How Machine Learning Will Unlock The Future of 3D Printing

Remember how, just five years ago, it seemed like 3D printing was going to take over the world? How it seemed like we’d have 3D printed cars that we’d be parking in our 3D printed houses? Things didn’t seem to work out so much. But even while the hype died, companies have been steadily working on the technology.


Two years after Autodesk announced a plan to 3D print an entire steel bridge designed by Joris Laarman, the project really is going forward, with anticipated completion at the end of the year. Autodesk agreed to share an exclusive update with Co.Design. What’s fascinating is how much things have evolved, how many problems have been conquered—and where the project goes from here.

A Case Study For Industrial Applications 

The bridge is really just a proof of concept for printed steel applications that range from shipbuilding to off-shore oil rigs. Getting there will require not just better software, but robots that can teach themselves how to get better at 3D printing. “We’re now making huge steps in the volume of object that can be printed. That’s going to create a significant leap in adoption,” says Gijs van der Velden, who runs MX3D, a startup spun off from Joris Laarman Lab that’s dedicated to commercializing large-scale steel printing.

Bridge Design [Photo: Joris Laarman Lab]When Laarman first dreamed up the bridge, it was supported by a lattice of struts that branched like an ice crystal. It was to be installed across a canal near Amsterdam’s historical Red Light district. But the bridge has changed radically, for one simple reason: The city found that the design stressed the walls of the canal, and so had to be reengineered. The bridge that’s being printed now more resembles a typical pedestrian structure, though the surface and form still bend and twist fantastically, in a way that could only be done with 3D printing. And that’s the point: To show all kinds of would-be partners what’s possible.

[Photo: Olivier de Gruijter]The challenge is printing big pieces. You might think that would be a hardware problem—a matter of making better robots—but it’s actually more about software. All along, the idea has been to use off-the-shelf industrial robots, so that a client could literally order the robots, get them in three weeks later, and then use MX3D’s software to print whatever they like. It’s complicated to get those robots to weld something that has all the physical properties required of a high-performance part.


When steel melts, its physical properties change. Constant reheating makes it brittle. That means that you can’t simply build up a 3D printed steel structure like you can with plastic, applying one layer of goop at a time. As the successive layers of steel are applied, they reheat the layers below. If those have been only recently applied, they get weaker. Conquering that challenge means an entirely different printing strategy. As different areas cool, the steel has to be built up in what look like random patterns. A robot that’s 3-D printing with steel looks less like a spider spinning a web—and more like a spider spinning a web while tripping on acid. Because the printer is no longer waiting for steel to cool in a particular spot, the printer itself can work twice as quickly.

[Photo: Olivier de Gruijter]But then things get even more complicated. Intricate 3D geometries are by definition bespoke, so it’s hard to know in advance where the machine will have trouble creating strong welds. This is where machine learning can help. The industrial robots that MX3D uses already have sensors that detect how much current is being used to heat up the metal, how hot that metal gets, and where exactly the welds are being applied. MX3D is working on the next phase: combining that data with machine learning algorithms to help the robot learn what welds are likely to pose problems—and either address those problems in real time, or avoid them altogether, coming up with new patterns of movement that allow each layer to build up properly. “When you’re making the file for printing, the big issues will be resolved,” explains van der Velden. “When you’re actually printing, the machine will recognize a problem and create a solution on the fly.”

GradientScreen [Photo: Joris Laarman Lab]He concedes that 3D printing steel won’t be useful in 95% of industrial building projects. In those cases, simple structures are all that’s needed. But the remaining 5% is a huge market. For example, the steel support structure for an off-shore oil rig incredibly difficult to engineer. Instead of having a team of builders create a single part, you might have two engineers keeping watch over eight robots. Moreover, one of the most time-consuming steps in making pieces for a huge project such as an oil rig is shaving critical parts down, to save whatever weight you can. Reducing a 6,000 kilo part to 5,000 kilos can mean renting an entirely different sort of crane for installation, at a dramatically lower cost. 3D printing such a part, with an intricate interior structure where all the weight has already been reduced, might stand to reduce weight by 50% while requiring no extra shaving work. The same goes with large, high-performance parts such as the rotor on a cargo ship. Massive energy savings would result from a piece the looks the same on the outside but has been optimally hollowed out on the inside.

