Digitalization and operational optimization

The focus will be on operational experience and how to utilize data from different systems in order to create enhanced benefits of the data onboard and ashore.

by Frederik Hammer Berthelsen, DFDS

Co-organizers Ulrik Dam Nielsen, associate professor, DTU and Peter Blach, projektchef, Maskinmestrenes Forening

by Niels Tingleff Haastrup, associate professor, Fredericia Maskinmesterskole and Chief Officer, Molslinjen

 

Operationel optimization and digitization go hand-in-hand in the maritime sector. As an associate professor at Fredericia Maskinmesterskole and working also part-time as a chief officer at Molslinjen, Niels will share his operational experience with us from several shipping companies. Also Niels will present a Molslinjen development project, where the vast amounts of operational data collected, are analyzed by Fredericia Maskinmesterskole, SDU and UCL.

 

by  Tomas Lindqvist, Qtagg

 

Qtagg's EcoPilot connects the entire propulsion chain, so that normally independent systems work together to optimize the ship’s performance. The system reads data from sensors monitoring more than 60 parameters in real time, including engine performance, propeller performance, rudder lift and drag forces, ship motion and navigational information. Data from previous voyages together with weather and sea forecasts are used to minimize the total fuel consumption for each voyage. EcoPilot is an intelligent speed pilot, that will automatically give the best result in any weather condition. During the voyage, the system automatically adapts to changing operational requirements, operator input, sea, and ship conditions, continuously using all available information to ensure on-time arrival at the lowest cost, every voyage.

 

 

by Malte Mittendorf, PhD student, DTU

 

The presentation is addressing a machine learning-based approach for sea state identification using the wave buoy analogy. Measurement data of a Panamax container vessel sailing in the Northern Atlantic is utilized and neural networks are trained on time and frequency domain features derived from 6-DOF accelerations for the prediction of integral sea state parameters. The frequency domain model is trained on sequences of spectral ordinates derived from cross response spectra, while the time domain model is applied to 5-minute time series of ship responses. Additionally, multi-task learning was employed and the frequency domain method stood out in terms of accuracy and efficiency.

 

by Frederik Hammer Berthelsen, Vessel Performance Specialist, DFDS

 

In a shipping company many different datasets are available from the vessels, terminals etc. which can be combined for enhanced benefits of the data onboard and ashore. Furthermore, presentation of this data for involved stakeholders are crucial in order to take any data-driven decisions to optimize the operation and thereby save fuel and CO2. Therefore, we will look into how DFDS work with operational data from the vessels in order to do vessel performance and some different projects based on this data.