Modeling of metal inert gas welding process using radial basis function neural networks

In the present study, input-output relationships of metal inert gas welding process have modeled using radial basis function neural networks. As the performance of a neural network depends on its structure and parameters, some approaches have been developed to optimize them simultaneously. The performances of the developed approaches have been compared among them on some test cases. It has been observed that clustering plays an important role in deciding a suitable structure of the network. Moreover, it has been felt that a combined optimization scheme involving one global optimizer (a genetic algorithm) and one local optimizer (back-propagation algorithm) could be efficient to optimize both the structure and parameters of a network simultaneously.