OPENZDM | Open Platform for Realising Zero Defects in Cyber-Physical Manufacturing

In the demonstrator of SONAE Arauco ES, the openZDM digital tools and platform will be used to achieve the following:- improvement of data collection and in-situ monitoring, namely in what concerns time-related annotation 
- improvement of inspection of quality issues through artificial intelligence and digital-twin technology.
- further advances in predictive quality based on data-driven and model-driven approaches for defect prediction and quality assessment.
- improvement in manufacturing decision making for ZDM strategies and process adaptation. This will also include recommendation models for new products, an explainable AI approach for a better understanding of Machine Learning decisions and a graphical user interface through UX/UI strategies.
 

thus effectively support productivity through the following aspects:

1. Improved decision-making at the plant level to reduce defects towards a zero defects paradigm

2. Improved product development (faster and with less waste generated)

3. Improved evaluation of machinery components 

The vision of the future process with the contribution of the openZDM solutions targets an improved decision-making at the plant level to reduce defects towards a zero defects paradigm, that will facilitate defect prediction and recommendation of production recipes to adjust machine parameters according to predicted defects. In turn, improved products can be developed using the data-driven knowledge acquired, resulting in less wasted material. Towards this direction, the openZDM project performed an LCA at the beginning ot he project to compare it with the final one and also it supports integration through its platform to an LCA tool for on-demand LCA. 

OPENZDM solutions for AI quality assessment and decision support aim for data driven defect prediction and estimation of machine components degradation through drifts in data distribution. The main goal is to predict defects such as broken paper, dust or glued paper so that changes in machinery/parameters can be performed and the defect avoided and also to estimate degradation based on slight and smooth changes in the process start occurring due to component wear-out / degradation and, if data is representative enough, it may be different data distributions in time.

OPENZDM is expected to contribute to the SONAE Arauco use case in the aspects of proactive quality control towards zero-defect manufacturing through the digital twin enabled machine learning approaches for data analytics and quality assessment.