JavaScript is disabled for your browser. Some features of this site may not work without it.
| dc.contributor.author | KALKIDAN, ANDUALEM AYELE | |
| dc.date.accessioned | 2024-05-23T07:00:26Z | |
| dc.date.available | 2024-05-23T07:00:26Z | |
| dc.date.issued | 2023-02 | |
| dc.identifier.uri | http://ir.bdu.edu.et/handle/123456789/15812 | |
| dc.description.abstract | Resistance spot welding (RSW) is a fusion welding process in which two metal sheets are joined by applying heat and pressure that forms small nuggets at the interface of the two metals. It is commonly used in the automotive industry and other manufacturing industries. In Amhara Metal Industry and Machine Technology Development Enterprise (AMMITDE), mild steel AISI 1020 sheet metals of one mm thickness were welded with a resistance spot welding process. But there is a lot of wastage of mild steel sheets due to welding failure and different welding defects. Because of these defects, the tensile strength, hardness, and the size of the nugget diameter of the weld were directly impacted since the enterprise welds without consider the optimum value of the welding parameters. This study has provided the multi-objective process parameters optimization of resistance spot welding on mild steel of AISI 1020 to optimize tensile strength, hardness of the nugget, and the size of the nugget's diameter with their input process parameters of welding current, welding force, holding, and welding time of a resistance spot welding machine. Taguchi’s L9 orthogonal array was utilized as the design of the experiment to reduce the number of experimental runs, and the experiment was conducted on a DTN-40 resistance spot welding machine using welding electrode C18150 chromium-zirconium copper alloys found in the case company. RSW process parameters were optimized by using a hybrid artificial neural network (ANN) and genetic algorithm (GA). Based on the input and output values, an ANN model was developed and trained with GA to get optimal weight. This objective function was further optimized by GA for an optimal result. From the analysis of the result, optimal sets of design variables were obtained as welding current 5.53038 KA, welding force 0.774159 MPa, welding time 29.51089 Cycles, and holding time 26.16549 Cycles, with their response values of ultimate tensile strength 392.6137 MPa, hardness 73.9 HRB, and nugget diameter 6.933139 mm. Finally, a confirmation test was carried out using the optimum process parameters, and the confirmed responses of ultimate tensile strength of 388.33 MPa, hardness of 59.9 HRB, and nugget diameter of 7.137 mm were obtained. Since the optimization was within an acceptable level of correctness with a minimum percent error and when comparing this study to before work, the UTS at 27.32%, the nugget hardness at 32.029%, and the diameter of the nugget at 8.97% were improved. Keywords: Resistance spot welding, ANN, Multi-objective Genetic Algorithm, Nugget diameter, Tensile strength | en_US |
| dc.language.iso | en_US | en_US |
| dc.subject | Mechanical and Industrial Engineering | en_US |
| dc.title | Optimization of resistance spot welding process parameters for AISI1020 mild steel using artificial neural network and genetic algorithm method (Case Study in AMIMTDE) | en_US |
| dc.type | Thesis | en_US |
