Hull Performance Twin Validation Index (HTVI)

GMI-MAR-025Maritime IndustriesIntegration-Required

Definition

Accuracy of hull performance twin factor decomposition against known-condition reference points.

The Measurement Gap

What This Metric Measures

HTVI measures the accuracy of the hull performance digital twin's factor decomposition when compared against known-condition reference points: post-dry-dock clean hull, controlled speed trials, or hull cleaning events. At these reference points, at least one performance factor is known (fouling is zero after cleaning, weather is recorded during speed trials), enabling validation of the twin's decomposition model.

The Decision It Supports

When the twin says the 3% speed loss is 60% fouling and 40% weather, can the fleet performance manager trust that attribution, or is the twin's decomposition model drifting from reality? Incorrect attribution leads to wrong decisions: if the twin says fouling when the real cause is engine degradation, the fleet schedules an unnecessary hull cleaning while ignoring a developing engine problem. HTVI validates the twin's ability to correctly attribute performance loss to its actual causes.

Why Legacy Metrics Cannot See This

Traditional hull performance monitoring tracks total speed-power deviation from a baseline curve. It shows that the vessel is 3% below reference performance but cannot decompose the causes. The digital twin claims to provide this decomposition, but no standard metric validates whether the decomposition is accurate. HTVI uses reference events where at least one factor is controlled to test whether the twin's model matches reality when reality is known.

Formula

Primary Formula

HTVI = 1 - |Twin_predicted_performance - Actual_measured_performance| / Actual_measured_performance

Measured at reference events where at least one performance factor is controlled or known.

Variable Definitions

  • Twin_predicted_performance = the twin's predicted speed, consumption, or power output at the reference condition
  • Actual_measured_performance = measured speed, consumption, or power at the reference condition
  • Reference conditions = post-dry-dock (fouling equals zero), controlled speed trial (weather is known), post-hull-clean (fouling resets to near-zero)

Units:

0 to 1. A value of 1.0 means perfect prediction at reference points. A declining trend indicates the twin's calibration is drifting from reality over time.

Edge Cases

Reference events are infrequent: dry-dock every 5 years, speed trials rare. Supplement with post-hull-cleaning events (more frequent) and weather-controlled calm-sea transits as natural reference points. Twin recalibration resets HTVI: track pre-calibration and post-calibration HTVI separately to measure the calibration benefit. Minimum of 3 reference events per vessel per measurement period, which may require 12-month windows.

Proposed formula, pending validation pilots.

At a Glance

Unit
Score (0 to 1)
Trend Direction
Toward 1.0
Reporting Frequency
Per reference event
Category
Digital Twin Fidelity and Model Validation
← Shore-Ship Override Value Index (SSOV)Biofouling Assessment Calibration (BAC) →

Assess Your Organization

The AI-GPS Assessment evaluates your AI governance maturity and recommends KPIs like this one for your implementation roadmap.

Take the Free AI-GPS Assessment