Revolutionierung technischer Herausforderungen mit KI: Ein neuer Ansatz zur Optimierung

Complex design challenges in engineering often come down to navigating a high number of variables and limited opportunities for testing. The stakes are high, especially when we’re talking about fine-tuning a power grid or developing safer vehicles. Each evaluation can be costly and the range of potential variables mind-boggling. Just think about car safety design – thousands of elements are in play and the tiniest decision can dramatically alter how a vehicle behaves during a collision. Unfortunately, traditional optimization tools often falter under the weight of this complexity.

The Gamechanger: MIT’s Fresh Take

That’s where a team of researchers from MIT steps in. They’ve come up with a fresh approach that reshapes how we use Bayesian optimization to address problems with hundreds of variables. In tests on engineering benchmarks, including power-system optimization, their method found top solutions 10 to 100 times speedier than traditional techniques.

So, what’s the secret? It’s all about a foundation model trained on tabular data. This model autonomously identifies the most impactful variables to improve performance and iteratively refines the solution. Being trained on a broad range of data, foundation models have the impressive ability to adapt to various applications.

Effizienzsteigerung

The crux of their tabular foundation model is that it doesn’t need constant retraining, which significantly ramp up the process’s efficiency. For more intricate problems, this method brings even higher speed, making it invaluable in sectors like materials development and drug discovery. To quote the leading author of the project, Rosen Yu, a graduate student in computational science and engineering, “Modern AI and machine learning models can change the way engineers and scientists create complex systems. We conceived one algorithm that not only solves high-dimensional problems but is also reusable, sidestepping the need to start everything from scratch”.[Quelle]

Wenn es um vielschichtige Probleme und umfangreiche Bewertungsmethoden geht, verwenden Wissenschaftler in der Regel die Bayes'sche Optimierung. Bei dieser Methode wird iterativ die beste Lösung gefunden, indem ein Ersatzmodell erstellt wird, das die Suche leitet. Allerdings ist es schwierig, dieses Modell nach jeder Iteration neu zu trainieren, vor allem, wenn es sich um einen großen Lösungsraum handelt. Das Team ging diese Herausforderung an, indem es ein generatives KI-System, ein tabellarisches Basismodell, als Ersatzmodell innerhalb des Bayes'schen Optimierungsalgorithmus einsetzte.

Ein neues Zeitalter der Optimierung

Yu vergleicht die Verwendung eines tabellarischen Basismodells mit einem ChatGPT für Tabellenkalkulationen, da seine Eingabe und Ausgabe aus tabellarischen Daten besteht, die im technischen Bereich häufiger vorkommen und verwendet werden als Sprache. Wie große Sprachmodelle wie ChatGPT, Claude und Gemini wurde es mit großen Mengen von Tabellendaten trainiert und kann daher verschiedene Vorhersageprobleme bewältigen. Einer seiner größten Vorteile ist, dass es ohne erneutes Training verwendet werden kann.

Die Forscher haben das tabellarische Gründungsmodell so verfeinert, dass es sich auf die Merkmale des Bemessungsraums konzentriert, die den größten Einfluss auf die Lösung haben. Dies führt zu größerer Präzision und Effizienz, da das Modell die wichtigsten Merkmale auswählen kann, auf die es sich konzentrieren soll. Ein Auto kann zum Beispiel 300 Designkriterien haben, aber nicht alle davon führen zum besten Design. Der Algorithmus kommt schnell zum Kern der einflussreichsten Merkmale und spart so Zeit für weniger einflussreiche Merkmale.

The team had to clear a few hurdles, such as finding the best tabular foundation model for the task. Also, they had to work out how to connect it with a Bayesian optimization algorithm to identify key design features. Once they established the framework, their method consistently outperformed five current state-of-the-art optimization algorithms, finding the best solutions 10 to 100 times quicker. However, it didn’t outdo all benchmarks, possibly due to gaps in the model’s training data.

Don’t worry, the MIT team isn’t resting on their laurels. They’re looking to enhance their tabular foundation models even further and apply their method to even more complex issues, such as naval ship design. As Ahmed, another member of the team, puts it: “At a higher level, this work points to a broader shift: using foundation models not just for perception or language, but as algorithmic engines inside scientific and engineering tools, allowing classical methods like Bayesian optimization to scale to regimes that were previously impractical.”

One academic not involved in the research, Professor Wei Chen, praises the MIT’s approach as a “creative and promising way to reduce the heavy data requirements of simulation-based design. Overall, this work is a powerful step toward making advanced design optimization more accessible and easier to apply in real-world settings.”

If this still hasn’t quenched your thirst for all things AI and engineering, you can read more on the topic straight from the source at the MIT-Nachrichten website. Exciting times are ahead in the engineering world, and we’re here to keep you informed!