Optimize Vehicle Design with AI and Simscape
Version 25.2.1.1 (45.6 MB) by
Steve Miller
Workflow for generating a surrogate AI model from a multibody vehicle dynamics model.
This example shows the workflow to create a surrogate AI model using training data from a multibody model of a vehicle. The resulting AI model can be used for design space exploration and for finding the optimal design parameters.
- Early-stage physical physical design is supported by creating a reduced order model to rapidly evaluate hardpoint locations.
- Sensitivity analysis is supported by running many simulations in parallel and analyzing the influence of design parameters on performance metrics
- Training data for the AI model is produced using Design of Experiments to ensure the entire design spaces is covered.
- Machine Learning and Deep Learning are both used to create surrogate models that are automatically validated against the generated data.
- Optimization algorithms are used to identify the set of design parameters that balance the tradeoff between multiple performance metrics.
- A MATLAB App enables exploration of the design space using responses surfaces.
Open the project file SSVT_Susp_Opt.prj to get started.
Use the "Download" button above to get files compatible with the latest release of MATLAB.
Use the links below to get files compatible with earlier releases of MATLAB.
- For R2025b: Use Download button above
- For R2025a: https://github.com/simscape/Optimize-Vehicle-Design-with-AI-and-Simscape/archive/refs/tags/25.1.1.1.zip
- For R2024b: https://github.com/simscape/Optimize-Vehicle-Design-with-AI-and-Simscape/archive/refs/tags/24.2.1.1.zip
Vehicle Model
Simscape Multibody is used to model the vehicle. The multibody model has 94 parameters defining the front and rear suspensions which can be tuned. This includes hardpoint locations, spring stiffnesses, and damping coefficients. The parameter values can be varied without recompiling the model so that parameter sweeps can be run as efficiently as possible.
Workflow
Try these free, hands-on tutorials to learn how to use Simscape:
- https://matlabacademy.mathworks.com/details/simscape-onramp/simscape
- https://matlabacademy.mathworks.com/details/multibody-simulation-onramp/ormb
To learn more about modeling and simulation with Simscape, please visit:
Product Capabilities:
Cite As
Steve Miller (2026). Optimize Vehicle Design with AI and Simscape (https://github.com/simscape/Optimize-Vehicle-Design-with-AI-and-Simscape/releases/tag/25.2.1.1), GitHub. Retrieved .
MATLAB Release Compatibility
Created with
R2025b
Compatible with R2024b to R2025b
Platform Compatibility
Windows macOS LinuxTags
Discover Live Editor
Create scripts with code, output, and formatted text in a single executable document.
| Version | Published | Release Notes | |
|---|---|---|---|
| 25.2.1.1 | See release notes for this release on GitHub: https://github.com/simscape/Optimize-Vehicle-Design-with-AI-and-Simscape/releases/tag/25.2.1.1 |
||
| 25.1.1.1 | See release notes for this release on GitHub: https://github.com/simscape/Optimize-Vehicle-Design-with-AI-and-Simscape/releases/tag/25.1.1.1 |
||
| 24.2.1.1 | See release notes for this release on GitHub: https://github.com/simscape/Optimize-Vehicle-Design-with-AI-and-Simscape/releases/tag/24.2.1.1 |
||
| 24.2.1.0 |
To view or report issues in this GitHub add-on, visit the GitHub Repository.
To view or report issues in this GitHub add-on, visit the GitHub Repository.