Which brings us back to the bridge. It’s meant to be marketing for MX3D; Autodesk, which makes the software; and a dozen other partners who’ve lent millions of dollars in resources to develop the technology. While the bridge looks cool on the outside, that surface is really meant to show what’s possible inside giant pieces of equipment that haven’t changed much in decades. “It’s not going to be a magical way of producing everything,” says van der Velden. “But we’ll find really important new parts to print.”

Australian Scientists Are Behind The World's First 3D Printed Shin Bone Implant

Image: iStock

Queensland University of Technology research and technology is behind the first ever 3D-printed shin bone implant.

The procedure was performed on a Gold Coast man who lost bone lost through an infection.

QUT’s Distinguished Professor Dietmar W Hutmacher is director of the ARC Industrial Transformation Training Centre in Additive Biomanufacturing that is at the frontier of 3D printing in medicine.

“Additive Biomanufacturing is an emerging sector within Advanced Manufacturing and the technology allows us to 3D print scaffolds, customised to the patient, which are then slowly resorbed by the body and guide the new bone formation,” Professor Hutmacher said.

QUT’s research team, including Dr Marie-Luise Wille, Dr Nathan Castro and PhD student Sebastien Eggert, worked closely with Dr Michael Wagels, the Princess Alexandra plastic surgeon who performed the surgery.

The team firstly developed a computer model, 3D printed a series of physical models of the large bone defect from CT scans of the patient’s tibia bone, and then designed a patient-specific implant – in the form of a highly porous scaffold which will guide the regeneration of the new bone.

The QUT team used a 3D printer from the Queensland-based company 3D Industries to print the models. The final scaffold design was sent to Osteopore International, who have been making biodegradable scaffolds for ten years now.

And this is just the beginning for QUT’s 3D printing endeavors.

Professor Hutmacher and Dr Wagels have started an innovative PhD training program which is partially funded by the PA Research Foundation in which young surgeons are trained and perform cutting-edge research in 3D printing in medicine to meet Australia’s need to build capacity in key areas of economic importance.

“Next to the ambition to deliver outstanding fundamental science and engineering, from a business and human capital perspective, my vision for the ARC ITCC in Additive Biomanufacturing is to deliver an exceptionally talented group of entrepreneurs who will start high-impact companies,” he said.

“They will have their roots in globally competitive fundamental and applied STEM research as well as in manufacturing innovation and new medical devices.”

New to forum and 3d printing

You’re going to have a blast! By the way, white filament is great for lithophanes. 🙂

Buying a 3D printer is a lot like buying an auto back in 1913. You have to do the repairs yourself, and there can be some frustration and jury-rigging, but when it’s running sweet…

Watch out for the little spring clips that hold the fan shroud to the hot end. They tend to fly off

when trying to remove them or put them back on. In a pinch, bent paperclips, plastic ties, or chewing gum (kidding) will hold them until you print replacement clips.

Suggestions for first mods… glass plate (3/32″ thick, from Lowes, etc) and replacing the 30mm fan with a 40mm.

Have fun!

Teachers learn 3D printing at Edmonds CC

Javascript is not enabled.

Javascript must be enabled to view HeraldNet online content. Please enable your javascript and click the link below to return. If you are unsure how to enable JavaScript in your web browser, please view these instructions.


Degrade On Demand: Brown University Researchers Create Dynamic 3D Printing Biomaterials

Pin It

We’ve seen 3D printable biomaterials before, but never any like the ones engineers at Rhode Island-based Brown University have been working on. They have developed a technique to make 3D printed biomaterials that are able to quickly degrade on demand. The research team made the degradable structures, which could have applications in making dynamically changing cell cultures and microfluidic devices with detailed patterns, using a stereolithography (SLA) 3D printing process. A biocompatible chemical trigger is used to degrade away the temporary structures.

Ian Wong, an assistant professor with Brown’s School of Engineering, explained, “It’s a bit like Legos. We can attach polymers together to build 3-D structures, and then gently detach them again under biocompatible conditions.”

[Image: Wong Lab, Brown University]

Wong and the other researchers wanted to work on making structures with ionic bonds that could be reversible, which has never been accomplished before with light-based 3D printing – SLA typically uses photoactive polymers that link together with strong, but irreversible, covalent bonds. The team used precursor solutions with sodium alginate, which is a compound derived from seaweed. Alginate, which can manage ionic crosslinking, has been combined with 3D printing technology before to fix bone defects, to improve hydrogel 3D printing, and to treat microtia; now, the team from Brown has shown that the compound can be used with SLA printing.

