Optimization Of Spot Welding Resistance Parameter On Tensile Strength And Tear Strength In Nickel Strip Plate Joints With Backpropagation Neural Networks And Genetic Algorithm Method

Kusumadjaja, Hafidh Adani (2024) Optimization Of Spot Welding Resistance Parameter On Tensile Strength And Tear Strength In Nickel Strip Plate Joints With Backpropagation Neural Networks And Genetic Algorithm Method. Other thesis, Institut Teknologi Sepuluh Nopember.

	Text 5007201108-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (6MB) | Request a copy
	Text 5007201108-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (595kB) | Request a copy

Abstract

Spot welding on nickel surfaces is used in the process of joining workpiece components. Connecting nickel plates using the Resistance Spot Welding (RSW) method is a technique commonly used in the manufacturing industry. This research aims to optimize the welding parameters of the SUNKKO 709A spot weld which has a specification of 1.9 KW AC220V 800A at the automotive STP of the Sepuluh Nopember Institute of Technology to increase the tensile strength of nickel strip plate joints, especially in battery pack applications. Optimized input parameters include current strength, welding pulse, and electrode pressure as well as output tensile and tear test results using the UTM SALT tensile testing machine in the materials testing laboratory of the mechanical engineering department of Sepuluh Nopember Institute of Technology. Apart from that, this research also applies an optimization method using Backpropagation Neural Network-Genetic Algorithm (BPNN-GA) to increase accuracy in predicting the maximum tensile strength and tear strength of plate joints. The expected output from this research is the development of RSW parameters that can produce connections with strong tensile strength and strong tear strength, thereby improving the quality and performance of batteries that use nickel strip plates as components. Apart from that, this research also highlights the importance of applying appropriate welding technology in the battery pack industry to produce high quality and long-lasting products. The results of this research obtained 27 data that will be trained with BPNN. In BPNN output tensile strength the best net is 2 hidden layer, 9 neurons per hidden layer, and the activation function for each hidden layer is logsig and tear strength is 5 hidden layers, 8 neurons per hidden layer. By using GA for the best parameters were obtained, Ampere parameters 600 A, Pulse 18 P, Electrode pressure 400g or 0.4 kg/mm2. Then these parameters were tensile tested and tear tested again as confirmation of the results of getting a tensile strength of 374.519N/mm2 and a tear strength of 47.13N/ mm2.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Spot Welding, Optimization, Nickel, Tensile Test, Genetic Algorithm, Battery pack
Subjects:	T Technology > T Technology (General) > T174 Technological forecasting
Divisions:	Faculty of Industrial Technology and Systems Engineering (INDSYS) > Mechanical Engineering > 21201-(S1) Undergraduate Thesis
Depositing User:	Hafidh Adani Kusumadjaja
Date Deposited:	16 Aug 2024 04:30
Last Modified:	16 Aug 2024 04:30
URI:	http://repository.its.ac.id/id/eprint/114127

Actions (login required)

View Item