3D printing has opened the door to a new universe of creations, both on a domestic and industrial scale. To advance the development of this technology, Researchers are testing new materials with different physical and mechanical propertiesHowever, this is a tedious and expensive task.
Since not all materials can be printed with the same parameters, experts often resort to trial and error. As you can imagine, this consists of making thousands of impressions to find the ideal parameters for this new material to pass the tests and perform its function.
Now, a research team from MIT says artificial intelligence could help improve this process. The main benefits are: Avoid the need to create thousands of test prints and consequently reduce the cost of researching new 3D printing materials, which could lead to projects that were previously impossible.
In a 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, resulting in a much more accurate final printed version.
Improving 3D printing with AI
To formulate this proposal, the researchers began developing a artificial vision system with cameras aimed at the nozzle of the 3D printer. When the printer begins its work, the system measures the thickness of the material based on the amount of light passing from one side to the other.
In parallel, they used reinforcement learning to train an artificial intelligence model through the trial and error process normally performed when testing new materials, but of course all of this took place in a simulation environment without any money being spent on it had to be a huge amount of materials.
As the model took more simulated impressions, it learned and updated to make an increasingly accurate impression. The next step, rough, was to blame the 3D printer for the model, receiving data in real time thanks to the artificial vision system mentioned above.
The researchers say that when they tested this system, the impressions were more accurate than any other method. “It performed particularly well in infill printing, which is printing on the inside of an object,” they note. In other words, the system was able to calculate the exact amount of material to use and correct itself during the process.
However, they assure that this solution tit is not yet ready to be used in the real world, where the 3D printing scenarios are not finely arranged like in a laboratory. Now the researchers are working on adding “noise” to the process for more realistic results.
However, the application of this type of solution has yet to be tested on complex multi-layer prints or multiple 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, although it certainly has to evolve.
In Xataka | Why build a house when you can 3D print it: They’re already being sold in the United States