Imagine having a perfect digital mirror of your battery factory that tells you exactly why a batch failed and how to fix it. Instead of guessing, it uses a mix of physics and smart AI to predict outcomes and guide workers in real-time. It's like a GPS for manufacturing that ensures every battery is built to the same high standard, regardless of the chemistry used.
Battery manufacturers struggle with 'black box' AI and complex process data that is hard for humans to interpret. This leads to inefficiencies in design and a lack of trust in automated decision-making during production.
An interpretable industrial decision support system (IIDSS) and a cross-chemistry data space. These tools combine physics-based modeling with explainable AI to monitor and optimize battery assembly.
If you are a redox flow battery manufacturer dealing with inconsistent cell performance — this project developed a digital twin that integrates real-time sensory data to allow live interventions. This ensures higher product quality and process efficiency during assembly.
If you are a coin cell producer dealing with high scrap rates in Li-ion or Na-ion lines — this project developed an interpretable industrial decision support system. It uses multicriteria optimization to help human operators make better design and process choices.
If you are a software provider dealing with 'black box' AI that operators don't trust — this project developed explainable-AI-ready (XAIR) models. These models combine data-driven methods with formal reasoning to guarantee reliable and transparent behavior.
Based on available project data, there is no specific pricing for the end-product; however, the project is supported by an EU contribution of EUR 5,106,384.
Yes, the digital twin is being validated in pilot production lines for both coin cells and redox flow batteries to prove its transferability.
Based on available project data, specific licensing terms are not listed, but the project follows FAIR data principles and is connected to the Knowledge Graph Alliance for industry uptake.
It integrates by acquiring and analysing sensory and operando data in real time within an Industry 5.0 environment.
The project period runs from 2024-01-01 to 2027-06-30, indicating the development and validation phase is ongoing.
The consortium is heavily weighted toward research and academia, with 7 universities and 8 research organizations. However, there is a strategic industrial presence of 3 companies (including 3 SMEs), representing a 17% industry ratio. This structure suggests the project is focused on translating high-level scientific modeling into practical pilot-line applications across 10 different countries.
Contact NORGES MILJO-OG BIOVITENSKAPELIGE UNIVERSITET
Contact us to explore licensing opportunities for the BatCAT digital twin models.
