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:
With an understanding of how Digital Twins work, the next step is to have a framework on which to start the process.
Start with questions that will drive you to articulate the necessary features of your system. Some of these questions are:
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.