工程优化问题中神经网络与进化算法的比较.PDF

计算机工程与应用 ， （ ） 1 Computer Engineering and Applications 2009 45 3 ◎博士论坛◎ 工程优化问题中神经网络与进化算法的比较 1 1 2 张煜东 ，吴乐南 ，吴含前 1 1 2 ZHANG Yu-dong ，WU Le-nan ，WU Han-qian 1.东南大学信息科学与工程学院，南京 210096 2.东南大学软件学院，南京 210096 1.School of Information Science Engineering ，Southeast University ，Nanjing 210096 ，China 2.School of Software ，Southeast University ，Nanjing 210096 ，China E-mail ：zhangyudongnuaa@ ZHANG Yu-dong ，WU Le-nan ，WU Han-qian.Comparison of neural network and evolutionary algorithm on engineering optimization.Computer Engineering and Applications ，2009 ，45 （3）：1-6. Abstract ：There are various types engineering optimization problems with different models and methods.This paper divides all the problems into two sorts ，black -box optimization and white -box optimization ，along with the deduction of their models.For the black-box optimization ，the superiority of Feed-forward Neural Network （FNN）on system approximation ，and the merits and de－ merits of Evolutionary Algorithm （EA）and Back Propagation （BP）on the weight values problems are discussed.For the white- box optimization ，the merits and demerits of EA and Recurrent Neural Network （RNN），and the survey on popular EAs and their common improvements are discussed.This article provides a more comprehensive cognition on current engineering optimization problem ，and the function by neural network and evolutionary algorithm. Key words ：engineering optimization ；Feed-forward Neural Network （FNN）；Recurrent Neural Network （RNN）；Evolutionary Algo－ rithm （EA） 摘 要：目前工程优化问题不仅种类繁多，而且各自采用的模型与方法迥异。从方法论的高度，将现有工程优化问题分为黑箱优化 与白箱优化，然后推出各自的优化模型。对于黑箱优化问题，阐述了前向神经网络在系统逼近上的优势，以及进化算法与 算法