Digital Twins and the Future of Productivity: New Approaches to ROI

Digital twins, and the Future of Productivity: New Approaches to ROI?

The concept of process improvement is about to be upended… factories of today collect massive amounts of data and use tools such as Microsoft Business Intelligence (Power BI) to create dashboards. These dashboards tell a story of what happened and model changes for process improvement. They have worked very well to establish standards and provide an early warning system with their formidable ability to bring relevance and context to data, but they cannot do a simulation and change variables using AI or ML in a predictable fashion then immediately bring them back into the physical world to provide ROI.??

Enter Digital Twins, which IBM defines as “… a virtual representation of an object or system that spans its lifecycle, is updated from real-time data, and uses simulation, machine learning and reasoning to help decision-making.” Digital twins are exact duplicates of a physical device or object such as an airplane, a skyscraper, machine, an entire factory or anything else that can be mapped as a virtual model. Once mapped and connections made between the physical device or object via sensors and the digital twin, data can be extracted in real-time and input into the Digital Twin to change variables, learn how those variables impact the system and then bring the successful variables into the object or system and achieve the modeled results.??

As a recent example, an airport in Germany wanted to maximize the efficiency of a proposed baggage handling system with Autonomous Guided Vehicles (AGVs). The objective was to find the most efficient path of each vehicle to ensure optimal system performance at the different waypoints by identifying cost efficient system variables and scenarios. The variables and scenarios, among many, were time of day, flight loads, accuracy of bar codes, weather conditions, battery level of the AGVs, support personnel, time to unload aircraft and number of AGVs on the ground.??

After a Digital Twin was created of the entire system, multiple variables were analyzed in this virtual environment and paths were simulated, tested and then established for the AGVs. The actual ROI was in-line with predicted results from the Digital Twin:?

• The number of required AGVs reduced by 13%?
• The number of necessary charging stations reduced by 17%?
• Overall costs were reduced by 14%?

(Source: Siemens Logistics GmbH, Germany - Optimized autonomous airport baggage handling with AGVs | Siemens References)?

?

With an understanding of how Digital Twins work, the next step is to have a framework on which to start the process.?

1. Define your purpose and scope?

Start with questions that will drive you to articulate the necessary features of your system. Some of these questions are:?

• What system functions will the Digital Twin monitor??
• Will the Digital Twin allow for remote access, or will users be on-site??
• What will be the process be to operate the Digital Twin??
• What controls must be in place??
• How many variables to the system will you want to introduce??
• How will you define success of the Digital Twin??
• What outside expertise needs to be brought in to help??
• What internal expertise is necessary to manage the system??
• What is my available budget for the initial engagement and future phases??
• Do we have top-down support for this project??

2. Choose your tools?

• Since Digital Twins transmit data between their virtual and physical counterparts, what kind of data is available??
• What Internet of Things (IoT) devices and tracking equipment are available and will they effectively transmit the necessary data??
• Will the physical infrastructure support wiring and cabling necessary for the IoT devices??
• Do you have the necessary infrastructure support (Azure, AWS, dedicated servers)??

3. Capture the physical environment and infrastructure digitally?

• Can you generate a 1:1 model that faithfully reflects the physical environment/machinery??
• Do you have the Machine Learning (ML) model to take the captured images and create the virtual model?

4. Bring functionality to the Digital Twin?

• Visual elements may be powered by gaming platforms and will have the look and feel of your physical environment, but they still need to be rendered. You or your partner’s design team will bring a realistic look and feel (colors and textures) to the model to add realism and familiarity.?
• Integration of IoT devices is necessary???

The magic behind modeling in real-time using digital twins is that variables can be tested and optimized virtually and immediately brought back to the physical world for improvement and ROI. Since there is no delay, continual improvement and ROI is the new approach to productivity.??

These are exciting times… when you are ready to create Digital Twins in your environment, contact the experts at Softura