The traditional BP neural network algorithm has some bugs such that it is easy to fall into local minimum and the slow convergence speed. Artificial Bee Colony Algorithm, which based on foraging behavior of honeybee swarms, is a new heuristic bionic algorithm and a typical kind of swarm intelligence algorithm. It is a global optimum algorithm with many advantages such as simple, convenient and strong robust. In this paper, a new BP neural network based on Artificial Bee Colony Algorithm was proposed to optimize the weight and threshold value of BP neural network. The result shows that the new algorithm improves the precision and expedites the convergence rate.