AI in Oil and Gas: A New Era of Efficiency and Innovation

سال انتشار: 1403
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 47

متن کامل این مقاله منتشر نشده است و فقط به صورت چکیده یا چکیده مبسوط در پایگاه موجود می باشد.
توضیح: معمولا کلیه مقالاتی که کمتر از ۵ صفحه باشند در پایگاه سیویلیکا اصل مقاله (فول تکست) محسوب نمی شوند و فقط کاربران عضو بدون کسر اعتبار می توانند فایل آنها را دریافت نمایند.

استخراج به نرم افزارهای پژوهشی:

لینک ثابت به این مقاله:

شناسه ملی سند علمی:

GASCONF03_019

تاریخ نمایه سازی: 22 مرداد 1403

چکیده مقاله:

The oil and gas industry (OGI) is one of the largest industries with a profound global impact. The upstream sector, covering exploration, development and production of crude oil and natural gas, is the most capital-intensive segment. AI implementation in OGI is rapidly growing, providing more accurate methods across exploration, drilling, production and refining. Virtual intelligence techniques like artificial neural networks, evolutionary programming, and fuzzy logic have matured into powerful analytical tools used across disciplines to solve complex problems related to pressure analysis, well-log interpretation, reservoir characterization, and candidate-well selection. The industry has been exploring AI applications since the ۱۹۷۰s, but has more proactively sought such opportunities in recent years, coinciding with advancements in AI capabilities and the industry's shift towards the Oil and Gas ۴.۰ concept focused on utilizing advanced digital technologies. Oil and gas exploration involves creating ۳D geological models using geophysical and petrophysical studies, including seismic surveying, well logging, and core analysis. Seismic surveying produces traces representing elastic waves reflected from subsurface boundaries, which are processed to generate ۳D seismic cubes. Interpreters then segment the cubes by selecting points, lines, and surfaces related to layer boundaries - a computationally intensive, time-consuming process reliant on expert judgment. Modern deep learning-based pattern recognition techniques have accelerated seismic data interpretation by ۱۰-۱۰۰۰x. While not optimizing initial survey design, AI can add value by optimizing secondary surveys using recommender systems and machine learning interpolation. Well logging provides detailed physical property data along the wellbore, which petrophysicists use for rock typing, porosity/permeability estimation, and fluid saturation analysis. Researchers have used upscaling and reservoir modeling to construct reservoir models from geological models, reducing ۳D cells to forecast production over ۱۵-۲۰ years. The exploration process culminates in a ۳D geological model of the oil/gas field or reservoir.

نویسندگان

Afsaneh Mojez

Department of Petroleum Engineering, Tarbiat Modares University, Tehran, Iran