Need to advance on how manufacturing efficiency is measured.

Invovle more advanced metrics such as flexibility or eventually resilience.

How to combine measurements at differnt factory levels, from proess to workplace and eventually to system level.

A key enabler of factory flexibiltiy involves intralogisitcs.

While resilienec has been discussed and given proper attention, this aspect is condidered mainly at a produciotn network level. However, resilience needs to be taken into account at a factory level, therefore factoy intralogisitcs are a key component.

In addition, material handling operations would be linked to intra-logistics, since this is a key parameter to enhance factory resilience.

Possibly links can be made to projetcs on flexible material handling (2022 call)

not sure about it, maybe we need to have some examples of critical components.

Probably it can be linked to development of advanced, modular mechatronics which can be used plug-n-produce in modern manufacturign systems.

Also aspects of digital engineerign and virtual commissioning can be better achieved by itnegrating such advanced components.

Overall not sure if the topic shuold be focused on the "criticality" dimension or on the “modularity” and “intelligence” of components.

Reliability of machinery is a key enabler of resilience. 

This area needs to advance beyond conventional dashboard that have been developed in past projects that limit their capabilities in providign information in visual form.

It is deemed important to advance in modeling cabailities and integratign deep learning models to enable more precise machinery condition estimation.

Moreover, such predictive models shuold be associated to the actual quality of the produceed parts, ensuring that OEE is also corelated to product qualtiy and reducign defects.

The approach should allow combining physics and deep learning methods.

In recent years, we have seen great advances in human/machine and human/robot collaboration.

The emergence of generative AI and relevant technology appears as a key enabler for achieving breakthoughs in this area.

NLP enabled by large Language Models and Large Multi-Modal Models can help further advacne the way humans interact with machines, robots and even other people or AI agents in the factory.

The focus should be more on modeling the manufacturign environment and less on the ICT framework.

Need to advance on how manufacturing efficiency is measured.

Invovle more advanced metrics such as flexibility or eventually resilience.

How to combine measurements at differnt factory levels, from proess to workplace and eventually to system level.

A key enabler of factory flexibiltiy involves intralogisitcs.

While resilienec has been discussed and given proper attention, this aspect is condidered mainly at a produciotn network level. However, resilience needs to be taken into account at a factory level, therefore factoy intralogisitcs are a key component.

In addition, material handling operations would be linked to intra-logistics, since this is a key parameter to enhance factory resilience.

Possibly links can be made to projetcs on flexible material handling (2022 call)

not sure about it, maybe we need to have some examples of critical components.

Probably it can be linked to development of advanced, modular mechatronics which can be used plug-n-produce in modern manufacturign systems.

Also aspects of digital engineerign and virtual commissioning can be better achieved by itnegrating such advanced components.

Overall not sure if the topic shuold be focused on the "criticality" dimension or on the “modularity” and “intelligence” of components.

Reliability of machinery is a key enabler of resilience. 

This area needs to advance beyond conventional dashboard that have been developed in past projects that limit their capabilities in providign information in visual form.

It is deemed important to advance in modeling cabailities and integratign deep learning models to enable more precise machinery condition estimation.

Moreover, such predictive models shuold be associated to the actual quality of the produceed parts, ensuring that OEE is also corelated to product qualtiy and reducign defects.

The approach should allow combining physics and deep learning methods.

In recent years, we have seen great advances in human/machine and human/robot collaboration.

The emergence of generative AI and relevant technology appears as a key enabler for achieving breakthoughs in this area.

NLP enabled by large Language Models and Large Multi-Modal Models can help further advacne the way humans interact with machines, robots and even other people or AI agents in the factory.

The focus should be more on modeling the manufacturign environment and less on the ICT framework.