Optimize Vehicle Design with AI and Simscape
Overview
This session demonstrates how AI-driven surrogate models can accelerate early-stage physical design by enabling rapid design space exploration. We show how to leverage deep learning, machine learning, optimization, multibody modelling, and parallel computing to create a surrogate model. The resulting AI model calculates performance metrics near instantaneously which enables design space exploration and optimizing system performance. To illustrate this workflow we use a vehicle suspension system, where physical design parameters are tuned using the AI model to improve and balance competing metrics such as ride comfort and handling. The workflow shown in this presentation is applicable to early-stage physical design for mechanical, electrical, and thermal systems.
Highlights
- Physical modeling with parametric models for efficient evaluation of vehicle performance
- Sensitivity analysis to identify which parameters have the most impact on performance
- AI-based surrogate modeling of the high-dimensional, nonlinear design space to enable rapid trade-off and “what if” studies
- Iterative optimization to identify optimal designs for difference design scenarios, competing criteria, and changing requirements
Please allow approximately 45 minutes to attend the presentation and Q&A session. We will be recording this webinar, so if you can't make it for the live broadcast, register and we will send you a link to watch it on-demand.
About the Presenter
Jianghao Wang is a Senior Product Manager for Deep Learning and AI at MathWorks. In her role, Jianghao collaborates with users and developers to build out and deliver on MathWorks AI product strategy. Prior to that, Jianghao led the AI education initiatives at MathWorks, supporting educators and researchers on their AI projects. Before joining MathWorks, Jianghao obtained her Ph.D. in Statistical Climatology from the University of Southern California and B.S. in Applied Mathematics from Nankai University.
Kishen Mahadevan is a Senior Product Manager in the Controls and Deep Learning Marketing Group at MathWorks. In his role, he leads initiatives to promote and drive the adoption of control products, collaborating closely with development teams to shape the strategic product roadmap. Prior to moving into product marketing, Kishen spent two years as an Application Support Engineer at MathWorks, providing guidance to customers on Simulink workflows, with a particular emphasis on physical modeling, controls, and deep learning applications. Kishen holds an M.S. in Electrical Engineering, specializing in Control Systems, from Arizona State University, and a B.E. in Electrical and Electronics Engineering from Visvesvaraya Technological University, India. His combined expertise in product management, technical support, and engineering enables him to bridge the gap between customer needs and innovative product solutions.
Steve Miller has been a core part of the Simscape team at MathWorks since 2006. Steve joined MathWorks as an Application Engineer in 2005 and moved to product management in 2006. Prior to that, Steve worked at Delphi Automotive in Braking Control Systems and at MSC.Software Adams consulting in various capacities at Ford, GM, Hyundai, BMW, and Audi. Steve has a B.S. in Mechanical Engineering from Cornell University and an M.S. in Mechanical Engineering from Stanford University.
