Enterprise AI for Preventing Downtime of End Flash Gas Compressors

Challenge

A major liquified natural gas (LNG) company wants to improve the reliability of end flash gas compressor systems used for natural gas production. However, existing control systems of the compressor systems cannot accurately predict compressor failures in advance or provide the root cause analysis required for troubleshooting. Operators also struggled to decipher false alarms from material alarms due to the complexity of the data received. The unplanned shutdowns cause significant delays and increased maintenance costs. The company needed a better solution that could accurately predict failures, identify root causes, and improve the quality of alarms.

Approach

To address these issues and increase the reliability of its compressors, the LNG company selected C3 AI® Reliability. Within 8 weeks, the Baker Hughes and C3 AI team ingested over 1.4 billion data points from 4 disparate data sources, configured an anomaly detection model to predict compressor failures, and configured the C3 AI Reliability to provide high-level view of KPIs, AI alerts and asset health. With C3 AI Reliability, the company can accurately predict 89% of unplanned shutdowns with 5 days of lead time and reduce false alarms by 55%.

Project Objectives

• Reduce the number of false alarms created by rules-based systems (DCS system)
• Deliver a user-friendly application that uses machine learning to identify high-risk end flash gas compressor units and predict unplanned shutdowns in advance

The C3 AI Platform provides the necessary and comprehensive services to build enterprise-scale AI applications up to 25x faster than alternative approaches. The C3 AI Platform integrates all relevant data sources to rapidly generate predictive insights across the oil and gas value chain. When deployed at enterprise-scale, C3 AI applications can deliver up to $100 million and more in annual economic value to oil and gas organizations.