Development of an intelligent model to optimize heat-affected zone, kerf, and roughness in 309 stainless steel plasma cutting by using experimental results.

Plasma cutting is an effective way to cut hard metals. In this process, three output parameters cutting width (kerf), surface roughness (Ra) and heat-affected zone (HAZ) are critical factors which affect the quality and efficiency of the cutting. In this paper, an experimental study was conducted to investigate the cutting quality in terms of kerf, Ra, and HAZ for the 309 stainless steel plasma cutting. First, the research tested the effect of input parameters including current, gas pressure, and cutting speed on the process outputs. Then, the results were used to develop three predictive models by intelligent systems based on genetic algorithm (GA) and artificial neural network (ANN). Finally, a hybrid technique of genetically optimized neural network systems (GONNs) was designed and employed to simultaneously optimize the process outputs. The results show that the implemented strategy is an effective method for optimizing the output parameters in the plasma cutting process. [ABSTRACT FROM AUTHOR]