Maximising the Value of Test Campaigns Using AI | A Fuel Cell Case Study
Validating intractable physics of complex, non-linear systems, such as fuel cells, is time-consuming and costly. It's not feasible to test every possible scenario and yet over-testing confirms what's already known while under-testing risks failing certification or missing issues.
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 behavior 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 make efficient use of testing times in expensive test facilities
- Understand the impact of test conditions and know which test conditions are most important to vary from one test to the next
- Use interactive prediction features to explore next tests to run.
Who should watch?
- Identify the benefits of using a standardised test data set for training AI models.
- Understand how to train an AI model using specific inputs and outputs, such as current density, pressure, and relative humidity as inputs and cell voltage as an output.
- Evaluate the use of a random forest model for predicting outcomes of subtests in advance.
- Test engineers who want to predict the outcome of a new test, to know whether it’s worth conducting it.
- Engineers involved in product validation and certification.
- Engineers and R&D leaders who want to understand the potential benefits of implementing AI.
- Engineers from the automotive and aerospace industry, as well as industrial markets.
- Business leaders who want to learn about the latest trends in AI in automotive, aerospace, and industrial markets.