Algorithm learns to correct 3D printing errors for different parts, materials and systems
Spin-out company formed
The engineers, from the University of Cambridge, developed a machine learning algorithm that can detect and correct a wide variety of different errors in real time, and can be easily added to new or existing machines to enhance their capabilities. 3D printers using the algorithm could also learn how to print new materials by themselves. Details of their low-cost approach are reported in the journal Nature Communications.
3D printing has the potential to revolutionise the production of complex and customised parts, such as aircraft components, personalised medical implants, or even intricate sweets, and could also transform manufacturing supply chains. However, it is also vulnerable to production errors, from small-scale inaccuracies and mechanical weaknesses through to total build failures.
Currently, the way to prevent or correct these errors is for a skilled worker to observe the process. The worker must recognise an error (a challenge even for the trained eye), stop the print, remove the part, and adjust settings for a new part. If a new material or printer is used, the process takes more time as the worker learns the new setup. Even then, errors may be missed as workers cannot continuously observe multiple printers at the same time, especially for long prints.
“3D printing is challenging because there's a lot that can go wrong, and so quite often 3D prints will fail,” said Dr Sebastian Pattinson from Cambridge’s Department of Engineering, the paper’s senior author. “When that happens, all of the material and time and energy that you used is lost.”
Engineers have been developing automated 3D printing monitoring, but existing systems can only detect a limited range of errors in one part, one material and one printing system.
“What’s really needed is a ‘driverless car’ system for 3D printing,” said first author Douglas Brion, also from the Department of Engineering. “A driverless car would be useless if it only worked on one road or in one town – it needs to learn to generalise across different environments, cities, and even countries. Similarly, a ‘driverless’ printer must work for multiple parts, materials, and printing conditions.”
Brion and Pattinson say the algorithm they’ve developed could be the ‘driverless car’ engineers have been looking for.
“What this means is that you could have an algorithm that can look at all of the different printers that you're operating, constantly monitoring and making changes as needed – basically doing what a human can't do,” said Pattinson.
The researchers trained a deep learning computer vision model by showing it around 950,000 images captured automatically during the production of 192 printed objects. Each of the images was labelled with the printer’s settings, such as the speed and temperature of the printing nozzle and flow rate of the printing material. The model also received information about how far those settings were from good values, allowing the algorithm to learn how errors arise.
“Once trained, the algorithm can figure out just by looking at an image which setting is correct and which is wrong – is a particular setting too high or too low, for example, and then apply the appropriate correction,” said Pattinson. “And the cool thing is that printers that use this approach could be continuously gathering data, so the algorithm could be continually improving as well.”
Using this approach, Brion and Pattinson were able to make an algorithm that is generalisable – in other words, it can be applied to identify and correct errors in unfamiliar objects or materials, or even in new printing systems.
“When you’re printing with a nozzle, then no matter the material you’re using – polymers, concrete, ketchup, or whatever – you can get similar errors,” said Brion. “For example, if the nozzle is moving too fast, you often end up with blobs of material, or if you’re pushing out too much material, then the printed lines will overlap forming creases.
“Errors that arise from similar settings will have similar features, no matter what part is being printed or what material is being used. Because our algorithm learned general features shared across different materials, it could say ‘Oh, the printed lines are forming creases, therefore we are likely pushing out too much material’.”
As a result, the algorithm that was trained using only one kind of material and printing system was able to detect and correct errors in different materials, from engineering polymers to even ketchup and mayonnaise, on a different kind of printing system.
In future, the trained algorithm could be more efficient and reliable than a human operator at spotting errors. This could be important for quality control in applications where component failure could have serious consequences.
With the support of Cambridge Enterprise, the University’s commercialisation arm, Brion has formed Matta, a spin-out company that will develop the technology for commercial applications.
“We’re turning our attention to how this might work in high-value industries such as the aerospace, energy, and automotive sectors, where 3D printing technologies are used to manufacture high performance and expensive parts,” said Brion. “It might take days or weeks to complete a single component at a cost of thousands of pounds. An error that occurs at the start might not be detected until the part is completed and inspected. Our approach would spot the error in real time, significantly improving manufacturing productivity.”
Other news from the department science
Novel approach towards nanomaterials developed
During this process, the team discovered an intriguing phenomenon
How can the use of plastics in agriculture become more sustainable?
New study on plastic in our food systems
Molybdenene – the "Metallic" Relative of Graphene
The researchers created the new 2D material using a microwave
Wastewater treatment plants as drivers for the energy transition
Technical add-on module can, in principle, turn any wastewater treatment plant into a CO2 sink and decentralized methane production plant
Pixel-by-pixel analysis yields insights into lithium-ion batteries
In a first, researchers have observed how lithium ions flow through a battery interface, which could help optimize the material’s design
New ionic materials boost hydrogen fuel cell efficiency!
