TECH Byte: Predictive Analysis of Oil Well Maintenance in the Oil & Gas Industry

  • Starts: 2:30 pm on Wednesday, March 1, 2023
  • Ends: 3:30 pm on Wednesday, March 1, 2023
The TECH Byte series features a 20-minute talk on a technical topic followed by 10-15 minutes of Q&A.

Guest Speaker: Daur Aktaukenov, Visiting Scholar, MET Department of Computer Science

Abstract: The current competitive market condition in the oil and gas industry is so concentrated on companies' budgets that they require methods to extract oil from wells at the lowest possible cost. All pumping units, new or old, require regular preventive maintenance and constant inspection. With 90 percent of total oil production coming from sucker rod pumps, the cost of diagnostics must be reduced accordingly. The use of predictive diagnostics can help to detect equipment problems early, thereby minimizing unplanned downtime. Unplanned sudden oil well failures increase the company's operating costs, as well as increase risks of environmental pollution.

This presentation proposes a simple predictive model to help oil workers unfamiliar with Machine Learning build a reliable model for identifying oil well failures. It can also help geologists experienced with Machine Learning to improve the accuracy of failure identification and a more accurate approach to well-maintenance planning.

Unlike other studies in the field of predictive oil well repair detection, the innovation of this study is based on output data statistics such as per-well daily oil flowmeter readings. The volatility of these indications makes it possible to determine the probability of an oil well failure. This method also makes it possible to rank wells according to the principle of the most probable failures, which makes it easier to apply directly to oil fields by simple workers making decisions on workover planning.

DAUR AKTAUKENOV received his bachelor of science degree in Automation and Control from Kazakh-British Technical University, Kazakhstan, in 2012, and his master of science degree in Information Systems from L.N.Gumilyov Eurasian National University, Kazakhstan, in 2016. He is currently pursuing a PhD with the Institute of Automation and Information Technologies at Satbayev University, Kazakhstan. His research interests include clustering and predictive recognition in oil and gas.

In person registration:

Online registration: