Case Studies

Using Analytics to Optimize Oil & Gas Drilling Processes

Posted by | Fuld & Company

Background

Recent research shows that the Oil & Gas industry is running well below its maximum production potential (https://www.mckinsey.com/industries/oil-and-gas/our-insights/why-oil-and-gas-companies-must-act-on-analytics). With a $200 billion performance gap, the industry must identify how this gap can be narrowed.

Challenge

One of Fuld & Company’s O&G clients was collecting vast amounts of data from the sensors attached to its drilling tools and equipment to track performance. However, while it was carrying out extensive analysis of the data points being collected, the company felt that further deep analysis was needed to derive additional value from the data. Our client had the resources to continuously look at the increasing volumes of data points and use them to make recommendations on maintenance requirements, with the help of SCADA (supervisory control and data acquisition) systems. But the client found that the major drawback of this method was that if any tool were modified at the rig or well, there was no corresponding real-time update in the system. With the company’s analysts receiving over 30,000 sensor data with more than 200 variables, this was an exceedingly complex task with a high chance of error.

Approach:

Fuld & Company’s O&G experts developed a solution to optimize the client’s drilling process by applying machine learning with customized predictive models that can anticipate tool failures and maintenance events, and identify which tool is suitable for which type of rig, well, mud type, etc:

  • Sensors attached to the drilling tool/equipment when they are sent to the site.
  • Metadata collected from the sensors to provide information about the tool, well, rig, operational settings, etc.
  • Resulting data points passed through the Fuld & Company machine learning algorithms to understand:
    • When & why a breakdown occurred
    • How efficiently it worked
    • Usage patterns
  • The machine learning algorithm understands & analyse these usage patterns and takes actions accordingly.

Outcome:

Fuld & Company’s algorithm helped the client fully exploit its drilling data and stay one step ahead of its competition by optimizing downtimes over the long term. Our algorithm also helped the client to:

  • Understand and predict the behavior and performance of the tool
  • Predict tool downtimes
  • Predict maintenance events
  • Extend the lifespan of tools
  • Avoid any on-site accident or failure to an accuracy of over 97%
  • Forecast production rates

With the help of Fuld & Company, the O&G client is able to save millions of US dollars through:

  • Timely maintenance events
  • Optimized (reduced) production costs
  • Improved process efficiency
  • Improved Reservoir Engineering and Upstream, Midstream, and Downstream Optimization

Tags: , , , , ,

Related Resources

Read More

Competitive Intelligence through conference tracking

A leading US-based global manufacturer, specializing in scientific and lab equipment, supplies, and software for scientists, faced a challenge. They […]

Read More

Sustainable innovation in the polymer industry

Delivering sustainable innovation How we helped a leading industrial polymer manufacturer cut 1.5 years off its R&D timeline… and win […]

Read More

Leveraging Machine Learning in customer sentiment analysis

In a highly competitive market, staying ahead of customer expectations is critical for any manufacturer. A leading US plumbing fixture […]

Subscribe to our mailing list for our latest updates: