To speed up the antenna modeling and optimization， this paper conducts a modeling study for antenna parameter optimization by the commercially available antenna design software. Firstly， the back propagation（BP） neural networks are optimized by several commonly-used heuristic algorithms， and used to improve the antenna parameters. These parameters are compared and the best one is the one optimized by genetic algorithm BP （GABP）. Secondly， the adaptive algorithm and simulated annealing algorithm is used to optimize GABP. Finally， the minimum error of the adaptive GABP algorithm for antenna parameter optimization is verified by simulation tests. The study provides a new method for antenna optimization in antenna design software with less errors. It has higher prediction accuracy and much faster fitting speed. The feasibility of this algorithm is also demonstrated by experimental comparison.