A framework for manufacturing features recognition using a Neural network trained by PSO Algorithm

Recently, the rule-based approach, the graph-based approach, the hint-based approach, the artificial neural networks based approach and the volume decomposition approach are the common feature recognition techniques available today. This work discusses a neural network approach for features recognition from B-rep solid modeler, which has significant effect on improving working efficiency in the product life cycle. PSO algorithm is applied to train the neural network. The PSO based NN training algorithm can converge faster and more easily achieve a global minimum