基于计算智能的射孔枪结构优化设计方法  

Structural Optimum Design Method of the Perforating Gun Based on Computing Intelligence

作　　者：常亚萍[1] 邹宽城[1] 韩秀清[1] 

机构地区：[1]长春工业大学,长春130012

出　　处：《微计算机信息》2009年第16期270-272,共3页Control & Automation

基　　金：国家高技术研究发展计划(863计划)(2006AA09Z326);吉林省科技发展计划项目(20060535)基金资助项目

摘　　要：在对石油射孔枪结构进行有限元静、动力分析的基础上,利用BP神经网络对有限元分析得出的样本数据,建立射孔枪结构设计参数盲孔处的最大应力(输入)与盲孔深度、盲孔直径(输出)的全局性映射关系,获得遗传算法求解结构优化问题所需的目标函数值。最后,用改进的遗传算法进行射孔枪结构的优化设计。结果表明,基于神经网络和遗传算法的优化技术应用在射孔枪结构的优化设计中是有效、合理的。从广义的角度,作为结构优化问题求解方法的一个探讨,本文所提出的优化技术,也为工程领域中复杂、多变量,尤其是优化设计目标无法或难以表示成设计变量的显函数的优化问题的求解提供了新的思路和技术手段。With the development of optimal technology, optimal design of structure has been applied in the perforating gun structural optimization. On the base of finite element method analysis on perforating gun frame structure, a non -linear mapping function from multiple input data Blind Hole at maximum stress （design variables） to multiple output data （Blind hole depth, Blind hole diameter） calculated by Finite Element Analysis was constructed with in BP neural networks. It is necessary to obtain the objective function values in optimum design of structures were put forward by using genetic algorithms. The results showed that on the basis Of Artifi- cial Neural Networks and Genetic Algorithm optimal technology applied in optimal design of perforating gun structure was effective and reasonable. As a discussion of the method to optimization,the method proposed in this paper also provides a new thought and method for complex structure with multi-variables,especially for those Optimization problems in which the optimization object can hardly be explicitly expressed as the function of design variables.

关 键 词：射孔枪 结构优化 神经网络 遗传算法 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]