JavaScript is disabled for your browser. Some features of this site may not work without it.
| dc.contributor.author | Waka, Amdesilassie Teka | |
| dc.date.accessioned | 2022-12-31T08:20:54Z | |
| dc.date.available | 2022-12-31T08:20:54Z | |
| dc.date.issued | 2022-10-05 | |
| dc.identifier.uri | http://ir.bdu.edu.et/handle/123456789/14819 | |
| dc.description.abstract | The MIG welding parameters are the foremost critical factors influencing the quality, productivity, and cost of welding. The optimization of welding input process parameters for getting more prominent weld quality within the metal inert gas welding of mild steel was displayed. the input parameters of welding in these studies were welding current, welding voltage, Gas flow rate; and welding speed. The the assessment of the wear by employing image processing to analyze the scan of the worn of nozzle needs scan using a digital camera. For measuring nozzle wear, a system based on digital image processing was developed.The problem was solved by using the experimental test of parameters, and the output or the response was got via exclusive regression research applied to evaluate the advanced artificial neural network and genetic algorithm model yield. It was become discovered that the welding strength expected employing the creating ANN model is also better than the alternative to do this research primarily based on extraordinary regression evaluation. To reduce the number of experimental runs, it was carried out on a MIG welding machine. For optimal weight, an ANN model was created and trained with GA based on the input and output result values. From the analysis of the result welding parameters, 118.69A welding current, 20.229V welding speed, 10.407 cm/min, and gas flow rate of 19 L/min were obtained as optimum values. Finally, a confirmation test was carried out by welding the specimens with the optimal process parameters. The measured responses showed that the tensile strength 421.126 MPa, nozzle diameter 20.673 mm, and hardness 71.214 HRB were chosen from the predicted values. the nozzle diameter had an error of 0.043 to 0.306 from the predicted optimal value and that the responses with this optimal value were better than the previous welding parameters. After taking material that was made by company employees, determine its hardness and tensile strength. As a result, this information's worth was less than what this study's investigations revealed. The research has given the enterprise a 35% boost for the previews because it was discovered to be preferable to what it had been utilizing. Keywords: MIG, welding parameters, Artificial Neural Network, Genetic Algorithm, Wear Rate, Hardness, Tensile Strength | en_US |
| dc.language.iso | en | en_US |
| dc.subject | MECHANICAL AND INDUSTRIAL ENGINEERING | en_US |
| dc.title | Optimization of Metal Inert Gas Welding Parameters on mild steel AISI 1020 using Artificial Neural Network and Genetic Algorithm A case study from Amhara Metal Industry and Machine technology Development Enterprise (AMIMTDE). | en_US |
| dc.type | Thesis | en_US |
