Machine learning is becoming an increasingly important part of our personal and business lives, either as a conscious decision by the user or subtly through the basic tools we use daily. Artificial intelligence software is also transforming how automotive engineers develop complex products. We believe by 2030 every engineer will be an AI engineer.
The power of AI lies in its ability to reduce the amount of physical testing time and simulations required to successfully develop products, especially those with highly complex physics. Using valuable and sometimes limited engineering test data, AI software can instantly predict product performance – or failure – and enable engineers to identify the exact areas where testing should be done, and where it can be skipped. With reduced repetitive, time-consuming physical tests, AI promises increased confidence in product quality while accelerating time-to-market.
The ChatGPT bot nicely visualizes through text how much more you can get out of data. Essentially, the software is taking existing data and delivering an output that the end user finds interesting or useful. However, unlike ChatGPT, engineers don’t need that much data to train a self-learning model. They leverage the test data that exists, but often goes unused, to deliver new engineering insights and accelerate product development.
With this outcome, it’s clear that self-learning models can become a standard tool for engineering. Yet, there’s understandable anxiety among knowledge workers that AI eventually could take work away from humans. But we see much more upside than potential risk of downside. Where AI might replace jobs at some point down the line, this technology not only will foster greater engineering creativity but also create many more new jobs. If we’re going to have an economy that grows, we need to reinvent how we do things. We can’t keep doing things the same way and expect progress.
As AI becomes a trusted part of the product-development process, we expect engineers across automotive and other industries to significantly reduce verification and validation steps that today take weeks or months. Of course, there are areas in which AI is more suited than others, but the wheelhouse of our AI software is firmly located in deeply complex engineering problems where the physics are intractable and the number of parameters are extensive.
An example is Kautex-Textron, a top 100 automotive supplier to global OEMs. AI technology enabled the Kautex-Textron validation engineering team to solve one of their most complex engineering challenges with vehicle acoustics, skipping CFD WHAT IS CFD? while reducing design iterations and prototyping and testing costs. Leveraging the power of AI to accurately predict sloshing noise generated when a vehicle decelerates, the work opens up a world of opportunities for Kautex-Textron engineers to expand the application of AI to solve further engineering challenges in the era of electrification.
Using AI, engineers can leverage their data to calibrate products for better performance, whether that’s a battery, an engine or a fuel tank. As a senior executive at one of our automotive customers says, “It almost gives them superpowers.”
These AI engineers do not need to be Python coders or data scientists, just domain experts in their field. AI software that is built by engineers specifically for engineering domain experts allows them to quickly understand and instantly predict complex physics where simulation tools and traditional R&D methods fall short and slow time-to-market.
Richard Ahlfeld (pictured, left) is founder and CEO of Monolith, an artificial-intelligence software provider to leading automotive, aerospace and industrial engineering teams.
