural Network, Multi-objective Jaya Algorism, SAW Process Parameters, Mechanical properties, and bead geometry | en_US |
| dc.language.iso | en_US | en_US |
| dc.subject | MECHANICAL AND INDUSTRIAL ENGINEERING | en_US |
| dc.title | Process parameters optimization of Submerged arc welding on mild steel AISI 1020 using Artificial neural network trained with multiobjective Jaya algorism. | en_US |
| dc.type | Thesis | en_US |
