From a ship designed to tell you what maintenance it needs and when, to an intelligent journey planner for global freight transportation. The three universities of Zuid-Holland are buzzing with AI research in the field of ports and maritime. Three researchers explain. Part two of a series of five themes on which the three universities are conducting research related to AI.
“The big challenges facing ports are accessibility, sustainability and finding the right employees,” says Rudy Negenborn, professor of multi-machine operations and logistics at Delft. “In a busy port, you need to optimize your planning to avoid delays, congestion and unnecessary emissions. It doesn’t just require solutions to technical challenges: a solution can only be implemented if an organization wants it and has the appropriate infrastructure for it.
“We can develop technology that allows ships to enter a port safely and independently, so that an operator only has to intervene in an emergency. But what would that mean for operator stress levels? How many ships can they monitor at a time? And would ships interact and exchange information with each other?
All the necessary expertise
Negenborn spent around a year and a half intensifying the collaboration with the universities of Leiden and Rotterdam. He can see how much expertise from all three universities is needed when working with many different parties on solutions related to smart maintenance, smart transportation and smart logistics. “In black and white terms, Delft’s main strength is technology, Rotterdam’s is its economy and business models, and Leiden’s is its social and legal aspects.
Black and white indeed, because Thomas Bäck from Leiden does not fit this stereotype. He heads the Natural Computing Research Group at the Leiden Institute of Advanced Computer Science (LIACS), which works on algorithms that apply the principles of evolution and nature. A key question in his work is how an algorithm can weigh different aspects, such as costs and sustainability, before suggesting the best option. “It could mean the best way to design ships, but learning algorithms can also predict the best time for maintenance. This is something that Delft is also looking for.
How can we tell the difference
Bäck was greatly inspired by a discussion group with ten participants from the three universities which focused on AI research in the field of ports and the maritime sector. “We discussed how we could really make a difference, while taking into consideration the United Nations Sustainable Development Goals, for example. We have to think about the social aspects: the regulation of AI and how it can be better explained to gain people’s trust. Rotterdam’s economic and logistical prospects were also new to me. It was great.’
Greater collaboration at Zuid-Holland will create opportunities, says Rob Zuidwijk of Erasmus University Rotterdam. As a professor of global supply chains and ports, he sees the chances of improving the efficiency of freight transport and ports. “I want to bring together the public, the city, researchers and nonprofits in society.
What does standalone shipping mean
If it were up to Zuidwijk, he would invite all of the above to the campus to simulate the Port of Rotterdam in a digital twin environment. “ Then they would see what autonomous navigation means and what impact certain behaviors have on employees and the public. This would strengthen the links between public and private actors, both in the port and in the city. The dialogues with, among others, Rudy Negenborn and Mark van Koningsveld from the Delft University of Technology help enormously to get a clear idea of the needs that a digital twin environment must meet in order to launch multidisciplinary research with impact on the ground. ”
Collaboration with business is extremely important if you want to have an impact as a researcher, and it’s something all researchers have a lot of experience with. With the port of Rotterdam of course, and Bäck also works with companies such as Air France-KLM, Tata Steel and the Honda Research Institute in Germany. Negenborn: “If we, three universities, can evolve, it will be easier to reach the board of directors of large companies, which will mean larger budgets for work. This will make us more decisive.
Below is an example of the work of each of the three professors: research related to AI in ports and the maritime.
Delft University of Technology – Rudy Negenborn
Proactive vessel maintenance: algorithm prevents damage and costs
“You have been buying a ship for 30 years. During that time, things break down, at unfortunate times. Being at anchor can cost tens of thousands of euros per day, and if a part is not in stock… We are working with Leiden on health surveillance systems in the Autonomous Navigation Research Laboratory (RAS). These types of systems closely track how a vessel responds to rudder, engine speed, etc.
“The algorithm collects and interprets this data. A sudden reduction in rudder response can be caused by sticks around the propeller. If the system suggests this diagnosis, a zigzag maneuver may resolve the problem. The system can automatically decide to temporarily reduce speed, for example to avoid engine failure.
“In this project, in Delft, we are working on ship dynamics: how to design a ship. Leiden deals with the side of data science: how and what data can lead to system diagnosis and advice. A user-friendly dashboard also comes from Leiden. We are working together on the algorithms.
Erasmus University Rotterdam – Rob Zuidwijk
A smart trip planner for freight transportation
“Fresh cargo should not be left on standby because the cooling system is on. If the trucks are driven in convoy, they can save up to 10% fuel. If they coordinate their trips, they can save even more. Inland navigation could be much more economical, but the best use is not always made of it. It requires more logistical coordination than the transport of goods by truck. What we need is a route planner for freight transport in Europe.
‘Where the 9292 [a journey planner for public transport] brings together all the individual schedules, our system must be smart. It has to harmonize a huge amount of data, recognize patterns, and then suggest and organize the cheapest, cleanest, and fastest route. If something is wrong, like the recent blockage of the Suez Canal, the system must react.
“Together with Professor of Econometrics and Computer Science Rommert Dekker and Professor of Freight Transport and Logistics Lorant Tavasszy from Delft, I am now thinking of such systems. We are in talks with parts of the Port of Rotterdam. If the port provides data that shows what’s going on in the port and in the European hinterland, we can get an algorithm to learn from that. In the future, all parties in the future will be able to organize the optimal transport on a virtual card and determine whether the contents of container X will arrive fresh.
Leiden University – Roy de Winter, doctoral student under the supervision of Thomas Bäck
Algorithm shows: the best design and clean your ship on time
“I am looking for efficient optimization algorithms at C-Job Naval Architects and the University of Leiden. An important question is how algorithms can compare the lowest production and running costs with the best quality and best result. If, for example, you make a long, thin ship, it will be more efficient, but you need more steel to build it than to build a shorter, wider one. And more durable materials and cleaner fuels are becoming increasingly important in the ship design process.
“We also analyze the operational data of the vessels. We recently made a unique discovery. A client wanted to see the influence of the wind on the power required and provided us with datasets for us to find out. We checked data from two identical vessels and found that one was over 30% more economical than the other. The first had just been cleaned, while the second had a heavy layer of algae and barnacles. This turned out to be a major cause of the difference. Cleaning can be a complete operation, but it is well worth it! Nowadays, there are methods to do this cleaning with water, with a kind of robotic lawnmower for example.
Five themes filled with AI research in Zuid-Holland
This article is part of a series in which we show how teaching and research using or in artificial intelligence plays a role at Erasmus University Rotterdam, Leiden University and the University of Technology from Delft. The articles will cover the five themes on which universities are working together and alone:
• Port and maritime
• Energy and sustainability
• Life sciences and health
• Smart industry
Text: Rianne Lindhout