TotalEnergies

The model predicted drum level; it did not answer the switching decision

75% prediction accuracy; use case not retained. One delayed coker at Port Arthur, Texas; accuracy denominator unknown. Drum work began July 2025; named remarks reported 11 June 2026.

Sponsored conference report quoting a named site engineer. No accuracy definition, test count or quantified loss. This is one discontinued use case, not an abandoned AI program.

One useful warning model did not make every coker use case useful

A named TotalEnergies engineer said a 75%-accuracy drum-level model was not retained because switching also depended on conditions outside its scope.

No test denominator or definition for 75% accuracy. At least two acted-on alerts is not a total-alert count, avoided-trip count or reliability rate.

Limits: Named remarks in sponsored conference coverage; original slides and later company confirmation not located. Other uses continued. No quantified loss, avoided flaring, downtime benefit or full costs; do not call the whole pilot a failure.

Honeywell AI pilot aids coker unit operations at TotalEnergies refinery · 2026-06-11

TotalEnergies uses generative AI to check trading data

AWS describes a TotalEnergies Trading & Shipping system that matches structured and unstructured transaction data.

A named customer manager reports more reliable controls and fewer financial losses, without amounts, error rates, a baseline or an observation period.

Limits: Vendor-published customer testimony, not independent validation. No costs or net ROI. Matching records does not establish authority to place trades, release payments or change books. No specific model provider can be inferred from the Bedrock service description.

TotalEnergies puts Gen AI to work on its trading operations · Undated

TotalEnergies reportedly dropped one drum-cycling use case

Control Global quotes TotalEnergies engineer Thomas Klein saying a Port Arthur drum-level model achieved 75% prediction accuracy, but the drum-cycling use case was not retained.

The report does not define the accuracy denominator or test set, or quantify cost or loss. Other pilot work continued; the entire program was not reported abandoned.

Limits: Original conference reporting, labeled Sponsored. We could not retrieve the presentation or a later company statement. The earlier company release confirms the broader pilot, not the decision to drop this use case. Keep these figures separate from its five-event result.

Honeywell AI pilot aids coker unit operations at TotalEnergies refinery · 2026-06-11

TotalEnergies and Honeywell pilot AI-assisted control room · 2025-11-11