This breakthrough contributes to accelerating progress toward sustainable energy solutions in line with global efforts towards decarbonization
A Second Life for Electric Car Batteries
Scientists develop a decision model for retired lithium-ion batteries
‘Lab-on-a-drone’ sends science skyward to keep track of smelly air pollution
A low-cost 3D printed analytical IoT platform for vertical monitoring of gaseous hydrogen sulphide
Accelerating battery research with robots
Smart, autonomous and chemistry-agnostic: The world urgently needs new types of energy storage
Pyrolysis processes promise sustainable recycling of fiber composites from rotor blades
Economic and ecological recycling solution for fiber composites on the horizon
Observing nanoparticles with unprecedented precision
Illuminated: Researchers investigate new physical phenomena on the nanoscale with microstructured fibers
Most read news
Major breakthrough in the development of electric vehicle batteries
New study finds ways to suppress lithium plating in automotive batteries for faster charging electric vehicles
Research shows table salt could be the secret ingredient for better chemical recycling
Table salt as the key to the plastics recycling revolution?
Graphene discovery could help generate hydrogen cheaply and sustainably
Microscopic insights into electrochemical interfaces
Leipzig-based start-up converts CO₂ into green chemicals with patented plasma catalysis
CO₂ recycling as a useful complement to carbon capture and storage
New battery holds promise for green energy
Redox-flow battery eliminates costly and inefficient membrane
A Second Life for Electric Car Batteries
Scientists develop a decision model for retired lithium-ion batteries
World record: World's longest-range electric car comes from Munich
Electric car drives over 2500 kilometres on a single battery charge
Green methanol for shipping and industry: € 10.4 Mio. for the "Leuna100" project
A consortium of two Fraunhofer institutes, DBI-Gastechnologisches Institut Freiberg, Technical University of Berlin and C1 makes industrial history at the Leuna site
New lithium battery with simple production and high safety developed
"This study underscores the importance of molecular structure design in creating effective additives for quasi-solid-state electrolytes"
More news from our other portals
Cells with an ear for music release insulin
For the first time, researchers are using music, including Queen's global hit "We will rock you," to stimulate insulin release from cells
Clean water from fog
A property known as photocatalytic memory ensures that this also functions when skies are overcast and at night
Microbe of the Year 2023: Bacillus subtilis – for health and technology
Already, Bacillus subtilis is indispensable in many industries, and many more innovations are expected
Green, sweet and crisp - New apple variety Pia41 approved
The apple bred at the Julius Kühn Institute receives variety protection
Benchtop NMR spectroscopy can accurately analyse pyrolysis oils
More accessible analysis could help develop the potential of bio-oils as an alternative to fossil fuels
Younger generation gets sick earlier and more often than older generation
In spite of their advanced age, they are in the middle of life, healthy, active and mentally alert – they are referred to as the “young old”
Sugar: Small increase in production despite record prices
EU sugar market more than in need of reform to keep medium-sized processing companies competitive
How sleep deprivation can harm the brain
Sleep deprivation decreases the amount of a factor that protects neurons
A microchip for Parmigiano Reggiano cheese
Consorzio del Parmigiano Reggiano, p-Chip Corporation, and Kaasmerk Matec Partner to Launch Breakthrough in Food-Safe Digital Tracking Technology
New approach to testing for long Covid
Blood vessels in the eye altered with persistent coronavirus symptoms
A whole new order of bacteria could hold the key to improving biogas production
The discovery was made by researchers from Germany, Spain and the Netherlands
Scientists use quantum device to slow down simulated chemical reaction 100 billion times
What happens in femtoseconds in nature can now be observed in milliseconds in the lab
How to inactivate common cold viruses
In the cold season, cold viruses are everywhere. But we can do something about it
Fondant under the magnifying glass
New insights into the properties of sweet coating: The results could be used to optimize the industrial production process in the future
How minimal genetic differences can turn healthy food into a deadly danger
You are what you eat - this old saying could take on a new dimension according to latest research results
Straws and disposable tableware: Also made of paper often with harmful chemicals for the environment and health
The supposedly better alternative is often not better at all, scientists emphasize
At which age we are at our happiest
An evaluation of over 400 samples shows how subjective well-being develops over the course of a lifespan
Making plant-based meat more ‘meaty’ — with fermented onions
When fermented with specific type of fungus, normally pungent onions can produce the same sort of chemicals that make meats smell ‘meaty’
Something is happening in the chemical industry ...
This is what true pioneering spirit looks like: Plenty of innovative start-ups are bringing fresh ideas, lifeblood and entrepreneurial spirit to change tomorrow's world for the better. Immerse yourself in the world of these young companies and take the opportunity to get in touch with the founders.