3D printing has opened the door to a whole new world of creations, both on a domestic scale as on an industrial scale. To promote the development of this technology, researchers are testing new materials with different physical and mechanical propertiesHowever, this is an arduous and costly task.
Since not all materials can be printed with the same settings, experts often resort to trial and error. As you can imagine, this consists of making thousands of impressions in search of the ideal parameters for this new material to pass the tests and perform its function.
Now, a research team from MIT claims that the artificial intelligence could help to improve this procedure. The advantages mainly consist of avoid having to make thousands of test prints and, therefore, reduce the costs of researching new 3D printing materials, which could lead to projects that were not possible until now.
In one study published in the online archive arXiv, The researchers explain that it is possible to train a machine learning model to dynamically monitor and adjust the 3D printing process. Thus, the parameters are calculated in real time, obtaining a much more precise final printed version.
Improving 3D printing with AI
To shape this proposal, the researchers began by developing a artificial vision system with cameras aimed at the nozzle of the 3D printer. When the printer begins to do its job, the system measures the thickness of the material based on the amount of light passing from side to side.
At the same time, they used reinforcement learning to train an artificial intelligence model through the process of trial and error, like that which is usually done when testing new materials, but of course, all of that comes together. unfolding in a simulation environment without needing to spend a huge amount of materials.
As the model made more simulated impressions, it learned and updated to make an increasingly accurate impression. The next step, more or less, was to leave the 3D printer in charge of the model, which received real-time data through the computer vision system mentioned above.
The researchers say that when they tested this system, the fingerprints were more accurate than any other method. “It worked particularly well in infill printing, which prints the interior of an object,” they note. In other words, the system was able to calculate the exact amount of material to use and correct itself in the process.
However, they assure that this solution tit is not ready for real world use yet, where 3D printing scenarios are not finely arranged like in a lab. Now researchers are working on adding “noise” to the process to provide more realistic results.
But the application of this type of solution has yet to be tested in complex multi-layer prints or several materials printed at the same time. In any case, the progress seems promising and the researchers assure that the effectiveness of this technique has been demonstrated, even if, of course, it must continue to evolve.
To Xataka | Why build a house when you can print it in 3D: in the United States we are already starting to sell them