Real-time decision support system for dynamic optimization in multi-product process manufacturing

The implementation of adaptive optimization in multi-product process manufacturing is a crucial strategy for the reduction of unplanned downtime and the enhancement of overall productivity. Nevertheless, the availability of real-time decision support tools for dynamic adjustments in large-scale industries is currently limited. In response to this challenge, we propose a novel model that processes data collected from extensive manufacturing operations. By leveraging Explainable Artificial Intelligence, we developed a real-time decision support system designed to dynamically adjust process parameters following varying input variables. The proposed model achieved a capture rate of 62% of the minority of products that cause micro-stoppages due to non-compliance with specifications. This approach provides a robust framework for adaptive optimization in complex and large-scale manufacturing environments, enhancing productivity and resilience against unplanned disruptions.

Mots clés

• manufacturing
• real-time systems
• optimization
• machine learning
• manufacturing processes
• principal component analysis
• feature extraction
• faces
• aptation models
• semiconductor device modeling