How Digital Twin Applications Can Help Manage and Optimize Inventory

This case study shows how one manufacturer used simulations to evaluate processes and potential equipment investments. 

TAKEAWAYS:
● Manufacturers can use digital twins to conduct real-time analyses of processes or operations to predict future performance.
● Running simulation scenarios helped an industrial food production company address bottlenecks and avoid spending millions on new tanks.
● Models created using digital twins can be easily modified to evaluate new operating scenarios in the future.  

Plenty of manufacturers use scenario modeling to forecast how their inventory needs may ebb and flow as supply and demand shift. But for organizations that want to enhance the precision of such forecasts, digital twin technology can take things a step further.

Digital twins—essentially virtual representations or simulations of physical operations—allow manufacturers to see how a process or operation performs in real time and predict how it may perform in the future. This type of simulation will increasingly become table stakes in the smart factories of the future.

One RSM client, a midsize industrial food production company, used digital twins to optimize its bulk inventory management capabilities and ultimately determine which investments in personnel, storage tanks, and other supporting storage capacity were necessary. Through simulation, the business was able to re-focus investments on areas of the business that would yield more value. We explore the factors at play in putting this transformative technology into action.

Determining Future Capacity

At the outset of the project, the industrial food production company had numerous priorities: making operations as efficient as possible, improving business processes, and reducing operating expenses while also prioritizing capital investment. To achieve those objectives, the company had purchased production line equipment that would enable it to produce a greater volume of product, but it needed to understand the upstream implications before increasing capacity.

That’s where a simulation analysis proved helpful. The company fed operational data into a digital twin model and ran various simulations to understand what the appropriate size of production equipment would be needed to meet the production line demands. Solving that question had many variables, including product mixes, batch sizes, upstream processes’ capacity, new and existing equipment, and plans for future growth.