AIMET – AI in Metallurgy

About the conference

AIMET brings together leading experts from academia, research institutes, and the metallurgical industry to explore the transformative impact of Artificial Intelligence on Metallurgy.
The conference serves as a platform to exchange knowledge, present breakthroughs, and foster collaboration across the entire metal value chain — from raw materials to finished products.

As AI technologies mature, their integration into metallurgical processes opens new horizons for process control, materials innovation, energy efficiency, and sustainability. AIMET invites contributions that bridge data-driven intelligence with metallurgical expertise, demonstrating real-world progress toward digital and climate-neutral production.

When and where

28–30 September 2026
Van der Valk Hotel Mechelen, Belgium

AIMET2026

Call for Abstracts

AI-Driven Innovation in Metals: Process Optimization, Alloy Development, Quality Assurance, Industrial IoT, Supply Chain Resilience, Sustainability, and Future Technologies

Researchers, engineers, and industry practitioners are invited to submit extended abstracts and full papers presenting novel insights, case studies, and technological advances. Both academic research and industrial applications are highly encouraged.

1. Process & Production Optimization

AI is revolutionizing metallurgical processes by enabling real-time decision-making, energy efficiency, and robust control in dynamic environments. This theme seeks contributions on:

  • Hybrid AI-physics models: Bridging data-driven approaches with first-principles physics to optimize complex processes like smelting and rolling. How can these models enhance accuracy while reducing computational costs?
  • Digital twins and real-time simulations: Case studies on virtual replicas of production lines, their integration with IoT sensors, and their role in predictive process control.
  • Predictive models for energy efficiency and stability: Innovations in AI-driven energy optimization, including adaptive control systems for furnaces, casters, and rolling mills.
  • Handling uncertainty in industrial data: Robust AI frameworks designed for “dirty data”—missing values, noise, and variability—in high-temperature or corrosive environments.
  • Raw material handling: AI applications in scrap quality assessment, pricing algorithms, and supply chain integration to ensure consistent input for downstream processes.

2. Alloy Development & Material Innovation

AI accelerates the development and optimization of high-performance alloys, aligning with circular economy principles. Key areas include:

  • Machine learning for alloy design (incl. metallic coatings): Beyond traditional trial-and-error, how can AI predict mechanical properties, corrosion resistance, or recyclability from compositional data?
  • Microstructure modeling and phase-diagram analysis: AI tools that decode complex phase transformations and grain boundary dynamics to tailor material properties.
  • Accelerated material discovery: Generative AI, Bayesian optimization, or reinforcement learning for identifying novel alloys with minimal experimental iterations.
  • Circular economy integration: Designing alloys with recyclability as a core parameter, using AI to assess lifecycle impacts and secondary material compatibility.

3. Quality Assurance & Safety

Ensuring defect-free products and safe operations is paramount. We invite papers on:

  • Computer vision for defect detection: AI-powered imaging (e.g., hyperspectral, thermal, or X-ray) to identify surface cracks, inclusions, or dimensional deviations in real time.
  • AI in non-destructive testing (NDT): Machine learning models that interpret ultrasonic, eddy-current, or radiographic data for flaw detection in critical components.
  • Predictive maintenance and safety monitoring: Proactive failure prediction in equipment (e.g. girders, cranes, ladles) using vibration analysis, acoustic emissions, or thermal patterns. Corrosion monitoring in view of asset reliability.
  • Industrial case studies: Successful deployments of AI for quality control, highlighting challenges like data labeling, model interpretability, and operator trust.

4. Data Infrastructure & Industrial IoT

The backbone of AI in metallurgy is seamless data integration. Topics of interest:

  • AI integration with business units: Aligning shop-floor AI systems with ERP, MES, or supply chain platforms for end-to-end visibility.
  • Industrial IoT and edge computing: Low-latency AI solutions for sensor networks in harsh environments, balancing cloud and on-premise processing.
  • Data management and standardization: Frameworks for data governance, including ownership, accessibility, and interoperability across legacy and modern systems.
  • Addressing “dirty data”: Strategies for cleaning, augmenting, or synthesizing incomplete datasets to train reliable models.

5. Supply Chain Optimization

This theme reflects the critical role of AI in logistics, procurement, and market responsiveness:

  • AI for procurement and pricing: Dynamic models for scrap quality valuation, vendor selection, or price forecasting amid volatile markets.
  • Logistics and inventory optimization: Predictive analytics for just-in-time delivery, warehouse automation, or transport route planning.
  • Resilience and risk mitigation: AI tools to anticipate disruptions (e.g., geopolitical, climatic) and redesign supply chains for agility.

6. Environmental Compliance & Sustainability

AI is a key enabler for greener metallurgy. Submit work on:

  • Wastewater and emission treatment: AI-driven systems for monitoring and reducing pollutants (e.g., SO₂, arsenic) in effluent streams.
  • Regulatory compliance: Automated reporting tools that leverage AI to ensure adherence to evolving environmental standards.
  • Carbon footprint optimization: AI models that minimize energy use or suggest alternative processes (e.g., hydrogen-based reduction).

7. Future Perspectives & Innovation

Exploring AI’s role in shaping the next decade of metallurgy:

  • Generative AI for R&D: From literature reviews to hypothesis generation, how can GenAI accelerate metallurgical research?
  • AI in training and knowledge transfer: Virtual assistants, AR/VR simulations, or adaptive learning platforms for upskilling workers.
  • Ethical AI and new business models: Beyond cost savings, how can AI drive revenue growth (e.g., custom alloys, as-a-service models) while addressing bias, transparency, and job displacement?
  • Collaborative innovation: Partnerships between academia, startups, and industry giants to democratize AI tools for SMEs.

Call for abstracts

Submission Guidelines

  • Abstracts: up to 500 words, clearly outlining objectives, methods, and key results.
  • Submissions will undergo peer review by the AIMET Scientific Committee.
  • Selected abstracts will be invited to proceed to a full paper or to a poster
  • Accepted contributions will be presented during AIMET 2026 and included in the conference proceedings.

Important Dates

  • Abstract submission deadline: 15 February 2026
  • Conference dates: 28–30 September 2026
Submit your abstract here
Submit your abstract here