Introduce tu búsqueda a continuación y presiona el botón para obtener resultados.
BECTON DICKINSON – Digital Twin
The project aims to identify bottlenecks in your plant’s manufacturing line before they occur or explore the outcome of reconfiguring a certain machine before making the decision to do so. Also predict the behavior of the production line in the next hours. All this is possible thanks to digital twins applied to manufacturing, such as the one already in operation at the Aragonese company Becton Dickinson.
Virtual models that allow simulations to design, test and optimize systems before implementing them in real life. Manufacturing has been one of the main drivers of the digital twins. Useful for production optimization, process efficiency improvement, performance analysis and virtual simulations for factory design and planning. Why incorporate a digital twin?
For starters, performing virtual simulations to design, test and optimize systems before implementing them in real life helps reduce costs and risks associated with process and product changes or improvements. In addition, by simulating scenarios, a digital twin can identify opportunities for improvement and optimization in systems and processes.
By having an accurate virtual replica of a system in real time, digital twins provide valuable information for decision making, he says. Having the opportunity to evaluate different scenarios and options reduces uncertainty and leads to more informed decisions.
Another application of digital twins is to serve as virtual training and education environments. In this way, employees can practice and acquire skills in a safe and controlled environment, reducing the risks associated with training on real systems. In production lines, there is a concept called continuous improvement to be more sustainable and competitive.
A digital twin can help, by constantly monitoring the performance of the systems, to predict potential problems and look for possible solutions to these problems. This allows preventive measures to be taken, maintenance to be scheduled at appropriate times and unplanned downtime to be avoided.
In many companies, we also see that a digital twin facilitates collaboration between different teams and departments because everyone can access the same source of up-to-date information, improving communication, coordination and shared understanding of processes.
The virtual model represents the operation of the syringe manufacturing line. Among other tasks, the critical parameters of each process have been analyzed and it has been verified that the virtual model behaves like the real model.
This is the first challenge: to get a model that faithfully represents the operation of the plant. To achieve this, we need technological and process knowledge. It is also important to create a model that is easy to replicate, scalable. In this way, the model can increase in size and complexity, and remain manageable. In addition, the digital twin has to be agile to evaluate many scenarios quickly and find the best solution at any given time.
Only in this way can it deliver what is expected of it, helping to identify bottlenecks, explore machine or process reconfigurations and predict line behavior. And, since a manufacturing plant is always evolving, implementing process improvements and with new products requiring process reconfigurations, being able to evaluate them virtually is a great help.
Work is underway on AI models that can learn from available information and help identify the best process configuration at any given time. AI is present in many technological aspects, here we also use it to learn from process data, learn what has gone right, what has gone wrong in the past and explore new scenarios in the future. AI multiplies the analytical capabilities of digital twins.
This pilot project has been designed to be scalable and in the coming months it will be possible to extend this technology and know-how to other lines and other plants of the company.
