Monolith software is trusted by the world’s top engineering teams including Rolls Royce, Siemens, Honeywell, and BMW to develop better quality products in half the time. Backed by one of world’s largest software investors and recognized by Gartner as a Cool Vendor for AI in Automotive, Monolith AI empowers engineering domain experts in automotive, aerospace and industrial markets to reduce expensive, time-intensive testing, lower risks to product performance and quality, and cut product development time. Featured in Forbes magazine and named one of the UK’s top 100 startups, Monolith AI founder Dr. Richard Ahlfeld received his PhD in Aerospace Engineering from Imperial College and was named to MIT Technology Review’s Top 10 Innovators under 35. Monolith AI is headquartered in London with global enterprise clients worldwide.

In the fast-paced electric vehicle (EV) market, testing batteries has become a significant bottleneck, hindering the timely launch of EVs. The escalating demand and intense competitive pressure to enhance the range and charging times compound this challenge exponentially.

Real-world data from a study conducted by Toyota, MIT, and Stanford demonstrates that AI can reduce testing efforts by a remarkable 98%. (Source: https://news.stanford.edu/2020/02/19/machine-learning-speed-arrival-ultra-fast-charging-electric-car/)

Monolith CEO Dr. Richard Alhfeld will explain and demonstrate how you can achieve these same results. 

Additionally, during the session, Dr. Ahlfeld will discuss how 3 major challenges faced by EV manufacturers can be strategically solved with AI:
– Early Stopping of Tests: Predicting battery failure after a certain number of cycles for efficient testing
– Lifetime Prediction of Batteries: Ensuring optimal performance and reliability by accurately estimating battery lifetimes
– AI-recommended Test Planning: AI-based models act as a "next test recommender" to identify the tests that provide maximum information gain with human-in-the-loop oversight

Reducing EV Battery Testing by 70%: How AI Solves 3 Key Obstacles

The complexity of EV batteries, which involves electrical, chemical, and thermal mechanisms, leads to a costly and time-consuming process for their testing and validation.

In the first part of the EV webinar series (https://www.monolithai.com/webinars/ev-battery-testing), we reviewed the latest research on using AI models to reduce the testing needed for EV batteries significantly.  This follow-up webinar will show how to implement these concepts using Monolith software.  

Monolith Lead Principal Engineer Dr. Joël Henry will demonstrate how to train a model using the latest active learning techniques to characterize battery performance in much fewer test steps than traditional approaches. During the demo, Dr. Henry will explore how to overcome common challenges in EV battery testing: 

– Learn how to define your experiment design to achieve optimal design space coverage, including using 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.

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

Dr. Richard Ahlfeld, Monolith CEO, will discuss Machine Learning in engineering tests. He'll compare physics-based and data-driven models using a battery test case study. He'll show how Machine Learning can complement physics-based approaches and validate complex systems.

Testing every possible scenario is impractical. Over-testing confirms known information, while under-testing risks missing issues. Physics-based models used in engineering tests have limitations in dealing with uncertainties and non-linearities. Optimizing design parameters through experiments is time-consuming, as in the case of the battery test study.

Monolith has developed an early-prediction model called the "Next Test Recommender" to provide engineers with active recommendations for the exact best test conditions to choose from for the next batch of tests. The model ranks the most impactful new tests to carry out based on an analysis of previously collected data.

This approach substantially reduces the time and the number of experiments required, and it replaces traditional exhaustive search methods that would take over 500 days with just 16 days (equivalent to 384 hours). Consequently, the Next Test Recommender has proven to be highly effective in reducing the time and resources needed for testing.

Check out the entire 'Artificial Intelligence and Machine Learning for Manufacturing'  online seminar from NAFEMS here: https://www.nafems.org/events/nafems/2023/artificial-intelligence-and-machine-learning-for-manufacturing/

Physics-Based vs. Data-Driven Methods to Accelerate Battery Test Cycles

Validating complex, non-linear systems can be difficult. It's not possible to test every possible scenario on a test bench or simulation. Over-testing only confirms what is already known, while under-testing can risk failing certification or missing issues. 

Active learning uses machine learning to help engineers create testing plans more efficiently in automotive and aerospace product development.

Monolith has created a new feature, the Next Test Recommender (NTR), which enables users to train and assess machine learning models. It offers valuable recommendations for optimal test conditions to apply in the next round of testing. NTR assesses previously gathered data to suggest the most effective new tests to conduct. 

Join Dr. Joel Henry, Dr. Gareth Jones, and Jousef Murad for a discussion on how Monolith AI software enhances test engineers' capabilities to iteratively optimise their test campaigns by maximising the value derived from the time allocated to a test campaign or by reducing the time taken to achieve a certain quality of testing.

This knowledge and human-in-the-loop design empower engineers to make informed decisions, optimise their test plans, and keep responsibility for continuously improving the final product's safety, quality, and reliability.

In this webinar, you will learn about:

– Optimising test campaigns for efficient resource allocation and improving testing quality.
– Leveraging machine learning models to make data-driven decisions.
– The benefits of using Monolith AI software.

AI-Powered Test Plan Optimisation: Predicting Next Tests in Engineering

Join us for this webinar, where we announce the release of our optimised time series models. In this session, we'll explore the exciting potential and untapped opportunities that series data offer compared to conventional structured tabular data. A live Monolith platform demo will showcase our cutting-edge features, highlighting the transformative applications in industries such as Automotive and Energy.

