Next Test Recommender software upgrade provides engineers with ranked selection of the most impactful validation tests to run
Artificial Intelligence (AI) specialists at Monolith have been working on a product update for the company’s engineering software. The update has been called “Next Test Recommender (NTR)”, a new technology, which is currently only available in beta format in the no-code AI platform built for engineering domain experts. NTR gives active recommendations on the validation tests to run during the development of hard-to-model, nonlinear products in complex automotive, aerospace and industrial applications.
As the physics of complex products in these industries become more and more intractable to understand, engineers find themselves in a dilemma, either conducting excessive tests to cover all possible operating conditions or running insufficient tests that risk the omission of critical performance parameters. NTR, powered by the company’s proprietary active learning technology, aims to optimise this trade off by providing test engineers with active recommendations, in ranked order, of the most impactful new tests to carry-out for their next batch of tests, to maximise coverage and optimise time and cost.
According to Dr Richard Ahlfeld, CEO and Founder of Monolith, throughout the development process of the new upgrade, the company’s specialists worked alongside existing users of its engineering software to understand how they would use an AI recommender system as part of their test workflow. The company wanted to understand why they had not yet adopted such tools despite the well-known potential of AI to more quickly explore high-dimensional design spaces.
“We found that existing tools didn’t fit their safety needs and did not allow test engineers to incorporate their domain expertise into the test plan or influence the AI recommender. As a result of this, our research and development team has been working for months on this robust active learning technology that powers Next Test Recommender and we’re pleased with early results and feedback, with even better results expected as the technology matures,” Ahlfeld says.
NTR works for any complex system for which engineers are trying to safely explore the design space, such as aero map analysis for racing cars or flight safety envelopes of aeroplanes where engineers are trying to find where gusts or eigenfrequencies cause issues. The use of AI is essential in being able to overcome such complex physics challenges in safety critical applications.
Another growing area is in powertrain development, such as battery or fuel cell cooling system calibration. In the latter use case, an engineer trying to configure a fan to provide optimal cooling for all driving conditions had a test plan for this highly complex, intractable application that included running a series of 129 tests. When this test plan was inserted into NTR, it returned a ranked list of what tests should be carried out first.
Out of these 129 tests, the NTR software upgrade recommended that the final test in the batch (test number 129) should actually be among the first 5 to be run and that a total of just 60 tests out of those originally envisaged would be sufficient to be able to characterise the full performance envelope of the fan, representing a 53% reduction in testing with associated cost and time to market benefits.
Human in the Loop
A number of open-source AI methods are already in existence but these don’t allow the engineer to influence the test plan. However, Monolith believes that this is a critically unique aspect of NTR, which provides the means for “human-in-the-loop” inspection of the selected experiments, granting a domain expert user oversight of the system and combining their expertise and domain knowledge with the power of machine learning without any knowledge of AI or coding.
A recent Forrester Consulting study, commissioned by Monolith, found that 71% of engineering leaders need to find ways to speed product development to stay competitive and the majority (67%) also feel pressure to adopt AI. Remarkably, those who have are more likely to achieve increased revenue, profitability and competitiveness for their employers.
By making use of AI and machine learning in the verification and validation process of product development, especially for highly complex products with intractable physics, engineers can extract valuable insights, optimise designs and identify crucial performance parameters accurately. The result is enhanced operational efficiency and streamlined testing procedures, ultimately speeding time to market and strengthening competitiveness.
No-Code Software for Engineering Domain Experts
Monolith is a no-code AI software platform that has been specifically built for use by domain experts so that they can make use of the power of machine learning with their existing, valuable testing datasets to speed product development.
Self-learning models within the engineering software analyse and learn from test data to understand the impact of test conditions and predict a new test’s outcome ahead of time. The ability to attain active next test recommendations will further enable engineering teams to reduce costly, time-intensive prototype testing programmes and develop higher-quality products in half the time.