9621 Agnes Crossing, Lake Suzanneview, New Mexico Island 84604-9295.
Digital twin: a popular term with many definitions. According to Cognizant, not everything with that name is actually twins. We talk to two experts about what exactly it
Digital twin: a popular term with many definitions. According to Cognizant, not everything with that name is actually twins. We talk to two experts about what exactly it takes to build a true digital twin, what it is used for and what added value it can have for a company.
Everyone is talking about today Digital twinsbut what exactly does this technology entail? “The term is used enthusiastically in various industries,” agrees Christophe Stas, Associate Director Life Sciences Manufacturing at Cognizant. “But everyone means it differently.” So time for a definition. Cognizant explains the importance of digital twins in life sciences, highlights their true value to an organization, and identifies the critical factors for successful implementation.
Digital twins in life sciences are virtual models connected to their real-world counterparts that mimic the behavior of biological processes such as cell culture growth in a bioreactor. These twins use real-time data architectures to feed the models with sensor data, predict process evolution and suggest optimal control measures to maximize production yield. In the most advanced implementation, a digital twin can directly control the physical assets in full automation.
Dr. Elisa Canzani, Data Science Lead at Cognizant, explains: “A digital twin is a model based on sensors to provide (near) real-time feedback or updates about its physical counterpart. Many organizations confuse a digital model with a digital twin. We view the digital twin as an end-to-end connected reality that leverages data streams to provide a dynamic view of physical processes in real time.”
A digital twin is a model that relies on sensors to provide real-time feedback or updates about its physical counterpart
Dr. Elisa Canzani, Data Science Lead Cognizant
This distinction is important. The twins only really come to life when they are integrated into the physical production process. According to Cognizant, digital twins must be connected to the physical sensors and process controls to provide the virtual models with actual production data. The digital twin can, in turn, predict and optimize production parameters to improve the efficiency of the production process through an open or closed feedback loop.
Canzani illustrates what such a system looks like in the abstract. “Batch data comes in real time from sensors in the production process and is transmitted reliably and cyber securely to an (edge or cloud-based) analysis platform. Digital twin models process and use such sensor data to carry out simulations and optimization scenarios and suggest optimal controls.
Then the communication goes in the opposite direction: If the model with the real-time data detects an optimization, the optimal control action flows back into the production process and its assets via the data platform. In an advanced implementation, the digital twin can control production itself fully automatically In an interim step, the digital twin can also provide optimization suggestions to human operators.
“A twin does not have to be a 3D replica of the physical asset,” emphasizes Canzani. “The solution must replicate the process dynamics in order to optimize them. 3D models can be a comprehensive representation and add to the user experience, but the core of digital twins is machine learning, data-driven and mechanistic models.”
Cognizant is strongly committed to true digital twins running on real-time streaming platforms. The initial focus is on large organizations in the life sciences sector. Think of pharmaceutical companies that can use digital twins to optimize the complex production of medicines.
There are many challenges associated with the successful implementation of a digital twin. Creating the model itself isn’t the biggest thing. Stas: “Customers have often already built models, or at least a basic design. These models then need to be developed or redeployed to run on real-time connectivity. Communication must be automatic and fast enough, ideally in both directions.”
Canzani has a different thought: “Sometimes organizations have already developed a great model, but they were using a closed environment such as third-party software.” A closed ecosystem creates problems because it becomes difficult to provide real-time connectivity with other platforms and automation systems. “
Organizations that already have a model but no true digital twin have a starting point. “Developing such a model is never a waste of time,” emphasizes Stas.
Much of the complexity comes from the connection between different teams that need to collaborate on a consistent data flow for the digital twin. A digital twin consists of an IT component with an automation team that tracks the data and an analytics team that builds the model. The data then comes from the OT environment. Different experts work in all of these business areas with different priorities and expectations. A successful digital twin must connect not only the systems, but also the people.
“People need to communicate first to reach a common understanding, and then you can connect the technology,” Canzani said. “A twin is an end-to-end system that needs to connect many different things. Many organizations are strong in one of three key areas; Production, IT or analytics. When you bring the three together, you create real added value.”
“Ideally, you don’t develop a digital twin as a one-off project,” says Stas. “The solution can be scalable and adaptable to different processes. You build the twin for a production line, and later when you launch a new product, you can reuse the framework and optimize production from the start with the twin.”
Ideally, you should not develop a digital twin as a one-off project
Christophe Stas, Deputy Director Life Sciences Manufacturing Cognizant
With this in mind, Cognizant developed TwinOps. This is a platform that consists of building blocks for data ingestion, validation, transformation and storage. These building blocks can be reused after validation and ensure a sustainable and scalable connection between the data on the one hand and digital twins on the other. “TwinOps is not only a framework for best practices, but also a Python-based suite of customizable components and building blocks for standardized, compliant and iterative workflows,” explains Canzani.
In addition, according to Stas, Cognizant has a good understanding of the challenges in all areas associated with implementing a digital twin. “We know where the challenges and bottlenecks lie,” he says. “We can correctly assess whether the investment is worth it and what a realistic business case entails.”
Stas continues: “For a good assessment of relevant technologies, you need vendor-independent knowledge, with a strong understanding of rules and standards and of course cybersecurity.”
An investment in a true digital twin will pay for itself in the long term. Canzani: “A digital twin can improve the yield of a process by ten percent.” In the pharmaceutical sector, this corresponds to an optimization of 400 million euros per year.”
However, you shouldn’t start big right away. “At the beginning of every process there is an assessment of the maturity of the organization,” says Canzani. “We are looking for a use case that is advanced enough where there is both data available and a good understanding of the underlying processes to model with the digital twin.”
“Then we create a digital twin for an initial limited use case,” Canzani continues. “We start small-scale but immediately build the twin with an architecture that supports real-time usage and scalability. The workflow must be automated and repeatable according to TwinOps best practices.” Such a small rollout immediately creates added value and shows that the investment is worth it. “Based on this first small but complete use case, we are building trust with stakeholders to clearly see the feasibility and potential. This allows us to scale the project while introducing other use cases.”
This is an editorial piece created in close collaboration with Cognizant.
Source: IT Daily
As an experienced journalist and author, Mary has been reporting on the latest news and trends for over 5 years. With a passion for uncovering the stories behind the headlines, Mary has earned a reputation as a trusted voice in the world of journalism. Her writing style is insightful, engaging and thought-provoking, as she takes a deep dive into the most pressing issues of our time.
