{"stable_id":"de31cb71dafe6b28","slug":"modec-fpso-predictive-maintenance","company":"MODEC","workflow_name":"Sensor, digital-twin, and machine-learning predictive maintenance on FPSO MV29","function_code":"engineering","pattern_codes":["autonomous_with_backstop","continuous_decisioning"],"changed_assumption":"ML warnings can identify offshore equipment deterioration before conventional schedules or symptoms.","evidence_strength":"reported","publication_tier":"showcase","freshness":"current","reviewed_at":"2026-08-23","updated_at":"2026-08-22","source_quality_summary":"1 independent, 1 primary; publication outcomes are reported.","caveat_summary":"The 65% figure is MODEC's before/after attribution and is repeated by the World Economic Forum; neither source publishes an audited counterfactual or isolates machine learning from the wider digital-twin and data-platform program.","freshness_caveat":null,"workflow_summary":{"before":[{"actor":"Offshore and onshore operations teams","action":"Monitors equipment and addresses maintenance needs without a machine-learning early-warning layer.","actor_type":"control"},{"actor":"Maintenance team","action":"Inspect and repair equipment after a conventional maintenance trigger or emerging operational problem.","actor_type":"human"}],"hinge":"ML warnings can identify offshore equipment deterioration before conventional schedules or symptoms.","after":[{"actor":"Sensor network, digital twin, and ML models","action":"Analyze vessel operating data to detect deteriorating equipment performance and identify processing-plant problems.","actor_type":"system"},{"actor":"Offshore personnel and onshore support team","action":"Review the predictive signal, investigate the equipment, and decide the maintenance response.","actor_type":"human"}],"decision_mode":"bounded_autonomy","decision_marker":"AI acts within a human backstop"},"before":[{"order":1,"actor":"Offshore and onshore operations teams","action":"Monitors equipment and addresses maintenance needs without a machine-learning early-warning layer.","handoff_to":"Maintenance team","control":"Existing operating and safety procedures; the public sources do not disclose the former trigger cadence"},{"order":2,"actor":"Maintenance team","action":"Inspect and repair equipment after a conventional maintenance trigger or emerging operational problem.","handoff_to":"Vessel operations","control":"Human maintenance and operating authority"}],"after":[{"order":1,"actor":"Sensor network, digital twin, and ML models","action":"Analyze vessel operating data to detect deteriorating equipment performance and identify processing-plant problems earlier.","handoff_to":"Offshore personnel and onshore support team","control":"More than 10,000 vessel sensors and the modeled operating context"},{"order":2,"actor":"Offshore personnel and onshore support team","action":"Review the predictive signal, investigate the equipment, and decide the maintenance response.","handoff_to":"Maintenance execution and vessel operations","control":"People retain operating, maintenance, and safety authority"}],"decision_rights":"Models surface potential deterioration; MODEC's offshore and onshore personnel retain inspection, maintenance, and operating decisions.","exception_path":"Unconfirmed or unsupported predictions remain subject to human investigation and the vessel's existing operating and safety controls; the public sources do not describe autonomous shutdown authority.","removed_work":["No specific labor step is quantified as eliminated; the documented change is earlier problem identification"],"outcomes":[{"metric":"Vessel downtime","baseline":"MV29 operating period from the beginning of production before the reported digital-maintenance impact accumulated","result":"MODEC reported a 65% reduction in downtime","period":"From the beginning of MV29 production through January 2020 reporting","scale":"FPSO Cidade de Campos dos Goytacazes MV29, with more than 10,000 sensors on the vessel","attribution_caveat":"The 65% figure is MODEC's before/after attribution and is repeated by the World Economic Forum; neither source publishes an audited counterfactual or isolates machine learning from the wider digital-twin and data-platform program.","evidence_label":"reported"}],"executive_lesson":"The operating change was not a standalone model. MODEC joined dense sensing, a digital representation of the plant, predictive analytics, and teams able to investigate early enough to prevent downtime.","anti_pattern":"Attributing the full bundled downtime result to machine learning alone or allowing an unconfirmed prediction to bypass vessel safety authority.","questions_for_leaders":["Can the team act inside the model's warning window?","How is the isolated contribution of each digital component measured?"],"collections":[],"bundle_version":"1.0.0","bundle_fingerprint":"sha256:c23c6cc2b88153d008ea8fda928f632ce0011fc2d4c5036672a16e5d895bab93","canonical_url":"https://brianletort.ai/transformations/modec-fpso-predictive-maintenance"}