DATABIO FISHERIES II

PILOT : SMALL PELAGIC FISHERIES IMMEDIATE OPERATIONAL CHOICES

DATA – DRIVEN BIOECONOMY

LOCATION    FOSNAVÅG

COUNTRY    NORWAY

CONTACT NAME    KARL GUNNAR AARSÆTHER

WEB    https://www.databio.eu/en/pilots/

EMAIL    pilot will develop technologies to assist the fishing vessel crew in making the best decisions to improve vessel energy efficiency and fish quality. The specific operational choices which will be addressed are: • Propu

PILOT PRODUCT DESCRIPTION

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

  • Propulsion mode (diesel electric, diesel mechanic, hybrid).
  • Which auxiliary engine(s) to run.
  • Using the main engine(s) for electricity production?
  • Loading of the vessel to reduce wave movements and thereby increase catch quality.
  • The main motivation for this pilot is: 
    • Improve catch efficiency through improved energy efficiency.

     

    Improve vessel operations by use of acquired data originating on the vessel in combination with meteorological data.Loading of the vessel to reduce resistance.

Operational data have provided valuable insight in how the operational choices affects fuel economy for fishing vessels. To increase the usefulness of such data, the considerable effect of parameters such as waves, wind, and load condition must be taken into account. This pilot will do this by combining onboard measurements with available meteorological and oceanographical data, so that the connection between more parameters can be more accurately modelled. This also makes it possible to remove the noise unmodelled effects inflict on the data, making it possible to study the effect of any operational parameter with more confidence. This includes, but is not limited to, how to operate the vessel in the most economical way in terms of propulsion mode, loading and use of auxiliary and main engines.

Another aspect which will be treated in this pilot, is how to reduce the degradation of catch quality because of vessel movements. This will be applied to vessels with RSW (refrigerated sea water) fish holding tanks. Based on large amounts of catch reports (time, species, size and position), coupled with the corresponding landing quality reports and the weather conditions along the vessel route, one wants to investigate and quantify 1) how vessel movements are affected by environmental conditions and operational choices (speed, trim, displacement) and 2) how fish quality is affected by vessel movements, species, initial catch condition and storage parameters (temperature, filling, design).

The challenges in this pilot are common to those in the A1 Pilot above, but excluding predictive maintenance, the main focus is on fuel reduction, energy optimization and to reduce degradation of catch quality.

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 large amounts of vessel measurements with meteorological and oceanographic hindcast, it will be possible to analyse how the vessel loading affects vessel movements and energy hull resistance. By combining measurements of vessel movements with reports of quality of landed fish, the relation between movements and catch quality can be analysed.

For a number of vessels:

  • 10 Hz 6DOF accelerations and velocities of the vessel
  • 1 Hz operational data (speed, energy consumption, machineries loads, propulsion choices).

For all Norwegian vessels:

  • Catch reports for all catches.
  • Sales reports all landings.
  • Quality reports from vessels for all landings.
  • Quality reports from landing site for all landings.
  • Meteorological data (wind and waves).

SINTEF Marine Data Center employs big data tools such as Apache Hadoop, Apache SPARK and GlusterFS for storage and analysis of incoming operational data from fishing vessels. Integration against other data sources, such as oceanographic and meteorological is planned.

This pilot will focus on the small pelagic fishing fleet, covering the North Atlantic Ocean. The Norwegian pelagic fishing fleet will be the main stakeholders. In this project they are represented by the ship owning companies Ervik & Saevik, Eros, Kings Bay, and Liegruppen. The main research partner is SINTEF Ocean.

Initially, the Norwegian pelagic fishing fleet will benefit from this pilot. But the results within energy efficiency will be general and easily transferable to both other fishing vessel types and other types of ships where the operational choices affecting energy efficiency is not trivial.

Within energy efficiency, SINTEF Ocean is working on a parallel project with much of the same aim, and a demonstrator is expected to be ready as a starting point for this pilot. For the work within the relationship between fish quality and vessel loading, the data gathering and onboard components are partly ready. The main work to be done in this pilot will be to develop Big Data methods and tools to take advantage of additional data sources. The average Technology Readiness Level of this pilot is approximately 4.

OBJETIVE OF THE PILOT

The main motivation for this pilot is:

  • Improve catch efficiency through improved energy efficiency.
  • Improve vessel operations by use of acquired data originating on the vessel in combination with meteorological data.

KPIS AND METRICS

The main KPIs of the pilot are:

  • Catch efficiency: Accumulated catch/accumulated nautical miles in [kg/m]. This shows the steaming distance required in order to catch fish and crew and fuel expenditure scales with increased steaming distance.
  • Accumulated fuel consumption/accumulated distance sailed [kg/m]. Fuel consumption (in tonnes or kg) pr sailed distance shows the effectiveness of the vessel and machinery system. This is both a function of machinery operation, and of nautical know how on how to save fuel with different cruising speeds.
  • Electrical end-consumers, share of total electric power output [-]. This KPI is the share of the electrical consumers power, which will together with main engine load indicates if there is extra capacity on the main engine to handle electric power production.
  • Energy main consumers, share of consumption [-]. This shows if a single power source dominates consumption.

PILOT PARTNERS