
AI boost for more accurate digital twin development
Siemens Digital Industries Software has developed an AI-based Simulation Predictor and Reduced Order Modeling software to boost the development of digital twin technology.
The HEEDS AI Simulation Predictor uses machine learning with built-in accuracy awareness to help fine-tune and optimize a digital twin by by tapping into historical simulation studies and accumulated knowledge.
This comes as Siemens teams with Amazon to provide the PAVE360 digital twin tool in the Amazon cloud to build digital twins of cars using ARM CPU models.
One of the most significant challenges in AI-powered simulation is AI drift, where models extrapolate inaccurately when faced with uncharted design spaces. To address this challenge, HEEDS AI Simulation Predictor introduces accuracy-aware AI that actively self-verifies predictions. This helps engineers conduct simulations that are not only accurate but also reliable in the context of real-world industrial engineering applications.
“With HEEDS AI Simulation Predictor, we have significantly improved various components of the gas turbine, leading to highly optimized designs and accelerated design cycles,” said Behnam Nouri, Team Lead, Engineering & Platform Design, Siemens Energy.
“Our thermo-mechanical fatigue predictions have been effectively upgraded to process ~20,000 design members in only 24 hours, yielding a 20% improvement in component lifetime. This has allowed us to fully characterize the limits of our existing design space which is required for high-efficiency turbine engines. The HEEDS AI Simulation Predictor technology has enabled us to save over 15,000 hours of computational time.”
Siemens has also introduced Simcenter Reduced Order Modeling for high-fidelity simulation and test data to train and validate AI/ML models. By training AI/ML models on comprehensive datasets, this technology enables engineers to gain robust, reliable, and trustworthy insights, helping to eliminate the common issue of AI drift.
“Simcenter Reduced Order Modeling lets us accelerate our simulation models to the point where a detailed fuel cell plant model runs faster than real time, with the same accuracy as a full system model,” said Jurgen Dedeurwaerder, Simulation Engineer at Plastic Omnium who is using the tool..
“This enables activities such as model-in-the-loop controller development and testing to be done faster, shortening the overall development cycle by around 25%. At the same time, it gives us a reliable, IP protected, and cost-effective way to distribute models to other teams, both internally and to our customers to augment their own products and processes, resulting in better quality products delivered to end users.”
“HEEDS AI Simulation Predictor and Simcenter Reduced Order Modeling represent a true breakthrough in simulation technology. They enable our customers to take advantage of benefits of artificial intelligence-driven simulation to speed their exploration of a design space and to do so accurately and robustly,” says Jean Claude Ercolanelli, Senior Vice President, Simulation and Test Solutions at Siemens Digital Industries Software.
“It also enables them to not only use these breakthrough technologies on new projects, but to leverage decades of past simulation data to help deliver new insights on current projects.”
- Renault creates industrial digital twin ‘metaverse’
- WAE launches digital twin and BMS software for EVs
Having the PAVE360 software available on Amazon Web Services (AWS) provides scalable simulation speeds which are significantly faster than conventional on-premises modeling and simulation infrastructures.
This includes includes IP from ARM that is built for automotive-specific workloads, functional system software, real-world stimulus and algorithm development tools such as Simcenter Prescan and mixed-fidelity EDA modeling and simulation engines
PAVE360 seamlessly integrates all these sources to provide not only a virtual car on an engineer’s desk but also a virtual car in the cloud that is more integrated and secure, dramatically reducing resources and costs for manufacturers. This helps to eliminate the need for costly IT upgrades to support high-speed simulation and can free up automotive engineers to focus on making more meaningful improvements.
“The automotive industry is facing disruption from multiple directions, but the greatest potential for growth and new revenue streams is the adoption of the Software Defined Vehicle (SDV),” said Mike Ellow, Executive Vice President, EDA Global Sales, Services and Customer Support, Siemens Digital Industries Software.
“The hyper-competitive SDV industry is under immense pressure to quickly react to consumer expectations for new features all while being pushed to move towards shorter software development cycles. This is driving the adoption of the “shift-left” methodology for parallel hardware and software co-development and the move toward the holistic digital twin. Delivering PAVE360 on Arm-based AWS cloud services helps enable organizational efficiencies that are simply not available through today’s traditional development methods.”
“The software defined vehicle is survival for the automotive industry, requiring new technologies and methodologies for faster and more agile development,” said Dipti Vachani, Senior Vice President and General Manager, Automotive Line of Business, Arm. “The innovative Siemens’ PAVE360 solution is helping to accelerate the automotive system development required to address the increasingly demanding consumer expectations. Together with Siemens and AWS, we are enabling a breadth of use cases on the Arm automotive platform across the entire supply chain, from IP evaluation to fleet management.”
“The proliferation of digital twin methodologies throughout the automotive industry uses the compute capabilities and world-class infrastructure of AWS,” said Wendy Bauer, Vice President of Automotive and Manufacturing, AWS. “With PAVE360 mapping accurate embedded environments to optimal AWS instances while using Arm automotive enhanced IP, OEMs and suppliers are enabling software defined vehicle solutions and methodologies that were previously impractical.”
eda.sw.siemens.com/en-US/pave360/
