One of the most important American artists of the 20th century, Jackson Pollock has played a decisive role in shaping contemporary art. Known for his abstract expressionism, he was an artist who stood out because of his drip painting technique. Pollock’s signature paint drips may seem like random splashes of paint, but the technique is much more controlled than what appears at first sight. Pollock constantly controlled the flow of paint and applied it to the canvas in measured amounts, and dripped colors onto the canvas in desired patterns with the help of gravity. Surprisingly, this approach has been used in a completely different field. Inspired by Pollock’s technique, scientists at Harvard University’s Soft Math Lab used the artist’s famous drip method in developing a novel 3D printing technology.
In extrusion-based 3D printing, the nozzle needs to be just a few millimeters away from the build plate to control the stability of the material flow and prevent printing errors. Because of fluid dynamics, liquids that fall from a great height tend to become more unstable as they fold or roll up into themselves. However, Pollock seemed to have control over this stream in his painting techniques. This characteristic prompted the Harvard research team to explore whether Jackson Pollock’s techniques could be employed to accurately and swiftly print intricate objects and shapes from a higher altitude.
“We aimed to develop a method that could harness the folding and coiling instabilities, rather than avoid them,” commented Gaurav Chaudhary, a member of the Harvard research group. In order to apply Jackson Pollock’s liquid ‘rope trick’ to 3D printing, the research group drew from the experience of the study’s leader, L. Mahadevan.
In a previous exploration, an Indian-American biologist and mathematician delved into the mathematical characteristics found in objects and substances such as insect wings, how fungi move and the formation of liquid droplets. He was the individual who, over two decades ago, provided an explanation and classification for Pollock’s techniques. The researchers thereby merged the disciplines of physics with artificial intelligence programming in order to apply Pollock’s method of drip painting to rapid, high-precision 3D printing.
This research effort did not have the objective of fabricating AI-driven Jackson Pollock art using algorithmic methodologies. Instead, the focus centered on the replication of the artist’s transmutational career technique and how that could be used in the additive manufacturing arena. The idea speculated that using this method might facilitate rapid, accurate 3D printing of complex structures that are further away from the 3D printing platform.
Chaudhary expounds, “Looking at traditional 3D printers, it can be observed that they are given a path from point A to point B, and the nozzle dutifully deposits ink along that pre-ordained path. But when observing Pollock’s methodology of tossing paint from an elevated position, it becomes apparent that even though his hand was moved in a particular pattern, the paint did not comply by strictly following that path. This was due to the acceleration provided by gravitational force. Even a minor change in movement could result in a broad scattering of paint. Implementing this technique allows for larger scale printing than pure movement would allow, all thanks to the free acceleration supplied by gravity.”
Pollock’s experiments with fluid dynamics in his projects are well documented. However, with the advent and proliferation of artificial intelligence, machines can now learn to mimic this style, leading to unique combinations and outcomes.
For successful printing, however, it is crucial to control dripping liquid from a greater distance through the nozzle of a 3D printer. To ‘teach’ the nozzle to do this, researchers relied on deep reinforcement machine learning. This is an algorithmic approach for iterative performance improvement. “With deep reinforcement learning, the model can learn from its mistakes and get more and more accurate with each trial,” says Chaudhary. Through this method, the nozzle repeatedly interacts with the environment with a viscous filament and improves its printing strategy based on the repeated results of the test.
A good visualization of this drip method is similar to how one puts icing on cookies. In fact, the researchers also decorated cookies with chocolate syrup and printed various complex shapes to test their method. Although only simple liquids were used in the study, the approach could be extended to liquid polymers, pastes and foodstuffs in the future and open up new horizons in 3D printing, according to the research team. “Harnessing physical processes for functional outcomes is both a hallmark of intelligent behavior, and at the heart of engineering design. This little example suggests, once again, that understanding the evolution of the first might help us be better at the second,” Mahadevan concluded. You can find out more about the Harvard project HERE.
What do you think about the Jackson Pollock-inspired 3D printing method under research at Harvard University? Let us know in a comment below or on our Linkedin, Facebook, and Twitter pages! Don’t forget to sign up for our free weekly Newsletter here, the latest 3D printing news straight to your inbox! You can also find all our videos on our YouTube channel.
“Why did the 3D printer go to therapy? Because it had too many layers of unresolved issues!”
0 Comments