3D printing with artificial intelligence will be the next new technology
Researchers at Washington State University have announced the development of a new 3D printing technology that could improve the design and manufacturing of complex devices, such as prosthetics, flexible electronics and wearable biosensors.
What does 3D printing technology depend on?
The new technique uses a machine learning algorithm to determine the best 3D printing settings needed to produce accurate models of human organs, such as the kidney and prostate. The researchers were able to produce 60 successive versions of these models, each one better than the last. This new technique could help save time, cost and effort required for design and manufacturing, said Kayan Qiu, one of the authors of the study published in the journal Advanced Materials Technologies.
3D printing is widely used in various industries, where engineers can transform digital designs into various physical products, such as wearable devices, batteries, and aircraft components. However, determining the correct settings for 3D printing can be a difficult and time-consuming process. Engineers must choose the right materials, printer configuration, and jet pressure, all of which affect the final result. The number of possible combinations of settings is enormous, and each attempt costs time and money, said Jana Doba, one of the study’s authors.
When will 3D printing technology be available?
Chiu has been researching for several years to develop complex 3D models that resemble human organs. These models can be used to train surgeons or evaluate implantable devices, but the models must include the mechanical and physical properties of real organs, including veins, arteries, ducts, and other detailed structures.
Chiu, Doba, and their students used an AI technique called Bayesian optimization to train the algorithm and find the optimal 3D printing settings. After training it, the researchers were able to optimize three different goals for the organ models: geometry accuracy, weight or porosity, and printing time. Porosity is important for surgical practice, as the mechanical properties of the model can change depending on its density.
“It’s difficult to balance all the objectives, but we were able to strike a proper balance and achieve the best possible print quality, regardless of the type of printing or the shape of the material,” said Eric Chen, one of the study’s authors. Allalt Ahmadian, one of the study’s authors, added that the researchers were able to look at all the objectives in a balanced way to get positive results, and that the project benefited from her interdisciplinary perspective.
“It’s very rewarding to work on interdisciplinary research by doing actual lab experiments to make a real-world impact,” she said. The researchers first trained the computer program to 3D print a surgical model of the prostate. Because the algorithm is generally generalizable, it can be easily changed with small adjustments to print a model of the kidney. “This means that this method could be used to manufacture other, more complex medical devices, and even in other fields,” Chiu said. The work was funded by the National Science Foundation, the WSU Startup Foundation, and the Cougar Cage Funds.
Read also: Apple's robot will be the next personal assistant