MIT researchers have developed a method that uses artificial intelligence to adjust the 3D-printing process to correct errors in real-time. It basically consists of a machine-learning system that utilizes computer vision to watch the manufacturing process and then fix any issues that the AI detects in real-time.
By utilizing computer vision to watch the manufacturing process, simulations were able to be employed to train the neural network on how to adjust printing parameters to minimize error before they were applied to a real 3D printer. This means that it was not necessary to print thousands or millions of real objects to train the neural network. In the future, more novel materials can be incorporated into the prints, resulting in objects with special electrical or chemical properties. It’s only a matter of time until AI is used to 3D-print glass sculptures.
No products found.
This project is really the first demonstration of building a manufacturing system that uses machine learning to learn a complex control policy. If you have manufacturing machines that are more intelligent, they can adapt to the changing environment in the workplace in real-time, to improve the yields or the accuracy of the system. You can squeeze more out of the machine,” said Wojciech Matusik, professor of electrical engineering and computer science at MIT.
