Speed up vehicle development process with AI tools

In the ever-evolving landscape of product development, advancements in technology have paved the way for innovative solutions to streamline processes and improve outcomes. One such groundbreaking innovation that is revolutionizing the industry is AI-supported noise prediction.

We are working on an AI-powered NVH analysis tool aimed at addressing the challenges posed by current software tools that often require a steep learning curve. Many existing solutions offer a one-size-fits-all approach, which can be limiting for engineers at different experience levels. Also, we want to reduce the testing burden like TPA methods by making use of functional mapping related deep or machine learning methods. Goal is to minimize physical testing while maintaining high predictive accuracy and providing a more tailored user experience.

For TPA methodology, instead of relying solely on transfer function measurements, our neural networks will learn from historical datasets to predict interior noise levels with various inputs (started with structural inputs) more efficiently. Additionally, we are developing an automated NVH post-processing system that allows users to select their experience level, enabling less experienced engineers to rely on AI-driven insights while allowing experts to fine-tune results for basic calculations such as overall level computations, order analysis, and filtering etc.