AI-based Condition Monitoring of Valves for AOD Converters (AICoMoVA)
Important results from the project
The project´s objective was met. A system for detecting abnormal valve behavior in real time has been developed and demonstrated in two independent industrial environments. Data collection infrastructure has been established and AI algorithms have been tested in factory trials together with process experts. The project has also led to new proposals for further development and has created a foundation for future applications.
Expected long term effects
The project is expected to contribute to more efficient valve monitoring, increased operational reliability and better decision support for operators. It creates the conditions for predictive maintenance through data-driven monitoring and analysis. The project also strengthens the collaboration between industry and academia and contributes to increased understanding and maturity of AI in the industry, which can facilitate future implementations and innovation.
Approach and implementation
The project was implemented in five work packages covering digital infrastructure, process knowledge, AI development and two plant trials. Data was connected from control systems and used to develop and test AI algorithms for valve monitoring. The work was carried out in close collaboration between academia and industry, with continuous feedback between the parties and iterative development of the solutions.
The text has been written by the project team. The content is copied from the funding agency’s website and has not been reviewed by the Program Office.