In this webinar, you will:

- Understand the unique challenges and opportunities presented by time series data
- Gain insights into Monolith AI's advanced time series model and its key differentiators
- Explore the diverse applications of time series models beyond traditional use cases

Learning objectives: 

- Announce the release of our time series models in an informative manner.
- Educate attendees on the additional complexity and opportunities of series data.
- Demonstrate the Monolith AI platform through a live demo.

The Power of Time Series Models in 15 Minutes: A Deep Dive into Monolith

Join us for a new webinar on Artificial Intelligence (AI) applied to battery testing. This session will showcase the potential for test engineers by demonstrating how to explore effectively, quickly, and easily build an AI-based solution with real battery test data to increase test plan efficiency. Through a live Monolith software demonstration, participants will gain practical insights into the following key aspects: 
 

- Loading and Exploring Battery Data: Learn the essential steps to load and explore battery data efficiently, laying the foundation for insightful analysis. 

- Model Training from Test Data: We'll give you step-by-step instructions on training AI models using your test data, empowering you to harness the predictive capabilities of AI.
 
- Choosing the Right AI Algorithms: Explore diverse methods to evaluate AI models, enabling you to identify the best-fit models for your unique testing requirements. Understand how to determine the most suitable AI algorithms for your specific battery data, ensuring optimal model performance. 

- Predictive Battery Performance: Discover how AI models can be used to make accurate predictions of battery performance, enhancing the efficiency of testing processes. 

- Model Sharing for Collaborative Use: Learn strategies to share your AI models for broader collaboration, fostering a community-driven approach to battery testing innovation. 

- Optimising Test Plans with AI: Uncover the impact of AI models on optimising test plans, maximising efficiency, and ensuring comprehensive testing coverage.

Predictive Insights From Battery Test Data

Using Monolith, customers such as Jota Sport are overcoming the tedious, time-intensive, and repetitive engineering approach that they previously utilised during testing. 

Rather than trying to hard-code all of the equations and making sure to embed all the physics of a given system, Jota instead feeds the self-learning model using real-world test data to learn from real-world performance, which can be taken from track or wind tunnel testing. 

Using self-learning models is the best way to infer the physics, quickly understand, and instantly predict what design parameters are affecting vehicle performance.

AI for Track Dynamics | Monolith

Using self-learning models, engineers can explore how their complex system performs under more operating conditions and design parameters to improve product quality while shortening development time.

Artificial Intelligence to Reduce Wind Tunnel Testing | Monolith

Engineers aim to use the best technology available to get the most from their data; with the ultimate goal being to understand physical relationships, increase product performance, while simultaneously reducing test times.

Monolith provides a new AI solution enabling engineers to build self-learning, intelligent models to reduce the amount of testing typically needed to build and validate quality products faster. Surrogate models are an essential engineering tool. Their popularity has recently increased due to the high cost of evaluating real-world simulations alongside real-world testing.

This webinar explains how engineers can use Monolith to quickly understand and instantly predict performances or new composites, while reducing testing time. Engineers are able to use a mixed-categorical data-driven approach for predictions and optimizations of hybrid discontinuous composites performance. Additionally, Monolith allows engineers to easily: predict results, understand relationships, understand sensitivities between input parameters and their component/product performance, and leverage their past test experience and datasets.

Accurate & Efficient Self-Learning Models for Composite Materials

During a Le Mans race, the Jota engineering team produces 7,500 data points per second – and, as you might know, the race lasts 24 hours. Attempting to analyze billions of data points in real-time to win the world’s most competitive car race is just the start of Jota’s challenges.

With only seconds separating those who take the podium from other competing teams, the winning edge comes down to engineering ingenuity – and the visionary use of technology.

This case study goes behind the scenes to explore how an unlikely team from Kent won Le Mans with a combination of AI, self-learning models, and engineering ingenuity. Inside, discover the lessons your business can learn from Jota’s AI success story.

Case Study: AI leading the way to Le Mans win

Validating the intractable physics of complex, non-linear systems, such as fuel cells, is time-consuming and costly. Testing every possible scenario is not feasible, yet over-testing confirms what's already known while under-testing risks failing certification or missing issues.  

Join Monolith engineers Arnaud Doko and Jousef Murad to discuss how the AI software enhances test engineers to reduce validation time while significantly increasing learning from each test.

In this session, engineers will learn how to train and evaluate machine learning models, receive recommendations for the next tests to perform, and optimise the testing process overall.

The featured dataset contains Nafion 112 membrane standard tests and MEA activation tests for PEM fuel cells in various conditions. The data provides insight into fuel cell behaviour during different tests and conditions, making it useful for analysis, simulation, and material performance investigation in PEM fuel cell research.

In this webinar, you will learn how to:

– Predict a new test's outcome ahead of time.
– Leverage your test data to train and evaluate AI models to efficiently use testing times in expensive test facilities.
– Understand the impact of test conditions and know which are most important to vary from one test to the next. 
– Use interactive prediction features to explore the next tests to run.

Maximising the Value of Test Campaigns Using AI | A Fuel Cell Case Study

Machine Learning

Artificial Intelligence

Engineering

Battery

Fuel Cell

The application development community features top thought leadership focusing on optimal practices in software development, SDLC methodology, mobile app development and application development platforms and tools. Join top software engineers and coders as they cover emerging trends in everything from enterprise app development to developing for mobile platforms such as Android and iOS.

Application Development

As an IT professional, many of the problems you face are multifaceted, complex and don’t lend themselves to simple solutions. The information technology community features useful and free information technology resources. Join to browse thousands of videos and webinars on ITIL best practices, IT security strategy and more presented by leading CTOs, CIOs and other technology experts.

Maximising the Value of Test Campaigns Using AI | A Fuel Cell Case Study

Presented by

About this talk

More from this channel