改进PSO算法在振荡式注汽速度优化中的应用

Improved PSO Algorithm and Its Application in Optimization of Oscillatory Steam Injection Rate

针对蒸汽驱恒定式注汽速度驱油效果差的现状,提出了一种基于改进PSO(Particle Swarm Optimization)算法的蒸汽驱振荡式注汽速度优化方法。该方法建立了蒸汽驱注汽速度数学模型,采用改进粒子群优化算法对此模型进行求解并优化振荡式注汽速度,最后得到蒸汽驱振荡式注汽速度最优方案。改进粒子群优化算法引入混沌优化算子产生初始解,依据各粒子适应值的距离,完成对各个粒子的自适应变异,同时引入极值扰动算子对个体历史最优值和全局最优值实施随机扰动,加快了收敛速度,提高了种群的可进化能力。实验结果表明:所建立模型准确,优化算法有效。通过此方法可指导蒸汽驱注采方案合理编制,指导蒸汽驱高效运行。

In view of the fact that the constant steam injection rate of steam flooding is poor,an oscillatory steam injection rate optimization method of steam flooding based on improved PSO(Particle Swarm Optimization) algorithm is proposed.Firstly,a mathematical model of steam injection rate of steam flooding is established.Then,the IPSO algorithm is used to solve the model and optimize of the oscillatory steam injection rate.Finally,the oscillatory steam injection rate optimization scheme of steam flooding is obtained.In the IPSO algorithm,we introduce chaos optimization operator to generate initial solutions and apply the self-adaptive mutation of particles according to the distance of the fitness of each particle.We adopt extreme disturbance on the individual history optimal values and global optimal value.It can speed up the convergence speed and increase the evolving ability of the population.The experimental results show that the established model is accurate and the optimization algorithm is effective.The proposed methodology can make steam flooding injection-production scheme more reasonable,ultimately contributing to its efficient operation.