Problem statement - Damen Shipyards (Damen) wants to use Big Data analysis to gain new market insights and forecast vessel demand. These insights are valuable because Damen keeps standardised vessels in stock in order to significantly reduce delivery times. This concept gives Damen a competitive advantage, but is not without risk since they must speculatively build vessels beforehand. As a case, Damen wants to improve the current forecasting methods for the thriving offshore wind market - for which they supply vessels - based on data derived from the Automatic Identification System (AIS). AIS data includes among others information about identification, location, speed, date and time of approximately 200.000 vessels worldwide. Made Smart Group (MSG) is an information service provider specialised in nautical information, and maintains the world’s largest AIS database. MSG and Damen joined forces for this research.

Objective - The objective of this research is to determine if and how Big Data analysis can be used to model (future) demand for Crew Transfer Vessels (CTV) being used for Crew Transfer Operations (CTO) in the offshore wind industry.

Methodology - Almost 45 million AIS location reports of 39 CTVs servicing 263 turbines in 3 offshore wind farms throughout 2016 are analysed to derive key figures of the executed CTOs. Key figures are e.g. the weather window, and the number of executed CTOs per hour. The CTV demand is modelled based on these key figures, and three wind farm specific input parameters: number of turbines, distance between wind farm and port, and the sea state distribution.

Results - The CTO demand of the 263 analysed wind turbines was on average 113 per year in 2016. This average CTO demand has a variation of almost 50% between turbine types. With an accuracy of 4%, it is modelled that a yearly average of 12.4 CTVs are needed to service these 263 turbines. Furthermore, the CTV demand decreases on average with 11% in the three analysed wind farms if the CTO limit can be increased from 1.5 m to 2.0 m mean significant wave height. This result in a potential cost saving around € 5.1 million on a yearly basis for these three wind farms alone.

Implications - AIS data can be used to model vessel demand and gain insight into the market size. The accuracy of the developed model can be improved by adding: more wind farm specific variables; and/ or data of more CTVs/ wind farms. The gained knowledge about using Big Data analysis to forecast the CTV market size is useful and important for the introduction and future development of commercial AIS based data analysis. Furthermore, it provides insights into the operational profile of CTVs. This can be used to develop better vessels, better service the market and ultimately help to lower the cost price of offshore wind energy. It is believed that the maritime sector could profit from AIS data analysis.

Spliethoff is a ship-operating company with around 120 cargo vessels under management.
The vessels of Spliethoff are generating a lot of operational data as they sail around the globe. To make better decisions based on this data, a system is required that takes operational data and translates it to useful information, accessible in the offce and on the ship through online dashboards. Ultimately, better informed decision making should lead to cost minimisation in the areas of fuel consumption and maintenance. In this research a Ship Performance Monitoring System (SPM System) for operational data of Spliethoff's vessels was developed, after which data analysis was performed with the goal to minimise
operational cost of the vessels.
The SPM System was developed using a Rapid Prototyping methodology. By conducting decision support analysis, data requirements analysis and user requirements analysis, Key Performance Indicators (KPIs) for the system were established and coupled to endusers.
In general, one can state that when developing new information systems, end-user involvement is key. If end-users are not involved from the start, interest will be low, resulting in limited added value.
Using the SPM System, data analysis was performed targeting a number of key questions with regards to fuel efficiency, maintenance and ship operation.
Firstly, from the data analysis it can be concluded that for a Spliethoff S-Type vessel the most fuel efficient speed is 14 knots, both in laden and unladen condition. It is recommended to implement this speed for all voyages where the schedule allows it. Accurate implementation of this speed optimum could result in bunker cost savings of up to 10% over a voyage.
Regarding engine efficiency, the specific fuel consumption (SFC) of the main engines of all three vessels is worse than the specifications given by the engine manufacturer. This is according to expectation, given the fact that manufacturers specifications are attained at different conditions. The development of SFC over time showed that the main engine
maintenance schedule currently employed is working effectively, so it is advised to continue in the same manner.
Hull and propeller fouling negatively in uence fuel consumption and speed of a ship. In the data analysis different trends are found regarding fouling. Therefore is is recommended to prolong the measuring period to at least a year before drawing any conclusions. If after a year a fuel consumption increase in the region of 5% is measured, it is advised to increase hull cleaning frequency to once every year. Regardless of any measured fouling increase, it is recommended to inspect the hull of all vessels at least twice a year to increase knowledge of fouling.
A ship's crew is of large in uence on the operational cost of a ship. Consequently,
more intensive collaboration between office and ship on the vessel's operation is suggested, using data in a supporting role. Training crew for correct use of onboard decision support systems and giving feedback on performance will build awareness among crew and increase fuel efficiency.
The SPM System can be improved by installing thrust sensors on the vessels. Implementing a newer correction method for wave added resistance will also enhance the system significantly. Thirdly, it is recommended to reduce dependence on manually entered data to a minimum, due to the inherent inaccuracy of manual input. Finally, matching data quality of all different data sources will increase the precision of the system. In general, the biggest challenge for Spliethoff is to create a company culture where decision making
is data-driven. This will yield the biggest benefits.