Bold of you to assume my prints come out the way they’re supposed to.
Or consistent.
From what I can tell from the article, that’s exactly the point. This is not about manufacturer-sanctioned intentional fingerprinting but about every printer making slightly different mistakes by accident that just happen to be consistent enough to be recognizable.
Bold of you to assume the mistakes my printer makes are in any way consistent.
I have one of those generic chinese printers. Good luck printing anything on it.
On my printers, each print looks differently. The prints sometimes also fail for various reasons. Add a constant process of modifications and I doubt someone can find enough reproducible unique features on the prints, to recognise the correct printer.
Reading the article, it seems like the intent of this technology is much more geared toward manufacturing supply chains, rather than saying “this part came from John Doe’s Ender 3”. As many people have pointed out, consumer/ hobbyist grade 3D printers aren’t nearly consistent enough to produce anything resembling something as unique as a true “fingerprint”, and when you consider that most printers are modified in some way… There’s just zero possibility of it being used in that way.
The only way I could see it being used in that way is trying to prove that this printer printed this part; if they have the printed part, and it hasn’t been post-processed at all (sanded, treated, etc), they could reprint the same part on the printer in question and see if it’s “fingerprint” is the same. But I’d be pretty surprised if this tech could even reliably say, “this part came from an Ender, this part came from a Neptune, and this one from came from a P1”.
Yeah this is basically just quality control geared towards mass 3d printed parts.
I wish my printer was consistent enough between two prints for proving that two parts came from the same printer.
The technology could also be used to track the origins of illicit goods.
Does that mean ghost guns? That was my first thought when I heard of this tech.
I think that’s the unspoken implication and I’m instantly suspicious of the entire premise. The entire field of forensic science is filled to the brim with things described as “fingerprints” that are not nearly as unique or consistent as the field would have us believe.
Yeah but if expert says its a match, it is enough to get the job done.
Nobody really cares if it is true or not when they do this.
I’m rather skeptical as well, but if there’s a defect on the nozzle causing stations in the extrusion, that might do it.
Otherwise they might get lucky, but I doubt it.
Resin printers might have something else, but it’s hard to imagine what. (Maybe dead pixels?)
The nozzle? The one part that gets replaced almost as often as the filament?
My guess is if there’s a defect somewhere on the z-axis so there’s always a consistent slip at a certain height would be the only way, and even then, that’s a replaceable part.
Yes. The nozzle.
The one part that puts a consistent pattern into the filament as it extrudes that can be corrected for variation from temps and materials and whatever else.
Unless you’re printing abrasives, your brass nozzles doesn’t wear that quickly and defects from the boring out during production will translate to patterns in the surface.
Most fdm printers might be accurate to .1mm, with the best getting to around .05mm in z and any measurement below that is basically random noise, so you have finite limits on how precise you can get measuring defects.
This means that well tuned printers will generally be close enough that it’s hard to differentiate between them.
Now imagine a pattern in an introduced by a warped lead screw, as an example. Sure this is cyclic. But its height is dependent on the lead screw’s thread lead. A T8x8 has an 8mm lead and this pattern will repeat every 8mm in height, with a consistent layer count between them.
As will basically every printer using a t8x8 screw. Printing at that same layer thickness. Which is pretty much every printer on the market. There might be some slop with backlash, but that’s not going to show up accurately enough.
And yes. You can swap out nozzles, just like you can belts and lead screws and every other part. Unlike most parts, though, the microscopic striations coming off the nozzle aren’t as inconsistent as say belt tightness.
I’ll have you know that my magic wand is 100% accurate at least 50% of the time!
My speculation says yes.
They’d need Access to the suspect’s printer, to print more copies for comparison in order to tell, though, from how the article describes it.
Similar to how they match bullets to the gun that fired it. It’s not like it prints a serial number QR code on it or anything
Those eyes are staring right into my soul
This seems like very standard ML. I’m not surprised it works, but also it likely takes a huge amount of training data (i.e. print samples) to recognize a specific machine.
I’ve done stuff like this. For instance I took a pre-trained model that could identify animals and used reinforcement learning to feed it thousands of annotated images of my cats. After this fine-tuning it could reliably tell the difference between them. Useful? Yes. Neat? Yes. But it’s not like it can identify a cat it’s never been trained on.
So it’s interesting and useful, but not as impressive or useful as the article makes it seem.
Also I’m sure something as simple as changing a nozzle or even what slicer is used would completely throw it off.
