Prediction of welding responses using AI approach: adaptive neuro-fuzzy inference system and genetic programming

Laser welding of thin sheets has widespread application in various fields such as battery manufacturing, automobiles, aviation, electronics circuits and medical sciences. Hence, it is very essential to develop a predictive model using artificial intelligence order achieve high-quality weldments an economical manner. In the present study, two advanced techniques, namely adaptive neuro-fuzzy inference system (ANFIS) multi-gene genetic programming (MGGP), were implemented predict responses heat-affected zone, surface roughness strength during joining Nd:YAG laser. The study attempts appropriate for process. proposed methodology, 70% experimental data constitutes training set whereas remaining 30% used testing set. results this indicated that root-mean-square error (RMSE) tested ranges between 7 16% MGGP model, while RMSE lies 18–35% ANFIS model. indicates predicts superior manner laser process can be applied accurate prediction performance measures.