Case Study Icon
  • CASE STUDY

C3 IoT Trial: Large Oil Producer Predicts Equipment Failure

C3_Hero_1920x1080_Occidental1

One of the largest oil and gas producers in the United States launched the first phase of deployment of C3 Predictive Maintenance in just 12 weeks, demonstrating the capability of software analytics to accurately forecast equipment failure and improve condition-based maintenance of their beam pumps.

Their upstream portfolio consists of more than 22,000 wells distributed across 10 countries in North America, South America, and the Middle East. Approximately 17,000 wells in their portfolio have beam pump artificial lift technology. While beam pump technology is relatively inexpensive compared to other artificial lift technology, beam pumps also fail frequently, at rates ranging from 66% to 95% per year. These unexpected failures result in weeks of lost production, emergency maintenance expenses, and costly equipment replacements. To reduce the impact of these costly failures, the oil and gas producer deployed C3 Predictive Maintenance across more than 1,000 producing wells.

As part of the C3 IoT analytic software suite, C3 Predictive Maintenance employs machine learning-based algorithms to enhance failure prediction and diagnostic capabilities. The application augments traditional systems by continuously monitoring all instrument signals, tracking complex failure modes, and detecting operating anomalies associated with impending equipment failures for a large range of assets.

In this deployment, C3 IoT integrated daily sensor readings from in-field equipment and unstructured data (e.g., field notes and operator comments) from maintenance work orders. This comprehensive data integration and analysis gives service teams a comprehensive weeks-ahead view of emerging equipment maintenance requirements, with detailed supporting data and diagnostic tools to support maintenance decision making.

Based on this first phase of deployment, the oil producer and C3 IoT plan to scale the machine learning-based methods of C3 Predictive Maintenance to a larger set of artificial lift equipment across 22,000+ globally dispersed oil and gas producing wells.