Summary: Neural networks are universal approximators for nonlinear functions. This study aimed to develop an algorithm for functional link artificial neural networks (FLANN), and to simulate insect’s food intake dynamics using this algorithm. Complete Matlab codes for the FLANN algorithm were given. Conventional models and FLANN were used to model accumulated food intake of the larva of a holometabolous insect, Spodoptera litura. Simulation performance of FLANN was compared against conventional models and sensitivity analysis was conducted on FLANN. The results showed that the FLANN algorithm performed better than conventional models in the simulation of dynamics and temperature-time dependent relationships of larvas’ food intake. The conventional models like fractional function, polynomial function, and exponential function were indicated to simulate the food intake dynamics at a higher accuracy but their performances were worse than FLANN. Both multivariate linear regression and trend surface models were used to describe temperature-time dependent relationships of food intake. The overall trend for this relationship could be simulated using these models; however, the simulation accuracy of these models was lower than FLANN. Sensitivity analysis showed that Legendre functions, Chebyshov functions, and trigonometric functions, used as the basis functions in FLANN, yielded better fitness than Laguerre functions and Hermite functions. The mean squared error of simulation using Legendre functions, Chebyshov functions, and trigonometric functions decreased by the increase of the number of these basis functions. Simulation performance also varied with the change of type of nonlinear functions and parameter values in the function. Linear functions, negative exponential functions and power functions were the best nonlinear functions, which yielded more stable outputs as the change of parameter values.