Sign in Subscribe
Machine learning

Artificial Neural Networks Improve Drilling Performance Prediction

Strategic Insights

— 1 min read

Researchers at the Chengdu University of Technology have successfully developed an artificial neural network that can accurately predict drilling performance in the petroleum industry. The team, led by Xiong Xiuli, used a back-propagation artificial neural network (BP-ANN) to train a drilling performance prediction function based on field data from a vertical well in Xinjiang province. The new algorithm was found to improve training speed and testing accuracy, resulting in a significant increase in rate of penetration (ROP) and a decrease in inclination.

Key Takeaways:

  • The developed artificial neural network can accurately predict drilling performance in the petroleum industry, with a 408% increase in ROP and a 67% decrease in inclination.
  • The algorithm sets independent optimization strategies for different drilling performances (ROP, drill diameter, inclination, and azimuth) and reduces the number of tests required to find the best drilling performance.
  • The inclusion of mineral composition in the model effectively improves training speed and testing accuracy.
  • The research was funded by the Natural Science Foundation of Sichuan Province, the Key Laboratory of Deep Geodrilling Technology, Ministry of Land And Resources, and the Engineering Research Center of Rock-soil Drilling & Excavation And Protection.
  • The developed predictive function uses a combination of mineral composition and operational factors to predict drilling performance.

Statistics:

  • 408% increase in ROP (rate of penetration) using the developed algorithm
  • 67% decrease in inclination using the developed algorithm
  • 15(7):1-17, the article number for the published research in the Journal of Petroleum Exploration and Production Technology
  • 2025, the year in which the research was published
  • 362, the page number for the news report in Energy Weekly News

Sources:

  • Prediction and dynamic optimization of drilling performance based on the combination of mineral composition and operational factors. Journal of Petroleum Exploration and Production Technology, 2025, 15(7), 1-17.
  • Energy Weekly News. July 18, 2025; p 362.
  • NewsRx. Research from Chengdu University of Technology Provide New Insights into Artificial Neural Networks (Prediction and dynamic optimization of drilling performance based on the combination of mineral composition and operational factors). Energy Weekly News. July 18, 2025; p 362.

Read more