Abstract

Line heating is one of the alternative methods of forming metals and this kind of forming uses the heating torch as a source of heat input. During the process, many parameters are considered like the size of the substrate, thickness, cooling method, source power intensity, the travel speed of the power source, the sequence of heating, and so on. It is important to analyze the factors affecting the metal bending process to effectively predict the nature and final shape of a material. The present study addresses parametric research and a new prediction technique for the final shape of metal using the ANN (Artificial Neural Network) approach. The experimental data are validated using the numerical finite element method. The test setup with orthogonal arrangement L9 is used for the setup of the experimental investigation. ANN is used for model accuracy with less dependence on measured data. All steps are performed in MATLAB with different training schemes. The network takes into account three process parameters, such as metal thickness, movement speed, and the number of passes, and the multi-layered perceptron neural network is trained and tested on the data. The predictive output of the ANN model is compared to the experimental results of the final bending of a metal and shows a good fit of the predicted values of ANN to the measured data with higher values, 97% of the coefficient of determination.

Citations

Author (1)