Maximising Battery Performance and Lifespan With AI

In this newsletter, I share the learnings from Monolith from over 300+ AI projects with engineering leaders and provide:

• Helpful?insights?from our learnings working at the forefront of product development
• Expected benefits from adopting a more data-driven workflow
• Guidelines?to evaluate a suitable use case for AI

Follow me for more insights on AI in Engineering Product Development.

4 Applications for AI in Validation Test ??

Artificial Intelligence (AI) predictive capabilities are changing how engineers test complex systems' intractable physics. For complex systems, traditional physics-based simulations often fail to predict design performance across a wide range of input conditions and design parameters.

We’ll show how you can reduce your validation testing by up to 73% based on battery test research done by teams at Stanford, MIT, and Toyota Research Institute.

By embracing AI and machine learning principles, engineering teams can navigate the intricate challenges of understanding - and validating - the intractable physics of complex products more efficiently, leading to streamlined development, optimised designs, and faster time to market.

Download the white paper here ?? https://www.monolithai.com/white-papers/ai-applications-validation-test

Data-driven prediction of battery failure for electric vehicles ??

Despite great progress in battery safety modeling, accurately predicting the evolution of multiphysics systems is extremely challenging. The question on how to ensure safety of billions of automotive batteries during their lifetime remains unanswered. In this study, we overcome the challenge by developing machine learning techniques based on the recorded data that are uploaded to the cloud.

Using charging voltage and temperature curves from early cycles that are yet to exhibit symptoms of battery failure, we apply data-driven models to both predict and classify the sample data by health condition based on the observational, empirical, physical, and statistical understanding of the multiscale systems. The best well-integrated machine learning models achieve a verified classification accuracy of 96.3% (exhibiting an increase of 20.4% from initial model) and an average misclassification test error of 7.7%. Our findings highlight the need for cloud-based artificial intelligence technology tailored to robustly and accurately predict battery failure in real-world applications.

Lessons from Stanford and MIT: Optimise Battery Testing ??

Battery technology is at the forefront of innovation, driving advancements in electric vehicles (EVs) and renewable energy storage. The demand for more powerful, longer-lasting batteries is on the rise, but it comes with complex challenges in testing and optimization.

Batteries are intricate systems with conflicting design objectives, including lifespan, cost, and safety. Engineers face regulatory requirements, certification standards, and customer demands while navigating a vast design space.

AI's predictive capabilities are transforming battery system testing, a critical validation step. Collaborative research by Stanford, MIT, and the Toyota Research Institute focused on fast-charging EV batteries without compromising their lifespan.

Machine learning, showcased in a Nature journal paper, significantly reduced testing times by 98%, making it a game-changer for battery applications. It enables engineers to analyze large datasets, uncover hidden patterns, and optimize battery performance, lifespan, and cost.

Read the full article??

Upcoming Webinar: October 17th @ 16:00 CET / 15:00 BST

Battery testing with AI:? Build a more efficient test plan you can trust? ??

• Learn how to define your design of experiments to achieve optimal coverage of the design space, including the use of AI models for better results than random or factorial experiments.
• Train and optimise an EV battery model in Monolith using real-world test data with no required programming or data science expertise.
• Apply robust active learning algorithms for real-time test recommendations to improve the model in much fewer testing steps iteratively.
• Share your findings with other team members, departments, or clients.

Feel free to contact the experts at Monolith to discuss your AI Use Case and run a feasibility analysis.

If you’d like to see more tips on AI in Engineering and Machine Learning for Battery Design, Lifetime and Charging Strategies, consider subscribing to this newsletter!

Test Less. Learn More.

Richard