Comparison of Novel Optimization Algorithms on Intelligent Well Production Performance
Publish Year: 1390
نوع سند: مقاله کنفرانسی
زبان: English
View: 2,177
This Paper With 18 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
این Paper در بخشهای موضوعی زیر دسته بندی شده است:
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
ETEC01_022
تاریخ نمایه سازی: 11 اسفند 1390
Abstract:
Oil production optimization is one of the main targets of reservoir management. Smart well technology gives ability of real time oil production optimization. Although this technology has many advantages; optimum adjustment or sizing of corresponding valves is its issue. In this research, we present comparison of CPU time of different optimization algorithms for optimum port sizing of three ICDs in a horizontal well. Three methods of Response Surface (RSM), Taguchi and Neural Network (NN) are employed for this study. In this work; Quadratic Programming (QP) and Non Linear Programming (NLP) is implemented in Response Surface and Taguchi methods respectively. Another optimization algorithm named Particle Swarm Optimization (PSO) is implemented in Neural Network method. The results show that the Neural Network- PSO and Response Surface Method- QP give better performance comparing with the other combinations.
Keywords:
Inflow Control Device (ICD) , Smart Well , Artificial Neural Network (ANN) , Taguchi Method , Response Surface Method (RSM) , Particle Swarm Optimization (PSO)
Authors
morteza hassanabadi
Amirkabir University, Department of Mathematics, Research Institute of Petroleum Industry
sayyed mahdia motahhari
Amirkabir University, Department of Mathematics, Research Institute of Petroleum Industry
mahdi nadri pari
Research Institute of Petroleum Industry (RIPI), Research Institute of Petroleum Industry
amir abas askari
Research Institute of Petroleum Industry (RIPI), Research Institute of Petroleum Industry
مراجع و منابع این Paper:
لیست زیر مراجع و منابع استفاده شده در این Paper را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود Paper لینک شده اند :