HPC-Powered Simulation Helps Engineers See into the Future

Oct 04, 2022
High-Performance Computing

Engineers are increasingly turning to simulated environments powered by high performance computing (HPC) to enhance computer-aided engineering processes.

Credit: Dell

 Imagine being able to fly one of the world’s fastest airplanes in a digital environment. In that virtual world, you can test the plane’s viability by adding or removing environmental and man-made variables. Or simulate jet engine performance to reduce fuel consumption and wear. Planes tested in these environments are more efficient, safe and sustainable. Existing crafts are maintained proactively, and the next generation is designed for future air mobility needs.

These digital environments that mirror reality, also known as digital twins, are based on fundamental principles of modeling, physics, mathematics and computer science. They are being brought to life by computer aided engineering (CAE) enhanced by high performance computing (HPC). This new configuration has the capacity and speed to handle data-intensive simulation applications across a wide variety of industries. The result is a quantum leap in performance and capabilities.

Today’s Engineering Challenges and the Promise of Digital Simulation

While the expectation of engineers to design more (better and faster) hasn’t diminished, the industry is facing some monumental challenges. Today’s engineering workforce is more distributed than ever, which can hinder collaboration and performance among teams. Engineers are also being tasked with producing more fuel-efficient products, reducing emissions, and optimizing maintenance, repair, and overhaul windows to save on costs.

As engineering teams grow beyond capacity, digital simulation powered by HPC is helping ease the burden. Engineers can collaborate with one another and do their work in a virtual environment, improving the speed and efficiency of engineering workloads. Simulation gives engineers the power to see how their designs will behave in millions of real-world scenarios, while reducing or even eliminating the need for costly physical testing. Ultimately helping engineers improve the safety, sustainability, and performance of products.

Engineers at United Kingdom’s McLaren Group are using simulation and prototyping to design faster, more aerodynamic vehicles. The engineering team conducts simulations powered by HPC based on as many as 100,000 data points per second coming from Formula 1 race cars as they’re moving at up to 200 miles per hour. The McLaren engineers build 3D digital twins and 3D printing models for continuous rapid prototyping and to generate analytics to improve car performance in subsequent races. The results of these efforts lead to rapid prototyping and testing of components. 

HPC for Power Plant Design

Simulation was the answer for California-based engineering company RJM International, a provider of emissions reduction and combustion improvement technologies, that serves large combustion plants like refineries and steelworks. The company runs operational analyses and simulations involving a series of computational fluid dynamics (CFD) on a HPC cluster with the goal of helping plants run more efficiently and limit emissions through adoption of co-firing, biomass fuels, or next generation energy pellets.

Engineers at RJM International use audits and detailed data sets to build accurate models of power plant performance. The team uses Ansys simulation software integrated with HPC infrastructure from Dell. This solution allows engineers to use CFD data to devise, test, and prove new solutions prior to their installation. It’s also modular, so the engineers can easily deploy a system optimized for the compute, storage, networking, and software requires of their specific HPC workloads.  

Simulations that took a week are now completed in a day ― using 86% less compute time than the company’s previous computing infrastructure. The cluster also enables RJM to run a variety of large, sophisticated computations to solve other complex engineering challenges.  Engineers can quickly and cost-effectively validate product integrity prior to prototyping by modelling behavior across real-world variables.

Simplify and Accelerate HPC

Retooling an IT environment for high performance engineering workloads can be streamlined by engineering validated architectural designs which include servers, storage, networking, software and services in customizable configurations. They’re designed to help simplify and speed the configuration of HPC clusters whose design has already been tested and tuned for CAE. 

As teams continue to work remotely and CAE software advances in sophistication, engineers are leading the way in the adoption of advanced computing technologies to overcome new challenges. HPC is not one-size-fits-all. The right solution configuration depends on a specific mix of applications and types of simulations, with a variety of options to consider. But once past those hurdles, HPC is playing a major role in advancing the use of simulation in engineering, speeding time-to-market and contributing to the design of innovative and higher-quality products.

For more information about how to leverage engineering simulation tools powered by HPC, click here.


Intel® Technologies Move Analytics Forward

Data analytics is the key to unlocking the most value you can extract from data across your organization. To create a productive, cost-effective analytics strategy that gets results, you need high performance hardware that’s optimized to work with the software you use.

Modern data analytics spans a range of technologies, from dedicated analytics platforms and databases to deep learning and artificial intelligence (AI). Just starting out with analytics? Ready to evolve your analytics strategy or improve your data quality? There’s always room to grow, and Intel is ready to help. With a deep ecosystem of analytics technologies and partners, Intel accelerates the efforts of data scientists, analysts, and developers in every industry. Find out more about Intel advanced analytics.