A research team led by Bill King, Professor of Mechanical Engineering at the University of Illinois Urbana-Champaign, has developed a method that allows 3D-printed components to be clearly assigned to the machine on which they were manufactured. This is based on an artificial neural network that recognizes microscopically fine, machine-specific features on the component surface – so-called manufacturing fingerprints.
As part of their investigations, the researchers discovered that even identical 3D printers with identical settings produce systematically different surface patterns. These differences can hardly be seen with the naked eye, but are detectable in high-resolution photographs. The AI model was trained using images of over 9,000 components produced on 21 machines from six different manufacturers and using four different additive processes. A surface section of just one square millimeter was enough to identify the machine with 98 percent accuracy.
“We are still amazed that this works: we can print the same part design on two identical machines –same model, same process settings, same material – and each machine leaves a unique fingerprint that the AI model can trace back to the machine,” King said. “It’s possible to determine exactly where and how something was made. You don’t have to take your supplier’s word on anything.”
“Modern supply chains are based on trust,” King said. “There’s due diligence in the form of audits and site tours at the start of the relationship. But, for most companies, it’s not feasible to continuously monitor their suppliers. Changes to the manufacturing process can go unnoticed for a long time, and you don’t find out until a bad batch of products is made. Everyone who works in manufacturing has a story about a supplier that changed something without permission and caused a serious problem.”
The technology has a wide range of possible applications. In an industrial context, manufacturers can use it to check whether suppliers are complying with agreed machines and processes. Particularly in safety-critical applications in aerospace, medical technology or automotive engineering, this type of traceability offers additional protection against unintentional or unauthorized changes in the manufacturing process.
“These manufacturing fingerprints have been hiding in plain sight,” King said. “There are thousands of 3D printers in the world, and tens of millions of 3D printed parts used in airplanes, automobiles, medical devices, consumer products, and a host of other applications. Each one of these parts has a unique signature that can be detected using AI.”
“Our results suggest that the AI model can make accurate predictions when trained with as few as 10 parts,” King said. “Using just a few samples from a supplier, it’s possible to verify everything that they deliver after.”
The study was published in the journal Advanced Manufacturing and shows that machine-specific features have been hidden in millions of 3D-printed products for years – and can now be made accessible with AI.
Metal Binder Jetting: The Key to Efficient Tool Manufacturing? - Exclusive Insights from INDO-MIM
Fill out the form and get instant access to an exclusive webinar on HP's Metal Binder Jetting 3D printing technology with exciting insights from INDO-MIM.Subscribe to our Newsletter
3DPresso is a weekly newsletter that links to the most exciting global stories from the 3D printing and additive manufacturing industry.
