Jakko Nieuwenkamp from Reden Research & Development Nederland gave a short presentation during the Math4NL community event “Digital Twins” with title "Digital twin for remaining useful lifetime estimation of an electrical component".
Electrical components play an increasingly important role in our everyday lives. We rely on them to function and keep on functioning, for example in autonomous vehicles. For these high-technological applications, it is important to have an accurate estimate on the state of the components and the remaining useful life. With this knowledge, the right actions can be taken to ensure the safety and availability of the device. Our aim is to create a digital twin of an electrical component. The first benefit of a digital twin is that it is transparent: state parameters that cannot be measured or seen in the physical object can be evaluated in the digital twin. Second, the digital twin can be used to predict future behavior of the device. These two characteristics allow us to estimate the current state and the remaining useful life of the component. The accuracy of this estimate fully depends on the how well the digital twin resembles the physical object. The challenge is to combine as much relevant data and knowledge as possible to create an accurate representation of the physical object, while keeping the processing time and effort within limits.