Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Journal of Shanghai Jiaotong University》 2003-11
Add to Favorite Get Latest Update

A New Annealing Genetic Algorithm Based on Human-Machine Interaction

MIAO Yubin1,LIU Chengliang1,ZHAO Shuang2,TENG Hongfei2(1.School of Mechanical Eng., Shanghai Jiaotong Univ., Shanghai 200030, China; 2.School of Mechanical Eng., Dalian Univ. of Technology, Dalian 116024)  
By combining the artificial scheme with the algorithmic scheme, a new annealing genetic algorithm based on humanmachine interaction were put forward, being aimed at global optimal problems with complicated characteristics of largescale, nonlinear, nonconvex in the engineering. The initial population is formed by combining an artificial scheme(or artificial individual), and then, automatically, artificial individuals are introduced into the solution population from the immigrant pool based on the individual's duration during the period of annealing operation. After the artificial individuals crossing widely with the other individuals, new population is formed according to the Metropolis rule, thus the population quality is improved and the search direction is guided into a more promising domain. The modified selfadaptive genetic operators improved the global search capability of the whole population further. This method not only has better property of the evolution algorithm, but also can make full use of the human's activity, which indicates that it is a potential tool for the solution of complicated optimal problems. The simulation results demonstrate that the algorithm is effective and feasible. And it especially fits for complex global optimization problems.
【Fund】: 国家自然科学基金资助项目(50128504)
【CateGory Index】: TP18
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved