Engineers at MIT have created an algorithm that presents the types of extreme events that are likely to take place in a complex system, such as an ocean environment, where waves of various magnitudes, lengths, and heights can create pressure on a ship or offshore platform. The researchers can simulate the forces that extreme events can generate on a structure.
Themistoklis Sapsis, associate professor of mechanical and ocean engineering at MIT and Mustafa Mohamad, will publish their results this week in the Proceedings of the National Academy of Sciences.
[smlsubform prepend=”GET THE SAFETY4SEA IN YOUR INBOX!” showname=false emailtxt=”” emailholder=”Enter your email address” showsubmit=true submittxt=”Submit” jsthanks=false thankyou=”Thank you for subscribing to our mailing list”]
The new simulations model not just the wave of interest but also its interaction with the structure. They simulating the entire wave field, estimating how a structure might be rocked, and what forces may cause damage.
Engineers can also use these simulators to run just a few scenarios, choosing to simulate random wave types that they think might cause maximum damage. If a structural design survives these extreme, randomly generated waves, engineers assume the design will stand up against similar extreme events in the ocean.
This machine-learning algorithm identifies the most important or most informative wave to run through such a simulation. It is based on the idea that each wave has a certain probability of contributing to an extreme event on the structure.
Through the algorithm, researchers can feed in various types of waves and their physical properties, along with their known effects on a theoretical offshore platform. From the known waves that the researchers add into the algorithm, it can learn and make a rough estimate of how the platform will behave in response to any unknown wave.
The algorithm also identifies a particular wave that maximally reduces the error of the probability for extreme events. This wave has a high probability of happening and leads to an extreme event. In this way the algorithm goes beyond a statistical approach and considers the dynamical behavior of the system under consideration.
The researchers tested the algorithm on a theoretical scenario involving a simplified offshore platform subject to incoming waves. The team added four typical waves into the algorithm, from which it identified the dimensions of a new wave that has a high probability of happening, and it maximally reduces the error for the probability of an extreme event.
The team then added this wave into a new simulation to model the response of an offshore platform. They fed the results of this first simulation back into their algorithm to identify the next best wave to simulate, and repeated the entire process.
The results showed that team’s method presents the waves that are most certain to be involved in an extreme event, and provides designers with more informed scenarios to simulate.
