BelgiumLogistics and transport2024 – ongoingExmar
Toqua machine-learning vessel performance models in fleet voyage optimisation
Exmar rolled out Toqua vessel models fleet-wide after a trial, with fuel savings of up to 3% on top of its voyage optimisation
Problem
Exmar relied on traditional methods such as sea trial curves and noon reports to judge how well its ships performed. These do not capture how a vessel performs across changing conditions.
Approach
Exmar worked with Toqua, which builds physics-informed machine learning models called Ship Kernels. Each kernel models the best a vessel can achieve, using sensor and operational data, and is updated with new performance data. After a trial showed significant potential, Exmar agreed to deploy the platform across its fleet. It plans to use the data for hull and engine monitoring, chartering decisions, sister vessel comparisons and voyage optimisation.
Results
Takeaway
Exmar added the models to a voyage optimisation tool it already had, and the gain was measured against that baseline.
Categories
- Industry
- Logistics and transport
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and MLOptimization
- Adoption
- Vendor solution
- Evidence
- Vendor case study
Sources
Source summaries
The report says Exmar agreed to deploy Toqua's platform across its fleet after a trial. It states that adding Ship Kernels to the existing voyage optimisation raised fuel savings by up to 3%. It quotes fleet manager Kristof Vercammen. The text reads like a company or vendor release and does not say how the savings were measured.
Full details are in the original sources.
