BP神经网络以其结构简单、工作状态稳定等特点,成为当前应用最广的一种神经网络模型,应用范围包括识别分类、非线性映射、复杂系统仿真等方面。但是,BP网络也存在局部极小、收敛速度慢、网络结构选取困难等缺点。对此,已提出了多种改进算 Due to its simple structure and stable working condition, BP neural network has become the most widely used neural network model in recent years. Its application range includes identification classification, nonlinear mapping and complex system simulation. However, there are some shortcomings of BP network, such as local minima, slow convergence rate and difficulties in network structure selection. In this regard, a number of improvements have been proposed