TULSA, Okla., Sept. 12, 2018 – With the increasing urgency in oil and gas to embrace disruptive technologies like Big Data, artificial intelligence (AI) and the Internet of Things (IoT), many operators see predictive analytics and machine learning as a business-driven path to digital transformation.
Predictive analytics has many potential applications in oil and gas. A common application uses scenario-based simulations to anticipate maintenance events and avoid equipment failure. When combined with machine-learning capabilities, predictive analytics can enable field operational systems to recognize data patterns and then take proactive maintenance measures. Studies show predictive analytics can reduce equipment maintenance costs and downtime significantly.*
For operators, the high potential return on investment makes predictive analytics an attractive opportunity. “When it comes to the digital oilfield, the most common question we hear from our clients is where to start,” said Stonebridge Consulting’s BJ Cummings, managing director of the EnerHub™ data management solution.
“While the answer is unique to each operator, most oil and gas companies today realize the inherent power of their data and how data analytics can be used to track problems. Predictive analytics takes the data conversation to a new level by creating a use case scenario for Big Data and digitization that makes business sense,” Cummings said.
As an example, Stonebridge is currently working with a mid-sized operator to co-create a predictive maintenance solution to anticipate plunger misses on its vertical wells. Each miss results in underperforming wells and lost production due to maintenance-related downtime.
The company teamed with Stonebridge to develop a plunger optimization solution that can predict plunger misses. By “learning” data variables such as pressure variances preceding past misses, acceptable casing, tubing, and line pressure ratios, and optimal after-flow durations, the solution will be able to recognize similar anomalies in the data and then proactively instruct the CygNet SCADA software to make necessary adjustments in one of many well controls such as tubing pressure automatic shut-in settings, maximum after flow durations, and even make suggestions on optimal plunger types such as bar stock versus dart. The machine-learning tool is built on Microsoft Power BI and will utilize the Databricks unified analytics platform.
“Our client expects this predictive maintenance solution will generate hundreds of thousands of dollars a year in savings,” said Stonebridge Senior Consultant Telha Ghanchi, who is leading the plunger optimization project. “What’s more, it provides them with an entrée into Big Data analytics that is both cost-effective and revenue-enhancing.”
About Stonebridge Consulting, LLC
Stonebridge Consulting provides business advisory and technology services for next-gen oil and gas. We serve the oil and gas industry exclusively. Our industry expertise, proven methodologies, and extensive project IP and solution accelerators enable us to deliver projects faster, generating measurable improvements in operational efficiency and saving project time and costs by as much as 50 percent. More information about Stonebridge is available at www.sbconsulting.com.
* Deloitte, “Predictive Maintenance: Taking pro-active measures based on advanced data analytics to predict and avoid machine failure.”
McKinsey Global Institute, “The Internet of Things: Mapping the Value Behind the Hype.”
NOTE: All product and company names are trademarks ™ or registered trademarks ® of their respective holders. Use of them does not imply any affiliation with or endorsement by them.