Monolith AI and Imperial College London have received £500,000 funding from Innovate UK to build an artificial intelligence solution that will assess the manufacturability of metal components.
Computer-Aided Engineering (CAE) simulations have improved the assessment of the manufacturability of industrial products such as car doors, but the final decision is still limited to the assessment of a small number of domain experts who must assess simulation results.
For example, it is known from medical image processing used to diagnose lung cancer that machine learning models can provide a very accurate assessment for new patients when trained with enough data. Knowing the final prediction isn’t enough, though — doctors need to understand why and where the AI algorithm detected cancer. The same goes for technical applications.
The goal of the project, led by Dr Joël Henry of Monolith AI, is to build a new version of explainable AI that will provide engineers with clear feedback on how it came to its conclusions, making it “black box”- dilemma is removed.
MORE AI NEWS FROM THE ENGINEER
monolith AI and Imperial College London aims to streamline the manufacturing process and provide a new competitive advantage to high-volume manufacturers by using AI to learn from what could be manufactured in the past and predict what will be best for new components. This would allow engineers to build expert simulations based on repetitive tasks and historical data.
The platform will be developed and evaluated by multiple industry partners over the course of 18 months. If successful, researchers believe the CAE could ‘revolutionize’ the manufacturing industry and enable engineers to perform complex manufacturability assessments in seconds instead of weeks. This could then free up technical skills for the most complex value-added tasks.
“CAE has done a fantastic job advancing component manufacturing, but there are still many areas where physical simulations still fail to capture the true complexity of components,” said Dr. Richard Ahlfeld, CEO and founder of Monolith AI.
“Large engineering companies collect a lot of data when assessing manufacturability and our goal is to make that data work to their advantage. This latest funding allows us to explore this opportunity and advance not only the automotive industry, but other sectors as well.”