Case study · Oil & Energy
Autonomous Crude Assay Blending & Distillation Yield Optimization
A Gulf Coast complex downstream refiner and midstream operator processing 180,000 barrels per day across crude distillation, catalytic cracking, and product blending units.
Engagement record
- Client
- Downstream refiner
- Industry
- Oil & Energy
- System
- Thermodynamic Blending & Yield Intelligence
- Timeline
- 8 Weeks
About this write-up
This case study describes the engagement as recorded. The client is not named; figures and outcomes are as reported by the client and have not been independently audited.
The challenge
The client's linear programming (LP) planning tools ran on weekly static cycles, failing to adapt to real-time tank stratification and crude assay delivery variances. As a result, product blenders over-added expensive reformate and alkylate to guarantee 87 and 93 octane specifications, giving away an estimated $0.28 per barrel in octane and Reid Vapor Pressure (RVP) margin.
Objectives
- Ingest LIMS component assays and DCS crude distillation unit temperatures in real time.
- Predict non-linear blend property interactions (octane number, RVP, sulfur, distillation points).
- Calculate least-cost component recipe additions for finished gasoline and diesel tanks in under 10 minutes.
- Eliminate off-spec tank re-blending and reduce product component giveaway by >80%.
Discovery
Historical tank batch audits revealed that 74% of finished gasoline batches exceeded octane specs by 0.6–1.2 AKI points. Blenders operated conservatively because static laboratory assays were 12 to 24 hours old by the time recipes were pumped.
What was built
- DCS & LIMS Ingestion Pipeline. Secure read-only OPC-UA bridge connecting OSIsoft PI historian tags with laboratory chromatography assays.
- Non-Linear Thermodynamic Engine. Neural physics-informed algorithms modeling true boiling point (TBP) curves and component blending interactions.
- Supervisory Blending Console. Control room advisory interface calculating exact component valve flow setpoints with operator verification checkpoints.
- Closed-Loop Model Recalibration. Post-blend laboratory certification results automatically update tank stratification coefficients continuously.
Outcomes as reported
Reported summary: +3.4% Refining Margin Lift & $3.2M Annual Value.
| Figure | What it refers to |
|---|---|
| +3.4% Margin Lift | Representing $3.2M in unlocked annual refining value |
| 4h → 8 mins | Blend recipe calculation turnaround compressed by 96% |
| -82% Giveaway | In expensive high-octane reformate and alkylate blendstocks |
| 0 Off-Spec Batches | Across 400+ finished product blending runs |
Figures as reported in the engagement record; not independently audited.
Lessons
- Displaying real-time margin cost per component gives control room board operators immediate economic clarity when adjusting recipe trims.
- Read-only DCS integration satisfies refinery cybersecurity without requiring operational shutdown windows.
Next steps
Extending predictive yield analytics to fluid catalytic cracking (FCC) unit catalyst circulation and hydrocracker hydrogen consumption optimization.
Implementation questions
No. Fortiv operates on existing DCS flow transmitter telemetry and LIMS laboratory assays via standard software bridges without physical hardware CapEx.
Strict regulatory guardrails for octane, RVP, benzene content, and distillation curves are hard-coded as non-violable boundary limits in the optimization solver.
We connect with Honeywell Experion, Emerson DeltaV, Yokogawa CENTUM, and OSIsoft PI System data historians.
Yes. Operators retain 100% supervisory control, with single-click manual override capability and automated logging of operational rationale.
