基于粒子群算法的射孔施工设计优化研究

发布时间：2018-05-23 20:39

本文选题：射孔施工设计 + 离散粒子群算法　；参考：《东北石油大学》2015年硕士论文

【摘要】：射孔是油田产能建设中非常重要的一环,直接影响到对油气藏的正确评价。射孔施工设计的结果对射孔起到直接指导作用,优质的射孔施工设计结果,可以达到控制射孔成本,提高射孔效益的目的。同时,较多的约束条件使得射孔施工设计优化问题的求解比较困难,因此射孔施工设计优化具有较高的现实意义和理论价值。本文以粒子群算法作为基本优化手段。针对两类射孔施工设计优化问题,通过设计符合问题特征的编码方案和改进粒子位置更新方式,提出相应的离散粒子群算法进行求解,主要研究内容概括如下:1、在标准粒子群算法的基础上重新定义粒子的表示形式,并通过动态调整惯性权重改进粒子位置更新方式,提出了动态自适应的离散粒子群算法求解以射孔枪总长为单一优化目标的电缆输送式射孔施工设计优化问题。该算法在保证粒子能在离散域更新的同时,又改善了算法的搜索性能。通过实验验证了算法的有效性和可行性。2、基于Pareto支配概念,设计了一种基于Maximin适应度函数和拥挤距离的多目标可行解优劣性判别方法,提出了一种截断式和循环式相结合的混合型外部档案保留策略,并结合改进的离散粒子群算法,给出了油管输送式射孔施工设计优化问题的求解方法,该问题以射孔枪总长和射开层盲区数量为优化目标。该算法的优劣性判别方法使得优质的粒子优先被保留,而混合型的保留策略使得算法在求出多样化的非支配解的同时,有效降低了算法的时间复杂度。实验证明算法取得了良好的设计效果。3、基于本文所提出的射孔施工设计方法,设计并实现了射孔施工设计系统,通过测试证明了系统的应用效果良好。并对全文所做的研究工作进行了总结和展望。
[Abstract]:Perforation is a very important part of oilfield productivity construction, which directly affects the correct evaluation of oil and gas reservoirs. The result of perforation construction design plays a direct guiding role in perforation design. The high quality perforation design result can control the perforation cost and improve the perforation benefit. At the same time, more constraints make it difficult to solve the optimization problem of perforation construction design, so the optimization of perforation construction design has higher practical significance and theoretical value. In this paper, particle swarm optimization (PSO) is used as the basic optimization method. For two kinds of perforation design optimization problems, a discrete particle swarm optimization algorithm is proposed to solve the problem by designing a coding scheme that conforms to the characteristics of the problem and improving the particle position updating method. The main research contents are summarized as follows: 1. Based on the standard particle swarm optimization algorithm, the representation of particles is redefined, and the updating method of particle position is improved by dynamically adjusting inertia weight. A dynamic adaptive discrete particle swarm optimization algorithm is proposed to solve the optimization problem of cable conveying perforation design with the total length of perforating gun as a single optimization object. The algorithm not only ensures that particles can be updated in discrete domain, but also improves the search performance of the algorithm. The validity and feasibility of the algorithm are verified by experiments. Based on the concept of Pareto domination, a multi-objective feasible solution identification method based on Maximin fitness function and congestion distance is designed. In this paper, a hybrid external file retention strategy combining truncation and circulation is proposed, and an improved discrete particle swarm optimization algorithm is proposed to solve the optimization problem in the design of tube-conveying perforation. The aim of this problem is to optimize the total length of perforating gun and the number of blind areas of perforating layer. The superiority and inferiority of the algorithm make the high quality particles to be preserved first, while the hybrid retention strategy makes the algorithm obtain a variety of non-dominated solutions, while effectively reducing the time complexity of the algorithm. Experimental results show that the algorithm has achieved a good design effect. Based on the perforation construction design method proposed in this paper, the perforation construction design system is designed and implemented. The test results show that the system has a good application effect. The research work done in this paper is summarized and prospected.
【学位授予单位】：东北石油大学
【学位级别】：硕士
【学位授予年份】：2015
【分类号】：TE257.1;TP18

【相似文献】