The development of machine learning will also drive many business model modifications in the manufacturer’s standard operating procedures. That’s especially true in the organisational makeup of the company.
The computer network (IT hallowed ground) will be co-located with the operational sensors on the production machinery so that data can be collected and sent to the data warehouse as training data for machine learning purposes. There will be a need to tear down the wall of silence, separating the two groups internally and allow for collaboration and cooperation.
The floor operators and technicians will be significantly impacted if the network is not reliable or for some reason gets hacked via a denial of service attack, which will bring production to a stop. The OT sensors and devices will be affected as much as the IT network and computers. Industry Week confirms these issues.
Smart manufacturing digital design and innovation/digital twin development
The ultimate objective of artificial intelligence and machine learning is to enable the development of a digital twin of the production floor. This would take place as an effort under a model-based systems engineering process (MBSE) using the machine learning algorithms and knowledge gained as a foundation. The digital twin would serve as a platform for running what-if scenarios to learn what we don’t know today. It can also serve as an end-to-end model to be used in designing higher reliability parts and adjusting the interactions between production line machines to improve performance. The possibilities are endless.
Connecting all these pieces, industrial cyber-physical systems are the primary enabling technology, which refers to an emerging data-driven paradigm focused on the creation of manufacturing intelligence using real-time pervasive networks and operational data streams. These cyber-physical systems enable objects and processes residing in the physical world (e.g., manufacturing facility), to be tightly coupled and evaluated by advanced predictive analytics (e.g., machine learning models) and simulation models in the cyber world, to realise self-configuring operations. Thus, this research presents an industrial cyber-physical system based on the emerging fog computing paradigm, which can embed production-ready PMML-encoded machine learning models in factory operations, and adhere to Industry 4.0 design concerns about decentralisation, security, privacy, and reliability. (Peter, O'Donovan, Gallagher, Bruton, & O'Sullivan, 2018)
If we dig deeper underneath the big-ticket items, there are thousands of other impacts that machine learning will have on smart manufacture ring and the industrial processes that make it all work, such as in semiconductor manufacturing, quality control and across the supply chain.