Introduction

Author: Richin Technology Frank-Su

In modern wheel rim design, engineers need to strike a balance between styling, lightweight design, strength, and durability. This design process usually requires repeated communication and adjustments; using traditional CAE modeling and analysis is often time-consuming and labor-intensive. This article introduces how to use Altair’s AI tool physicsAI to “quickly and accurately predict the stress of newly designed wheel rims with AI, without relying on traditional CAE analysis.”

Background

During wheel rim design, engineers must balance styling, lightweight design, strength, and durability.
Traditional design methods require repeated CAE modeling and analysis, which not only consumes a large amount of time but also involves frequent design modifications.

Results

Using Altair’s AI prediction tool, we parameterized the wheel rim dimensions at the CAD stage and imported them into SimLab to set up analysis and automation workflows. Through DOE, multiple different wheel rim design datasets were generated and automatically analyzed with CAE. The CAE analysis results were then used to train the AI prediction model.
With the wheel rim AI stress prediction model, a task that originally required more than one hour using traditional methods can now be completed in just thirty to forty seconds to predict stress on a new wheel rim design.
Practical testing shows that the difference between AI prediction results and CAE analysis results is only 0.2%, demonstrating the “high accuracy” and “practicality” of the AI model.

Technical Highlights

Parametric Design
Wheel rim dimensions are parameterized at the CAD stage to facilitate the subsequent automated DOE process.

SimLab Automated Workflow
Use SimLab for meshing and analysis setup, and record these operations to create an automated workflow.

AI Model Training
Train the AI model using historical CAE analysis results and DOE-generated data, selecting appropriate neural network model parameters and validating the model’s accuracy.

Rapid Prediction
The AI tool can complete stress distribution prediction for a new wheel rim design within thirty to forty seconds, saving a substantial amount of time compared to traditional CAE analysis.

Conclusion

Through AI technology, engineers can quickly predict wheel rim stress at the design stage, reduce repeated CAE analyses, and improve both design efficiency and accuracy. Altair’s AI tools can run within the familiar HyperMesh environment, allowing engineers to easily integrate them into existing workflows, achieving an efficient combination of design and virtual validation. It is hoped that this introduction will inspire CAE engineers and help drive further advancements in wheel rim design technology.

Further Reading: YouTube Video Introduction

Richin Technology is an “expert in CAE and AI data analysis”, and we have completed many successful case studies.

▶ Contact us now to get more information.
▶ Subscribe to the Richin YouTube channel to explore more CAE and data analytics.

Back to list