Application of an optimized SA-ANN hybrid model for parametric modeling and optimization of LASOX cutting of mild steel

Abstract

Laser assisted oxygen cutting (LASOX) process is an efficient method for cutting thick mild steel plates compared to conventional laser cutting process. However, scanty information is available as to modeling of the process. The paper presents an optimized SA-ANN model of artificial neural network (ANN) and simulated annealing (SA) to predict and optimize cutting quality of LASOX cutting process of mild steel plates. Optimization of SA-ANN parameters is carried out first where the ANN architecture and initial temperature for SA are optimized. The optimized ANN architecture is further trained using single hidden layer back propagation neural network (BPNN) with Bayesian regularization (BR). The trained ANN is then used to evaluate the objective function during optimization with SA. Experimental dataset employed for the purpose consists of input cutting parameters comprising laser power, cutting speed, gas pressure and stand-off distance while the resulting cutting quality is represented by heat affected zone (HAZ) width, kerf width and surface roughness. Results indicate that the SA-ANN model can predict the optimized output with reasonably good accuracy (around 3%). The proposed approach can be extended for prediction and optimization of operational parameters with reasonable accuracy for any experimental dataset.

Ann modeling of kerf transfer in Co2 laser cutting and optimization of cutting parameters using monte carlo method

“…In the field of laser cutting, most of the time the optimal cutting conditions are determined using the Taguchi method (Prajapati et al, 2013) and by coupling response surface models (Sivarao et al, 2013) and ANNs models with different optimization and metaheuristic algorithms such as particle swarm optimization (Ciurana et al, 2009), genetic algorithm (GA) (Tsai et al, 2008), and simulated annealing (Chaki & Ghosal, 2011). The open literature reveals several research attempts based on ANNs such as for modeling and optimization of laser micromachining process (Ciurana et al, 2009;Biswas et al, 2010;Dhara et al, 2008;Dhupal et al, 2007), selection of optimal laser cutting parameters through integration of ANNs with GA (Tsai et al, 2008;Ghoreishi & Nakhjavani 2008), development of a prediction model through integration with the Taguchi method (Yang et al, 2012) and parametric modeling and optimization of lasox cutting (Chaki & Ghosal, 2011). The ANNs are the learning algorithms and mathematical models, which imitate the information processing capability of human brain and can be applied to non-linear and complex data, even if the data are imprecise and noisy (Raja et al, 2012).…”

Comparative Regression and Neural Network Modeling of Roughness and Kerf Width in CO2 Laser Cutting of Aluminium

“…They found that the ANN model could effectively predict the surface quality. Chaki and Ghosal [14] developed simulated annealing hybrid with ANN model for predicting the quality of cut during laser cutting of mild steel plates and concluded that optimization using this hybrid simulated annealing with ANN optimization yields good accuracy. Yang et al [15] combined Taguchi with ANN model for the prediction of responses in laser cutting and confirmed that the training samples can be reduced by this hybrid approach.…”

Evaluation and optimal design of supersonic nozzle for laser-assisted oxygen cutting of thick steel sections

“…Sundar [9] developed a regression analysis model to describe the effect of the independent processing parameters on cut quality for LASOX. Artificial neural network was also used to optimize cutting parameters for LASOX [10]. It was found that gas pressure and cutting speed had pronounced effect on cut quality.…”