The majority of Norwegian industries are still a long way from being able to adopt AI and machine learning methods in their daily operations. One of the main barriers is the lack of robustness and trustworthiness of existing methods, particularly when applied to physical processes. PhysML will contribute to solving this challenge by combining machine learning models with the geometric properties of mathematical models in a hybrid analytics framework that alleviates the weaknesses of the individual approaches by leveraging their complementary strengths.
Industrial data often originates from sensors or manual measurements that can suffer from low quality or quantity, hindering pure data-driven approaches. However, industrial data frequently describes physical processes which are governed by the laws of nature and can thus be modelled. When such models exist, they are based on first principles, making them trustworthy but lacking the flexibility of data-driven approaches. PhysML will work towards two goals: i) Use machine learning to gain physical knowledge about the systems, and ii) use physical knowledge to obtain machine learning models that are open, trustable, robust, and flexible. A fundamental innovation in our approach is to utilize the assumed underlying structures of the system, such as symmetry or preservation of energy, and thus build on the established field called numerical geometric integration, which is the study of how to incorporate such structures into mathematical models. The national and international academic partners (NTNU, Brown University) are among the world’s foremost experts in numerical geometric integration and physics-informed machine learning, respectively. Partnership with Elkem and Veas will ensure industrial relevance by providing use cases for development and testing of algorithms within the areas of predictive maintenance, control theory and process optimization.
In the first year of the project, new methods have been developed and tested on simulated test problems. The results have been shared through scientific papers, open-source code, and presentations at workshops and conferences, in Norway and abroad. The next planned step is to extend these methods further and apply them methods to real-world data and the use cases of the industry partners.
A workshop with participants from the US, Japan and all over Europe was organized in Oslo in May 2024. The participants were invited speakers from academia, PhD students and researchers who registered to attend and present their work, and industrial companies who presented both specific use cases and the challenges they face. At the workshop and in the months that followed, new collaborations were established between attendants, from Norway and abroad.
The majority of Norwegian industries are still a long way from being able to adopt AI and machine learning methods in their daily operations. One of the main barriers is the lack of robustness and trustworthiness of existing methods, particularly when applied to physical processes. PhysML will contribute to solving this challenge by combining machine learning models with the geometric properties of mathematical models in a hybrid analytics framework that alleviates the weaknesses of both individual approaches by leveraging their complementary strengths.
Industrial data often originates from sensors or manual measurements that can suffer from low quality or quantity, hindering pure data-driven approaches. However, industrial data frequently describes physical processes which are governed by the laws of nature and can thus be modelled. When such models exist, they are based on first principles, making them trustworthy but lacking the flexibility of data-driven approaches. PhysML will work towards two goals: i) Use machine learning to gain physical knowledge about the systems, and ii) use physical knowledge to obtain machine learning models that are open, trustable, robust, and flexible. A fundamental innovation in our approach is to utilize the assumed underlying structures of the system, such as symmetry or preservation of energy, and thus build on the established field called numerical geometric integration, which is the study of how to incorporate such structures in mathematical models. The national and international academic partners are among the world’s foremost experts in numerical geometric integration and physics-informed machine learning, respectively. Partnership with Elkem and Veas will ensure industrial relevance by providing use cases for development and testing of algorithms within the areas of predictive maintenance, control and process optimization.