In order to improve the calculation efficiency of flight load analysis in the design phase, surrogate models of flight load based on artificial neural network are researched in this paper. The horizontal tail of a turboprop aircraft is studied for example. The input cases and output loads for training and checking are obtained by flight simulation in the full flight envelope according to standards and horizontal tail distributed loads calculation. This paper builds three surrogate models of horizontal tail loads based on BP network, RBF network and ELM network respectively. And the accuracy and efficiency for horizontal tail root section loads prediction of different models are compared. We also conduct quantitative analysis of contribution for input load parameters. The study results show that all three neural network models are accurate, which can greatly improve the analysis efficiency of flight load.