In the third in a series of articles on the value of simulation, Ian Risk of the Center for Modeling & Simulation explores the essential role simulation plays in the creation of digital twins and enables engineers to meet the demands of our world. evolving.
The ability to independently and accurately monitor and virtually model how a process or product operates in real time without physical intervention is the ultimate price for engineers and manufacturers.
Without the enormous cost of downtime, it can assess all kinds of performance-enhancing scenarios, from equipment upgrades to assessing safety issues that may arise in service.
Guest blog: why digitization is vital for future prosperity
Guest blog: Building the right product with simulation
This “holy grail” is now commonly referred to as a Dual digital of the product. Working in symbiosis with its real-world counterpart, the digital twin is a fully connected but virtually modeled representation of the product, continuously fed by live data from the actual physical system.
Creating a viable digital twin is a major undertaking. If it is to be used to predict what may happen to a product or system as circumstances change, then the business consequences can be substantial in one way or another. This makes a high level of confidence in the outcome essential.
Any model is only as good as the data used to develop it. A digital twin is no different – it needs data to grow with its physical counterpart.
Capturing real-world data has historically been a long-term problem, especially for large volumes. This means that existing models operate in retrospect rather than being able to make predictions based on live data. A model that tells you what went evil is much less valuable than the one that tells you something will not going well.
Industry 4.0 provides the means to capture and record data at scale and can quickly identify variations in the condition of a component or system. It goes well beyond crossing a set threshold and can provide insight into how a system may degrade or act based on its original design assumptions.
This amount of data means that the digital twin has the potential to predict the remaining life of the system, anticipate maintenance activities, or improve the design for greater resilience to variations. Essentially, improving the product and providing better service to the customer.
The role of AI
However, for some applications, the volume and speed of data required is impossible to monitor by a single human. Fortunately, with the advent of techniques such as AI, properly trained algorithms running on relatively simple computing platforms can automatically monitor changes, highlight them for traders, and advise them on potential actions. they can undertake. Statistics from the US Department of Energy indicate that these AI systems could reduce equipment downtime due to unexpected failures by 35-40%, which currently costs $ 150 billion per year. Likewise, for large-scale manufacturing facilities, such failures can result in a loss of productivity of hundreds of thousands of pounds per day.
While AI systems can handle the volume of data generated, the algorithms used must also identify the law data in order to provide meaningful results. Just as the human brain uses the senses to learn, algorithms learn by observing or experiencing what is good and bad – or even out of the ordinary.
A maintenance engineer spends years gathering knowledge from textbooks and manuals as well as the experience of working with peers and observing what may and may not contribute to failure. An AI system must do the same. You have to experience all, which is often physically impractical to achieve. This is where simulation is able to fill the void in what can be replicated from the real world, synthetically.
It all comes down to simulation
Simulation can create the range of scenarios an AI system needs in order to learn how a product should work or what it is likely to experience – effectively integrating a lifetime of knowledge into a relatively simple algorithm. It is essential that this be done to accurately encode knowledge in these systems and that the approach be approved by experts. Only then will the system have value and subject matter knowledge that can be trusted.
Simulation can also help us understand what happens if things go beyond the realms of human experience or when unforeseen properties emerge from the use of a system. It can do this at a much faster rate than could be achieved in physical testing, which, again, means less downtime and better productivity.
It is not only maintenance that can be taken care of in this way. Production, quality control and operations management can all be improved through such AI systems. But, to develop them reliably and make them profitable, you need simulation.
This shows that simulation is necessary throughout the life of a product. This is something every manufacturer must embrace throughout their business if they are to remain efficient and achieve the highest levels of productivity.
As the world around us changes, engineers must question what they do in a more comprehensive yet economical way if we are to provide products that meet the needs of society, such as the search for net-zero. . Virtualizing design and simulation by embracing digitization is a key path to achieve this goal and realize the power of concepts such as digital twins.
As the industry has moved on from a situation where large-scale physical experimentation is the modus operandi, there is still a long way to go. The next leg of the journey requires the industry to overcome two hurdles.
First, adopt a mindset that not only cultivates a digital culture within organizations, but also champions how a digital approach can bring about change. Second, as technology continues to evolve, so too must simulation, emerging from the constraints of what can be bought off the shelf. Industry needs to democratize this capability to a much greater extent than is seen today through better collaboration and open source software.
The payoff for taking these important next steps on the digital journey is clear, but the journey itself is also imperative if engineers and manufacturers are to become more innovative, efficient and sustainable.
Ian Risk is Chief Technology Officer at CFMS, responsible for evolving the company’s technical vision and leading all aspects of technology development based on its strategic direction and growth goals. Ian was previously responsible for Airbus Group Innovations UK, where he was responsible for the company’s UK research capacity, technical strategy development, business development and launching industrial and academic partnerships.