Prediction Model of Corrosion Current Density Induced by Stray Current Based on QPSO-Driven Neural Network

Table 2

Parameters of the QPSO-ANN algorithm.

QPSO
Population size	80
Max iterations	300
Contraction-expansion coefficient	0.5
ANN
Number of input neurons	4
Number of output neurons	1
Transfer function in hidden layer	Tansig
Transfer function in output layer	Purelin
Learning rate	0.01
Training times	300