If you are an aluminium smelter dealing with unpredictable electrolysis cell failures — this project developed a predictive AI platform that predicts the likelihood of failure within different timeframes. This allows for better maintenance and reduces downtime in a €255BN/y market.
AI-Powered Real-Time Chemical Analysis for Molten Metal Production
Imagine being able to taste a soup while it's boiling to know exactly when to add salt, but for liquid metal. Instead of taking a sample to a lab and waiting, a laser instantly checks the metal's ingredients. An AI then tells the operator exactly how to adjust the process to avoid mistakes and save energy.
What needed solving
Metals manufacturers lack real-time visibility into the chemical composition of molten metals, leading to inefficient process control, higher carbon footprints, and unexpected equipment failure.
What was built
A combined solution featuring LP-LIBS™ sensing hardware and a predictive AI cloud platform for real-time monitoring and process optimization.
Who needs this
Who can put this to work
If you are a steel mill dealing with inefficient alloying processes — this project developed a real-time sensing and cloud platform that monitors chemical composition. This enables process automation and efficiency gains in a €950BN/y market.
If you are a metal processor dealing with high carbon footprints and waste — this project developed LP-LIBS™ sensing technology that provides real-time data for decision making. This helps maximize efficiency and reduce the environmental impact of production.
Quick answers
What is the cost or pricing model for this system?
Based on available project data, specific pricing or cost details are not provided.
Can this be deployed at an industrial scale?
Yes, the system uses edge devices at customer sites to aggregate plant data and a cloud-agnostic platform to handle real-time data flow for large-scale metals manufacturing.
What is the IP and licensing status?
The system utilizes DTE's proprietary LP-LIBS™ sensing technology and the project included the definition of an IP strategy.
How is the system integrated into existing plants?
Integration is achieved via edge devices hosted on-site that forward data to a cloud platform, with the option for on-premises setup for specific customer requests.
What is the implementation timeline?
The project ran from 2022-10-01 to 2024-09-30, during which the architecture was defined and the first version of the platform was built.
Who built it
The project is led by a single SME, DTE EHF, based in Iceland. With a 100% industry ratio and no university or research institute partners, the project is purely commercially driven, focusing on rapid development and direct customer validation.
Contact DTE EHF regarding LP-LIBS™ technology
Talk to the team behind this work.
Contact us to explore licensing or integration of real-time metal analysis AI.