This pilot will develop technologies to assist the fishing vessel crew in taking the best decisions to improve vessel energy efficiency and engine preventive maintenance. The specific operational choices which will be addressed are:

  • Loading of the vessel in the different possible configurations to reduce the hull resistance and reduce fuel consumption.
  • Reduction of the fuel consumption by means of taking in account sea surface currents and meteorological conditions to make an intelligent sailing.
  • Use of the data from the engine and propulsion sensors to predict in advance any mechanical failure for proactive maintenance and saving unproductive days at port and reduce the cost of the reparations (increase also safety of ships and crew on board due to reduced unexpected failures).

All the historic available data from 3 tuna purse seines built exactly with the same design in the same shipyard will be used in this pilot. In this case, a model of the hull used in the hydrodynamics channel is available together with the last two years of results of more than 100 sensors of the different engines and the propulsion system of the vessels with a sampling rate of every ten seconds. All this data with the route data (from AIS or vessels own plotters) and the historical data about meteorological conditions, sea currents and engine failures will be used to adjust the more appropriate models (end of life, machine learning algorithms, etc.) for giving immediate operational choices to oceanic tuna fisheries.

During the analysis period, the platforms and mechanisms to acquire in real or near to real time, the data from the engine and propulsion system sensors and for meteorological models will be set up in order to be ready for the second phase of providing immediate operational choices to the skippers or captains of the vessels minutes after sending the engine and propulsion data and receiving the meteorological models.

A central challenge is to develop models to reduce fuel consumption from the interaction between engine data, propulsion data, meteo data and the vessels design by means of big data approaches.

The second challenge is to use algorithms in real time to estimate the expected lifetime of different parts of the engine and propulsion system, or to learn when a part of the engine is close to failure and advice the technical staff in order to have the necessary parts and technicians at port and reduce the downtime for unexpected failures.

Another central challenge is to establish a common data management and analysis systems that combines data from the fleet in real time (engines, propulsion, route and speed of the vessel, destination), data coming from public institutions with different types of meteorological models and model outputs and finally data from Earth observation for sea surface currents and other oceanographic parameters.

The connection between operational choices and its consequences are difficult to reveal, since many hard to measure parameters and effects come into play. It is therefore assumed that employing big data methods, such as machine learning, to existing datasets will prove useful. By combining specific vessel measurements with meteorological and oceanographic hindcast, it will be possible to analyse how the vessel loading affects vessel movements and ship resistance.

  • Historical records of 117 measurements from the engine and propulsion system every 10 seconds. Access to real time data from the vessel in a second phase.
  • AZTI’s Marine Datacenter. Currently has implemented different databases for engine and propulsion parameters.
  • Integration against other data sources, such as oceanographic and meteorological parameters is planned.

South Atlantic and Indian Oceans are the main fishing grounds for the Basque Oceanic Tuna Purse Seine fleet but Europe has vessels all around the world.

Echebastar Fleet will be the main beneficiary of the developed technology at first, but, if successful, the creation of a company for exploitation of the technology as a service to other vessels owner is expected.

The whole Tuna purse seine industry will benefit from the implementation of such measurements. In the case of the condition based maintenance all the vessels with engines similar to the ones used by tuna purse seines will benefit of optimized maintenance intervals and improved propulsion condition. The improvement of propulsion system condition will not only save energy and money in maintenance; but will also increase safety of ships and crews that sail in remote areas.


The main motivation for this pilot is:

  • Reduce costs from fuel consumption on board while keeping the amount of catches.
  • Reduce maintenance costs and downtime of ship with precise event prediction prior to fault occurrence.


The main KPIs of the pilot are:

  • Fuel consumed per sailed nautical mile.
  • Fuel consumed per catch unit of mass [kg fuel/fish ton or kg].
  • Downtime hours due to main engine failure per year.
  • Miles sailed per catch unit of mass [Nautical mile/fish ton or kg].