多Agent并行遗传算法在地震勘探属性优化中的应用
|
摘要
研究了基于多Agent的并行遗传算法,并将其应用于石油勘探的属性优化。针对常规遗传算法的不足,采用Agent构建多Agent系统实现了基于粗粒度的并行遗传算法,该算法能从进化环境中获取表征当前进化状态的有用信息,智能地监控调度GA的进化操作,在避免早熟的同时加快全局寻优,提高遗传算法搜索的效率,同时具有通讯开销小的特点。将该方法用于地震勘探属性优化,取得了良好的效果。
The method of design and implementation for parallel genetic algorithm is based on thick grain,with the multi-Agent combined with genetic evolution technology,to optimize the seismic attribution selection.A multi-Agent system includes two kinds of Agents:N-Agent and M-Agent,they can exchange the useful information which can represent the current situation of evolution.The methods are benefit to improve the performance of parallel genetic algorithm,and to raise the searching efficiency of the parallel genetic algorithm.The projecting feature in the parallel module is less communicating overhead.It was used in the optimization of oil exploration attribute selection and the result is good.
The method of design and implementation for parallel genetic algorithm is based on thick grain,with the multi-Agent combined with genetic evolution technology,to optimize the seismic attribution selection.A multi-Agent system includes two kinds of Agents:N-Agent and M-Agent,they can exchange the useful information which can represent the current situation of evolution.The methods are benefit to improve the performance of parallel genetic algorithm,and to raise the searching efficiency of the parallel genetic algorithm.The projecting feature in the parallel module is less communicating overhead.It was used in the optimization of oil exploration attribute selection and the result is good.
引文
[1]杨光正,等.一种薄层砂岩的分类方法[J].模式识别与人工智能,1994,7(4):312-316
[2]Srinivas M,Patnaik L M.Adaptive Probabilities of Crossoverand Mutation in Genetic Algorithms[J].IEEE Transaction onSystem,Man and Cybernetics,1994,24(4):656-667
[3]Hartvigsen G,Johnsan D.Corperation in a distributed artificialintelligence environment the stormcast application[J].Enginee-ring Apply of Artificial Intelligence,1990,3(3):229-237
[4]Onn S,Tennenholtz M.Determination of social laws for multi-Agent mobilization[J].Artificial Intelligence,1997,95(1):155-167
[5]Chaib-draa B,Millot P.A framework for cooperative work:Anapproach based on the intentionlity[J].AI in Engineering,1990(4):199-205
[6]Findler N V.Multiagent coordination and cooperation in a dis-tributed dynamic environment with limited resoures[J].Artifi-cial Intelligence in Engineering,1995,9:229-238
[7]Zhang C.Cooperation under uncertainty in distributed expertsystem[J].AI,1992,56:21-69
[8]丁明勇,代春艳,杨永斌.一种基于Multi-Agent的工程项目智能评标模型[J].计算机科学,2008,35(1):224-226
[9]梁军,程显毅.基于混合蚁群遗传算法的Agent联盟求解[J].计算机科学,2009,36(4):227-231
[2]Srinivas M,Patnaik L M.Adaptive Probabilities of Crossoverand Mutation in Genetic Algorithms[J].IEEE Transaction onSystem,Man and Cybernetics,1994,24(4):656-667
[3]Hartvigsen G,Johnsan D.Corperation in a distributed artificialintelligence environment the stormcast application[J].Enginee-ring Apply of Artificial Intelligence,1990,3(3):229-237
[4]Onn S,Tennenholtz M.Determination of social laws for multi-Agent mobilization[J].Artificial Intelligence,1997,95(1):155-167
[5]Chaib-draa B,Millot P.A framework for cooperative work:Anapproach based on the intentionlity[J].AI in Engineering,1990(4):199-205
[6]Findler N V.Multiagent coordination and cooperation in a dis-tributed dynamic environment with limited resoures[J].Artifi-cial Intelligence in Engineering,1995,9:229-238
[7]Zhang C.Cooperation under uncertainty in distributed expertsystem[J].AI,1992,56:21-69
[8]丁明勇,代春艳,杨永斌.一种基于Multi-Agent的工程项目智能评标模型[J].计算机科学,2008,35(1):224-226
[9]梁军,程显毅.基于混合蚁群遗传算法的Agent联盟求解[J].计算机科学,2009,36(4):227-231
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心