CLASCO Innovations
CLASCO AI Monitoring and Decision Support System
The CLASCO AI Monitoring and Decision Support System is designed to support the intelligent operation of the CLASCO machine by analysing process data collected during laser polishing and DLIP surface processing. Developed by Mousavi A., Danishvar M., Rostohar D., Danishvar S., and Gavrilovic M., the system acts as a digital assistant for the machine. It interprets sensor and process data, identifies relevant process patterns, and supports informed decision-making for improved surface quality, process stability, and greener production.
-
Intelligent Process Monitoring
- The system collects and prepares data from laser processing experiments and connects it with sensor and machine data generated during laser polishing and DLIP operations. This enables faster interpretation of complex process behaviour and helps identify stable and unstable processing conditions.
-
Surface Quality Prediction
- By analysing relationships between laser parameters, material responses, sensor signals, and surface quality measurements, the AI framework supports the prediction of process outcomes and quality indicators such as roughness. This helps users understand how process conditions may affect the final surface.
-
Process Optimisation Support
- The AI system supports the identification of suitable processing windows for better surface quality, fewer defects, and more efficient production. It combines data-driven analysis with physics-based and AI-driven inferential modelling, simulation, and digital twin approaches to compare different processing conditions against ideal target conditions.
-
Towards Autonomous Machine Control
- The system is currently used for monitoring, analysis, and decision support rather than as a fully autonomous control system. Its innovative contribution lies in linking process data, sensor information, and surface quality measurements into one intelligent framework, providing the foundation for future autonomous machine control and high-frequency closed-loop process optimisation.
Funding
