Enterprise AI for Predicting Asset Failures

Challenge

A large hydrocarbon producer experienced a major unplanned shutdown due to asset failures and began to reevaluate its current asset maintenance strategy. Before engaging Baker Hughes and C3 AI, the company relied on rules-based control systems to detect operational anomalies. However, the control systems generated a high volume of alarms daily and operators struggled to distinguish false alarms from material anomalies. The control systems also could not accurately predict asset failures and operated in siloes. The company needed a better solution that could improve the quality of alarms, accurately predict failures before they occurred, and provide an integrated end-to-end view of assets.

Approach

To address these issues and increase the reliability of the critical systems, the company selected BHC3^® Reliability. Within 2 weeks, a Baker Hughes and C3 AI experts ingested and unified over 2 years of data for more than 2,500 assets from 27 locations. The team configured an anomaly detection pipeline to predict asset failures and provide root cause analyses for 2 critical upstream systems: gas compressors and water injection pumps. With BHC3 Reliability, the oil & gas company can generate over $10 millions of additional annual revenue and savings from increased uptime and reduced maintenance costs across the 2 systems: gas compressors and water injection pumps.

Project Objectives

• Configure ML algorithms to detect anomalies at the system and subsystem level
• Display prioritized alerts and recommended actions supported by a robust evidence package

Solution Architecture