Geometric form diagnosis of Ni60 alloy by laser cladding based on fuzzy neural network

Geometric form of Ni60 alloy fabricated by laser cladding is analyzed by a new diagnosis algorithm in which Back-propagation is combined with fuzzy classifier. In some complexity environments, the classic BP neural network appears limitation in classification. The proposed approach in this paper uses fuzzy model to the neural network structure. It considers classify variance and energy function to adjust convergence of the network. With the improved nonlinear mapping property, the proposed approach achieves perfect results with change all this term to identification ratio of 100% in our experiments, while that of the classical experiment is 57% accordingly.