Computational Intelligence for metals science and technology

In the last decade, metallurgical industry is undergoing an unstoppable digitalization process, where information sources are being multiplied by the spread of sensing and monitoring devices, equipment and solutions. As a consequence, large volumes of data are harvested, which conveys relevant and sometimes sensitive information and hide part of the know-how of the companies. They are increasingly perceived as a “treasure” to be suitably handled, protected and exploited to preserve and increase the companies’ competitiveness.
Such data availability paves the way to a more intensive application of computational intelligence in this field, for a wide variety of applications (e.g. related to improved product quality, costs and environmental impact reduction via efficient and cost-effective process management). The interest and expectations of this industrial sector toward AI applications is ever increasing.
On the other hand, a relevant background knowledge in material science is available, which needs to be taken into account and exploited by the researchers and who are willing to implement AI-based solutions, thus hybrid solutions, such as those investigated in the field of the so-called physics-guided AI are very likely to show a huge potential for deployment in this sector.

This special session aims at collecting contributions concerning the application and deployment of computational intelligence in the metal sector (e.g. iron and steel, aluminum, non-ferrous metals and alloys, precious metals), by intensifying the dialogue among technology providers in the field of AI and end-users from the metal and alloy industry to explore further opportunities for cooperation.


TOPICS

This session seeks original manuscripts that investigate research trends, relevant issues and challenges related to the implementation of AI-based solutions within metallurgical industry as well as relevant applications and industrial case studies related (but not limited) to the following topics:

  • AI-enhanced fundamental metal science;
  • AI-based and hybrid material characterization in metallurgy;
  • Data driven modelling and forecasting of product properties;
  • Physics-informed ML and physics-guided AI for the metallurgical sector.
  • AI-based data management and handling to improve knowledge on material properties evolution during production and manufacturing;
  • Intelligent data management and exploitation to improve production efficiency and product quality;
  • Intelligent process monitoring and control strategies and tools;
  • Artificial Intelligence and Machine learning-based approaches targeting improvement of sustainability of the production processes;
  • Multi-Agent Systems deployment in the metallurgical sector;
  • Quantum computing applications for the metallurgical sector;
  • AI-supported production planning and scheduling systems;
  • Intelligent decision support systems for the metallurgical sector
  • IoT and seamless integration of workers into production processes
  • Impact of intelligent systems on the workers of the steel sector

The section is transversal with respect to the main themes of WCCI (Ieee World Confress on Computational Intelligence), as it deals with the application of most of the technologies and approaches treated in WCCI to a specific industrial sector. However, the section also aims at analyzing the peculiar features of the metallurgical sector with respect to the application and implementation, by identifying main open issues and existing barriers to the wide deployment of computational intelligence in such sector, by possibly identifying ways, means, approaches and exemplar cases to overcome such barriers.


Important Dates

  • Paper submission: January 31, 2022 (11:59 PM AoE)
  • Notification of acceptance: April 26, 2022
  • Final paper submission: May 23, 2022

Organizers

Valentina Colla valentina.colla@santannapisa.it

Marco Vannucci marco.vannucci@santannapisa.it


More details on the conference website: https://wcci2022.org/