Fuzzy Optimization of an Elevator Mechanism Applying the Genetic Algorithm and Neural Networks  

作　　者：XI Ping-yuan WANG Bing SHENTU Liu-fang HU Heng-yin 

机构地区：[1]Mechanical Engineering Department, Huaihai Institute of Technology, Lianyungang 222005, P. R. China [2]Engineering Department, Continental Teves Corporation （ LYG ） Co. , Ltd, Lianyungang 222005, P. R. China

出　　处：《International Journal of Plant Engineering and Management》2005年第4期236-240,共5页国际设备工程与管理（英文版）

基　　金：ThispaperissupportedbytheNaturalScienceFoundationofJiangsuProvince,China(01KJB460010)

摘　　要：Considering the indefinite character of the value of design parameters and being satisfied with load-bearing capacity and stiffness, the fuzzy optimization mathematical model is set up to minimize the volume of tooth corona of a worm gear in an elevator mechanism. The method of second-class comprehensive evaluation was used based on the optimal level cut set, thus the optimal level value of every fuzzy constraint can be attained; the fuzzy optimization is transformed into the usual optimization. The Fast Back Propagation of the neural networks algorithm are adopted to train feed-forward networks so as to fit a relative coefficient. Then the fitness function with penalty terms is built by a penalty strategy, a neural networks program is recalled, and solver functions of the Genetic Algorithm Toolbox of Matlab software are adopted to solve the optimization model.Considering the indefinite character of the value of design parameters and being satisfied with load-bearing capacity and stiffness, the fuzzy optimization mathematical model is set up to minimize the volume of tooth corona of a worm gear in an elevator mechanism. The method of second-class comprehensive evaluation was used based on the optimal level cut set, thus the optimal level value of every fuzzy constraint can be attained; the fuzzy optimization is transformed into the usual optimization. The Fast Back Propagation of the neural networks algorithm are adopted to train feed-forward networks so as to fit a relative coefficient. Then the fitness function with penalty terms is built by a penalty strategy, a neural networks program is recalled, and solver functions of the Genetic Algorithm Toolbox of Matlab software are adopted to solve the optimization model.

关 键 词：elevator mechanism fuzzy design optimization genetic algorithm and neural networks toolbox 

分 类 号：TU857[建筑科学] TP183[自动化与计算机技术—控制理论与控制工程]