Neuro-Fuzzy Model for the Prediction and Classification of the Fused Zone Levels of Imperfections in Ti6Al4V Alloy Butt Weld

Table 5

Neural network architecture and performance for the reverse approach.

Process parameters	Neurons in the input layer	Neurons in the hidden layer	Neurons in the output layer	Regression slope for training	Regression slope for validation	Correlation coefficient
Laser power	3	11	1	0.976	0.942	0.907
Welding speed	3	14	1	0.986	0.952	0.904