Several organisations are familiar with making use of digital twin modelling to improve operations. This digitised model typically enables firms to map the physical characteristics of a production environment as well as its processes. But, this mapping process has limitations because it only includes data from machines and not from humans, which are crucial too
Alongside this, human employees will continue to play an important role in the Fourth Industrial Revolution, also known as Industry 4.0. The challenge, however, lies in combining data from machines with that of the people working in a factory and evaluating it in real-time. Which is precisely where the concept of the human digital twin comes in. It takes this concept one step further and improves it. But, how exactly, does it achieve this?
Artificial intelligence (AI) and digital twins are terms that are often associated with Industry 4.0. One controversial view is that within the smart factory model, robots will take over the role of humans to execute work and reduce failures and errors. But, this idea of full automation is neither possible today nor in the near future — because it won’t work without humans.
Even technology pioneers such as Amazon's Scott Anderson see it that way. In his view, technology is still at least 10 years away from being able to fully automate a single order picked by a worker in the warehouse.
The effects of the COVID-19 crisis, in particular, amplify this sentiment too and show that humans are indispensable. Logistics and supply chains need the intervention of human dexterity, spontaneity and the ability to work directly with others. These skills distinguish humans from robots.
Evidence of this is provided, for example, by US retail giant Walmart; which ended its collaboration with a robotics company during the pandemic, after it became apparent that Walmart employees could come up with similar results.
Author Axel Schmidt, Senior Communications Manager, ProGlove
In contrast, technologies like AI, can, of course, support the role of humans and free up time for people to concentrate on more important tasks. But, in order for organisations and employees to benefit from the freedoms that AI can bring, without complications, certain preconditions must be put in place to enable the human-machine relationship to thrive. This will enable greater collaboration between people and machines and protect the workforce.
When improving productivity, the main goal is to support people with technology that lets them concentrate better on core tasks. For this to succeed, and for humans to be integrated effectively into Industry 4.0, they need the appropriate equipment. Wearables, such as smart glove barcode scanners from ProGlove, connect humans to the Internet of Things (IoT) and provide the interface for human-machine collaboration.
However, it is not only the connection of the wearables to various systems that is crucial, it’s also the use of a corresponding data management platform that combines the information from machines and employees, which can then be appropriately evaluated and modelled to create a human digital twin.
Specifically, within production and logistics scenarios, the human digital twin models the human worker in its environment. And, not just a single employee’s data, but rather a collection of employee data from several people across the team. For the human digital twin to become a reality and form a true digital counterpart of a worker in a warehouse, for example, firms need a solution that puts people at the centre.
The ProGlove Insight analytics platform enables this and takes advantage of the fact that users wear a scanner on their bodies. This allows time-motion studies to be done; the information captured and provided here is valuable. Tracking walking times in the warehouse, for example, which accounts for 30–50% of the effort involved in picking, provides insight into an important lever for optimisation, which can save unnecessary walking.
More so because the data can be visualised in heatmaps. The bottom line is that Insight collects data, contextualises it and derives executable recommendations for action from the bottom up. For example, if too many workers are deployed at one location while, at the same time, staff are missing elsewhere.
Such data also provides concrete information about hotspots, identifies obstacles and allows workstations to be compared with one another.
What’s more, human digital twins can provide insight to organisations about the quality of scanned barcodes. For instance, often items arrive from a supplier into a warehouse and cause problems when scanned. This problematic information can now be passed on to the supplier, backed up by data, so that the supplier can take remedial action.
When this happens, ProGlove Insight offers an immediate solution to this issue by providing image capture functionality that improves this process. These images can be stored in a structured manner in the cloud, equivalent to a back-up. Ultimately, the solution aims to initially capture and solve everyday challenges that occur during scanning and picking.
Further, data from the Insight platform complements and extends Warehouse Management System (WMS) or Enterprise Resource Management System (ERP) data. This is because WMS and ERP lack the capabilities to capture the time-motion studies that Insight provides. But, only by combining this human and machine data in real-time, through the appropriate analytics software, is it possible to offer a true operational picture of the store floor.
Using wearable technology and appropriate supporting process analytics platforms can help to deliver human digital twin-based insights. As this data comes from the bottom up, at the operational level within a warehouse, it has the potential to provide management with powerful information about how to improve operations, productivity and health and safety.
Further, in a world in which there is talk about machines replacing humans, human digital twins act as advocates for employees, showing how valuable people are within organisations at all levels.