Strength modeling and optimizing ultrasonic welded parts of ABS-PMMA using artificial intelligence methods

The present work deals with modeling and optimization of ultrasonic welding (USW) process parameters including welding time, pressure, and vibration amplitude influencing strength of the welded parts of acrylonitrile butadiene styrene (ABS) and poly(methyl methacrylate) (PMMA) using artificial intelligence (AI) methods. Experiments performed on samples by spot welding workpieces of ABS and PMMA. The experimental data are used for training of artificial neural networks (ANN), adaptive neuro-fuzzy inference systems, and hybrid systems. It is found that ANN had better predictions compared with the other AI methods. The best model was a feed-forward back-propagation network, with uniform transfer functions (TANSIG-TANSIG-TANSIG) and 4/2 neurons in the first/second hidden layers. The best predictor is then presented to genetic algorithm (GA) and particle swarm optimization (PSO), as the fitness function and for optimizing the USW machine parameters. After the optimization, results of this part revealed that GA and PSO have comparable results and the calculated strength increased by 10%, as compared with a non-optimized case. In order to confirm the computational results, validating experiments are performed which their outputs demonstrates good agreement with the optimization result.