Digital Twins Helping EV Development

Powertrain electrification brings additional challenges to manufacturing operations. But digital twins can help companies identify and address numerous issues faster and at smaller costs.

Manufacturing an electrified vehicle, whether it is a battery-electric vehicle (BEV), plug-in or regular hybrid (P-HEV, HEV) or fuel-cell electric vehicle, is forcing automakers and suppliers to innovate at a faster pace. "The pressure to innovate and produce mass-market vehicles forces the entire transportation industry to adapt and to deliver solutions that offer desired attributes – drive range, performance, life and in-vehicle experience – at low cost," said Siemens on a recent blog post.

Manufacturers and developers are introducing a solution to address these challenges in the form of “digital twins.” IBM defines a digital twin 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 highly complete virtual models that represent with fidelity the physical elements of a product, whether it is a car, building, bridge or jet engine. Digital twins have proven useful when embarking on state-of-the-art digital transformation and IoT projects. "Before the real implementation, we work on a digital twin, which is to design the product and the production line virtually. This digital-reality combination is the basis for implementing a successful digital transformation," said Alejandro Preinflak, CEO of Siemens México to MBN.
 

The Role Digital Twins Play in EVs

Academics Wu, et al (2020), have highlighted the role digital twins have in improving the performance of lithium-ion batteries, the essential element of any EV powertrain. "The lifetime of these devices depends greatly on the materials used, the system design and the operating conditions. This complexity has therefore made real-world control of battery systems challenging. However, with the recent advances in understanding battery degradation, modelling tools and diagnostics, there is an opportunity to fuse this knowledge with emerging machine learning techniques towards creating a battery digital twin," they wrote.

The digital twin acts as a "cyber-physical system" that both scientists and engineers from industry and academia can use to develop "more intelligent and interconnected battery management in the future," said the paper. A more recent study by Bhatti, et al (May 2021) highlighted the advancements of the digital twin technology in the development of smart electric vehicles.

Academics point out that there are three stages of a digital twin model for EV batteries. First there is the archetype modeling, in which the developer should decide first which archetype segments are to be displayed. Second, there is the modeling of virtual sensors, where the selection and implementation of computer-generated sensors are undertaken. Finally, the third stage is "to define the pertinent boundaries which shall be periodically updated to synchronize the archetype with the physical machine's present condition."

Digital twins are not new to the automotive industry. They are also used in intelligent driver assistance, autonomous navigation, smart manufacturing and other developments as Preinfalk mentioned. Recently Volkswagen and AWS announced the launch of an industrial cloud that will include a wide range of software applications. Digital twins have also been addressed during Mexico Automotive Summit by leaders in the heavy industry segment.