Bringing Pre-Trained Battery Models to the Market

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

Feel free to follow me for more insights on AI in Engineering Product Development.

Understanding Battery Degradation With AI and Test Data????

?? Watch the full webinar here: https://www.monolithai.com/webinars/ev-battery-data-ai

By employing an AI-guided test strategy, test engineers can accelerate new products to market in the following ways:

? Learn how to use AI for more efficient battery cell validation and more accurate lifetime estimates.

? Gain insights into developing an AI-powered test plan, optimising the number of tests required, and improving overall battery analytics.

?Explore how high-quality battery test data can accelerate your development effort.

?Learn how Monolith and About:Energy will collaborate to bring new possibilities to the battery development process.?

Machine Learning in Lithium-Ion Battery Cell Production: A Comprehensive Mapping Study ??

Over the last five years, machine learning approaches have shown significant promise in understanding and optimizing the battery production processes. This comprehensive review details the state-of-the-art applications of machine learning within the lithium-ion battery cell production domain. It highlights the fundamental aspects, such as product and process parameters and adopted algorithms.

The figure?explores the relationship between input variables, output variables, and adopted algorithms. The focus has been given to the combination of input and output variables analyzed in at least two studies to provide a concise overviewRegarding algorithms, tree-based models, including ensemble tree models, and neural networks, predominantly Artificial Neural Networks (ANN), are the most commonly used modelling techniques.

?? Read more here: Machine Learning in Lithium-Ion Battery Cell Production: https://chemistry-europe.onlinelibrary.wiley.com/doi/full/10.1002/batt.202300046

A Guide to Data Preprocessing in ML ??

3 Steps to Model Training for Data Preprocessing in Machine Learning

In this blog post, we’ll cover the 3 basic steps to prepare your raw data for modelling:?

1. Data Structure – recommendations for organising your test results into a tabular format?

1. Data Exploration – methods for understanding your data and finding issues, such as outliers, gaps, or duplicates?

1. Data Preparation – Tools for cleaning, fixing, and transforming your data to address issues and prepare it for model training?

Monolith and About:Energy partner to accelerate development of next-generation EV batteries ??

Monolith and About:Energy, two of the UK’s leading EV technology start-ups, share a common vision for a dramatic reduction in EV development time, with the potential to speed up the R&D process by 12 to 18 months through AI-powered battery modelling.

To achieve this, engineers from both companies are working together to develop pre-trained AI models in the Monolith platform using precise, advanced battery data from About:Energy. Taking data from numerous batteries, these pre-trained models will enable more accurate, valuable predictions for battery degradation and thermal propagation – resulting in a lower number of tests, reduced testing costs, and improved battery performance and safety.

?? Read the announcement: https://www.aboutenergy.io/post/monolith-and-about-energy-partner-to-accelerate-development-of-next-generation-ev-batteries

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

If you’d like 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