An improved genetic algorithm for searching for pollution sources

作     者：Quan-min BU Zhan-jun WANG Xing TONG 

作者机构：School of GovernmentNanjing University Center for Social Risk and Public Crisis Management of Nanjing University Institute of Chemical Industry of Forest Products 

出 版 物：《Water Science and Engineering》 (水科学与水工程（英文版）)

年 卷 期：2013年第6卷第4期

页      面：392-401页

核心收录：

学科分类：083002[工学-环境工程] 0830[工学-环境科学与工程（可授工学、理学、农学学位）] 07[理学] 08[工学] 080203[工学-机械设计及理论] 09[农学] 0903[农学-农业资源与环境] 0802[工学-机械工程] 0713[理学-生态学] 

基　　金：supported by the Science and Technology Support Program of Jiangsu Province(Grant No.BE2010738) Jiangsu Colleges and Universities Natural Science Foundation Funded Project(Grant No.08KJB620001) the Qing Lan Project of Jiangsu Province 

主　　题：genetic algorithm fitness selection crossover mutation pollution sources 

摘      要：As an optimization method that has experienced rapid development over the past 20 years, the genetic algorithm has been successfully applied in many fields, but it requires repeated searches based on the characteristics of high-speed computer calculation and conditions of the known relationship between the objective function and independent variables. There are several hundred generations of evolvement, but the functional relationship is unknown in pollution source searches. Therefore, the genetic algorithm cannot be used directly. Certain improvements need to be made based on the actual situation, so that the genetic algorithm can adapt to the actual conditions of environmental problems, and can be used in environmental monitoring and environmental quality assessment. Therefore, a series of methods are proposed for the improvement of the genetic algorithm： （1） the initial generation of individual groups should be artificially set and move from lightly polluted areas to heavily polluted areas; （2） intervention measures should be introduced in the competition between individuals; （3） guide individuals should be added; and （4） specific improvement programs should be put forward. Finally, the scientific rigor and rationality of the improved genetic algorithm are proven through an example.