“The idea is that the attachments between polymers should come apart when the ions are removed, which we can do by adding a chelating agent that grabs all the ions. This way we can pattern transient structures that dissolve away when we want them to,” said Wong.

They also used multiple combinations of ionic salts, like barium, calcium, and magnesium, to make structures that had different levels of stiffness, which could be dissolved at various rates. The researchers published a paper on their work, titled “Stereolithographic Printing of Ionically-Crosslinked Alginate Hydrogels for Degradable Biomaterials and Microfluidics,” in the journal Lab on a Chip; co-authors include Thomas M. Valentin, Susan E. Leggett, Po-Yen Chen, Jaskiranjeet K. Sodhi, Lauren H. Stephens, Hayley D. McClintock, Jea Yun Sim, and Wong. The Department of Education, the National Institutes of Health (NIH), Brown University’s Hibbitt Postdoctoral Fellowship, and the Center for Cancer Research and Development at Rhode Island Hospital all supported the Brown University team’s research.

The abstract explains, “3D printed biomaterials with spatial and temporal functionality could enable interfacial manipulation of fluid flows and motile cells. However, such dynamic biomaterials are challenging to implement since they must be responsive to multiple, biocompatible stimuli. Here, we show stereolithographic printing of hydrogels using noncovalent (ionic) crosslinking, which enables reversible patterning with controlled degradation. We demonstrate this approach using sodium alginate, photoacid generators and various combinations of divalent cation salts, which can be used to tune the hydrogel degradation kinetics, pattern fidelity, and mechanical properties. This approach is first utilized to template perfusable microfluidic channels within a second encapsulating hydrogel for T-junction and gradient devices. The presence and degradation of printed alginate microstructures were further verified to have minimal toxicity on epithelial cells. Degradable alginate barriers were used to direct collective cell migration from different initial geometries, revealing differences in front speed and leader cell formation.”

Fabrication steps for agarose microfluidic channels. 3% alginate with 1:3 Ba2+: Mg2+ was SLA-printed in a 35 mm diameter Petri dish, and washed with DI water. Alginate template
structures were encapsulated in molten 1.5% agarose, and allowed to cool to form a hydrogel. Reservoirs were biopsy-punched and the alginate degraded with 100 mM EDTA. The source channel was filled with 0.2% Evans Blue and the sink channel with DI water.

The innovative research led the team to discover several different ways that temporary alginate structures could be of use, such as using them as templates for lab-on-a-chip devices that contain “complex microfluidic channels.”

Valentin, the study’s lead author and a PhD student in Wong’s lab at Brown, said, “It’s a helpful tool for fabrication.”

“We can print the shape of the channel using alginate, then print a permanent structure around it using a second biomaterial. Then we simply dissolve away the alginate and we have a hollow channel. We don’t have to do any cutting or complex assembly.”

In addition, the degradable structures made of alginate can also be used to make “dynamic environments” in order to run experiments using live cells, and the researchers demonstrated this by running multiple experiments that used human mammary cells to surround alginate barriers. When the barrier was fully dissolved, they then observed how exactly the cells migrated; this would be helpful when considering how to study cells migrating in cancer or wound-healing processes. As there was no “appreciable toxicity to the cells” in either the alginate barrier or the chelating agent that dissolves it, the researchers deduced that these types of experiments could work using degradable alginate barriers.

The researchers also explained that due to the alginate’s biocompatibility, it would be an ideal material for making artificial organ and tissue scaffolds as well.

Time-lapse video shows an intricately printed Brown logo dissolving away after the application of a biocompatible chemical trigger (speed 300X real time).

Wong said, “We can start to think about using this in artificial tissues where you might want channels running through it that mimic blood vessels. We could potentially template that vasculature using alginate and then dissolve it away like we did for the microfluidic channels.”

Experiments with the team’s degradable alginate structures will continue, and the researchers will focus next on fine-tuning the pace of degradation, as well as the structures’ stiffness and strength properties.

What do you think about this 3D printed degradable biomaterial? Let us know your thoughts; join the discussion of this and other 3D printing topics at You can also discuss in the Facebook comments below.

[Source/Images: Brown University]