SPE Drilling Uncertainty Prediction Technical Section Competition Results: ML Techniques to Detect, Assess, and Grade Drill Bits from Bit Images Captured at the Drill Site

Includes a Live Web Event on 02/16/2023 at 11:00 AM (EST)

Quickly evaluating damage to drill bits at the end of a run can help optimize future drilling operations. Image capturing technology has developed to where bit photos with sufficient resolution for image processing can be easily captured at the rig site. Machine Learning (ML) has also improved significantly over the last decade. In 2022, the SPE DUPTS organized a university student competition to see if student teams could develop ML algorithms to automatically detect, assess and grade drill bits from bit images. This webinar showcases the approaches used by the top three winners of the competition.

This webinar is categorized under the Drilling and Data Science and Engineering Analytics technical disciplines.

All content contained within this webinar is copyrighted by Asma Yamani, Abdulbaset Ali and Cesar Vivas and its use and/or reproduction outside the portal requires express permission from Asma Yamani, Abdulbaset Ali and Cesar Vivas.

Asma Yamani

Asma Yamani received her B.S. degree in computer science from Imam Abdulrahman bin Faisal University, Saudi Arabia, in 2019 and her M.S. degree in computer science from King Fahd University of Petroleum and Minerals, Saudi Arabia, in 2020. She is currently pursuing her Ph.D. degree in computer science also at King Fahd University of Petroleum and Minerals, Saudi Arabia.

Yamani's research interest is in Applied Machine Learning. More specifically, in solving problems related to Petroleum Engineering and Energy using AI. She also worked on several projects related to NLP and Computer Vision. She is a Women in Data Science Ambassador and has been recently exploring ethical and usability issues related to AI systems.

Abdulbaset Ali

Abdulbaset Ali received his M.S. degree in electrical engineering from Rochester Institute of Technology, NY, USA, in 2009 and his Ph.D. degree in electrical and computer engineering from the University of Waterloo, ON, Canada, in 2017. He is currently a postdoctoral fellow at the Memorial University of Newfoundland, NL, Canada working on a drilling data analytics project to enhance drilling efficiency and reduce carbon emissions. Abdulbaset is interested in working on projects related to machine learning and computer vision and welcomes collaboration.

Cesar Vivas

Cesar Vivas is a Ph.D. Candidate at University of Oklahoma, Geothermal and Thermal Energy Storage Research Group. Before embarking on a Ph.D. at OU Mewbourne School of Petroleum and Geological Engineering, where he investigated the use of oil and gas infrastructure for geothermal and thermal energy storage, Cesar was a Principal Applications Engineer and Country Services Lead of Coring and Downhole Tools with Halliburton. Cesar garnered over 10 years of oil and gas experience in several roles and locations in onshore and offshore operations.

Pradeep Ashok (Moderator)

Pradeep Ashok is a PhD. in mechanical engineering and a senior research scientist at the University of Texas at Austin where he performs research on drilling automation technologies. He has published more than 50 papers related to drilling automation covering topics on modelling, controls, sensor development, data analytics, ML/AI, etc.

Pradeep Ashok is also the CTO of Intellicess, and in that role has guided the development and deployment of Sentinel RT™, a hybrid (combination AI and Physics based) drilling advisory software on more than 1200 wells.

He actively volunteers his time for SPE and IADC and is currently on the organizing committee for the SPE/IADC drilling conference. He is also the student competition chair for the SPE DUPTS (Drilling Uncertainty and Predictions Technical Section) which in 2022 hosted a student competition on the development of an AI model for automatically grading used drill bits.

SPE Webinars are FREE to members courtesy of the

image

Key:

Complete
Failed
Available
Locked
SPE Drilling Uncertainty Prediction Technical Section Competition Results: ML Techniques to Detect, Assess, and Grade Drill Bits from Bit Images Captured at the Drill Site
02/16/2023 at 11:00 AM (EST)  |  90 minutes
02/16/2023 at 11:00 AM (EST)  |  90 minutes
Survey
20 Questions
Certificate
Live and Archive Viewing: 0.15 CEU/1.5 PDH credits and certificate available
Live and Archive Viewing: 0.15 CEU/1.5 PDH credits and certificate available