Chevron Deploys AI-Powered IOCaaS for Artificial Lift Optimization at Kaybob Duvernay

Title

Chevron Deploys AI-Powered IOCaaS for Artificial Lift Optimization at Kaybob Duvernay

Content

Chevron deployed an AI-driven Integrated Operations Center as a Service (IOCaaS), developed by OPX Ai, at the Kaybob Duvernay Formation in Alberta starting in 2020 and fully live by early 2022 after a phased 12-month rollout. The system monitors dozens of gas wells, associated compressors, and a central processing facility, and over the first year of full operation delivered a 5% reduction in lease operating expenses (LOE) and roughly 6% higher BOE output than originally projected, after normalizing for new-drill wells, with avoidance of an estimated 71,000 BOE of deferred production and several million dollars in cost savings over a 12-month period. The architecture integrates field SCADA, data historians, and Chevron's ERP — including real-time wellhead pressures, compressor statuses, plunger lift cycles, and maintenance work orders — into a cloud-based IOCaaS platform with edge-deployed microservices. OPX Ai's domain experts worked closely with Chevron's production engineers to configure AI models to site-specific conditions, for example tailoring the hydrate model to the field's gas composition and pipeline network. The shift to exception-based management was the core operational change. Instead of personnel watching screens 24 hours a day, 7 days a week, the system monitors every well and piece of equipment autonomously and alerts engineers only when anomalies are detected. In one example, the AI flagged an anomalous drop in plunger travel velocity on a single well — a subtle sign of liquid loading — prompting operator intervention hours before that well would have accumulated enough fluid to trigger an automatic shutdown. The AI artificial lift optimizer also systematically trimmed plunger gas injection on many wells, saving fuel and compressor runtime. In separate pilots, IOCaaS delivered surveillance efficiency improvements of up to 30%, allowing engineers to manage a greater number of wells per person and helping mitigate ongoing workforce shortages. Chevron kept humans in the loop throughout. Engineers were required to manually review and approve each AI-recommended action, with progressively more decisions handed off to the system as model accuracy proved out. By the end of the deployment year, Chevron allowed the IOCaaS to autonomously adjust certain gas lift valve set points and regenerate compressor restarts (within safety limits) without direct human approval. The same IOCaaS model has since been adopted by ConocoPhillips in its Montney asset in British Columbia, where a greenfield digital infrastructure enabled a 4-month kickoff-to-deployment timeline — roughly one-third of the time required to stand up a conventional operations center.