A machine learning tool is being developed by Purdue University to increase the accuracy in additive manufacturing. The resulting research could increase precision and reduce testing time.
“We’re really taking a giant leap and working on the future of manufacturing,” said Arman Sabbaghi, an assistant professor of statistics in Purdue’s College of Science, who led the research team at Purdue with support from the National Science Foundation.
“We have developed automated machine learning technology to help improve additive manufacturing. This kind of innovation is heading on the path to essentially allowing anyone to be a manufacturer.” Additive manufacturing like 3D printing has changed the way many products are made and assembled.
But an ongoing issue has always been accuracy, especially when it comes to parts that need to fit together with extreme precision. The new technology addresses this downfall.
Easy tool to improve accuracy and consistency
The software developed by Purdue uses machine learning to analyze the user’s product data and create plans to manufacture the needed pieces with greater accuracy. "This has applications for many industries, such as aerospace, where exact geometric dimensions are crucial to ensure reliability and safety,” Sabbaghi said.
“This has been the first time where I’ve been able to see my statistical work really make a difference and it’s the most incredible feeling in the world.” Additive manufacturing or 3D printing has gone from a conceptual idea to an essential product in a short amount of time.
Individual components are printed from a base layer. It has many benefits over traditional manufacturing processes that include advanced shape complexity, waste reduction, and potentially less expensive manufacturing.
Additive manufacturing on the rise
The latter is particularly applicable to manufacturing processes that involve beginning with a block of raw material and deducting from it until the desired shape is created. The new software improves the accuracy of the parts being printed so that they are within the needed tolerances as well as increasing the consistency so that they all perform the same, no matter when they were printed.
“We use machine learning technology to quickly correct computer-aided design models and produce parts with improved geometric accuracy,” Sabbaghi said. The technology increases the complexity of designs not otherwise able to be created with traditional manufacturing processes.
Wohlers Associates estimates that additive manufacturing is a $7.3 billion industry. The industry is only going to expand as technology improves. Additive printing is even being used on the Ineternational Space Station.
Astronauts are able to print tools they need as well as use printers within the scope of experiments. Improving the accuracy of printers could increase their use in the development of highly precise manufacturing process such as spacecraft.