What Can AI Really Do for 3D Printing?

An in-depth look at how ChatGPT and other LLMs are impacting the additive manufacturing landscape.

The growth of additive manufacturing (AM) has been accompanied by incredible leaps in digital design from the likes of generative design and computational monitoring. Built-in computer intelligence platforms have been developing for some time now, with generative design creating new types of files that can only become reality through digital technologies like 3D printing.

But are these “smart” designs just the beginning?

Artificial intelligence (AI) is seemingly everywhere today, ever since OpenAI’s ChatGPT boomed onto the scene in a big way at the end of November 2022. The freely available chatbot opened large language model (LLM) access to the general public, creating new avenues to create, ideate, iterate, potentially plagiarize – and to question.

• What do we need AI for?
• Do we need it at all?
• How and where does AI fit into workflows under the Industry 4.0 umbrella?
• What about specifically to AM as an industry?

AI LLM Features & Flaws

AI offers incredible benefits that could save real human hours of work through automation. LLMs in particular offer virtual conversations that can be used to automate coding, generate ideas from specific prompts or quickly sort through mountains of data to target specific findings.

As with any conversationalist, though, AI is prone to inaccuracies. LLMs are prone to “hallucinations,” which are confident responses not justified by the training data. Such hallucinations underscore the precariousness of relying on AI. In such early days of widely available LLM capabilities, even the extremely thorough training and testing done to date are not nearly enough to avoid inaccuracies.

ChatGPT and similar programs are also limited in terms of timeliness: the free version of ChatGPT only has information up to 2021, for example. When it comes to fast-moving, cutting-edge industries, two-plus-year-old data may already be obsolete. Advances, discoveries, and debuts in the last two years have already moved several Industry 4.0 sectors forward, such as additive manufacturing.

AI for AM

As an advanced manufacturing technology, AM relies on software as much as hardware. Generating design files, slicing those designs, preparing print jobs, automated traceability, workflows, post-processing; every step of the AM process requires advanced software and reliable programming.

Most recently, we’ve seen manufacturing software explode with design for additive manufacturing (DfAM), such as “smart” offerings in generative design.

Generative design in software for 3D printing is nothing new. We’ve seen announcements and discussions from the likes of Autodesk, Frustum, ANSYS, MIT, Jabil, Shapeways, Dassault Systèmes, Siemens, Desktop Metal, and so many others over the past decade.

Computers can run thousands of potential design scenarios, including virtual stress testing, in the time it might take human designers to explore a few dozen options. With the added advantage of fundamentally building in the complexity of designs that could be made only by additive processes, AI in DfAM is a tantalizing proposition.

3DGPT

Turning more directly to the latest wave of LLM interest, manufacturing workflow software provider Authentise recently introduced its own AI solution specific to additive manufacturing with 3DGPT.

The release, currently more an experiment than a product per se, is freely available for interested parties to check out. Its algorithms are built upon “the power of 12,000+ additive manufacturing journal articles and standards,” as Authentise describes it.

“There are many ways we think that this tool might be useful inside our product portfolio – whether it’s to help create reliable and efficient workflows or make RFQ’s with many standards references more penetrable. Before that – we, Authentise as well as partners such as ASTM, naturally need to understand the technology’s opportunities and limits; we know that GPT algorithms sometimes hallucinate, for instance,” said Authentise CEO Andre Wegner upon the experiment’s release.

Shortly after debuting 3DGPT, Authentise followed with the introduction of Threads. This new workflow tool is supposed to integrate communication and project management tools into a new work thread collaboration suite. Threads represents a more concrete product release already backed up by reviews from early users.

“Additive is maturing,” Wegner says, about the impetus behind the 3DGPT and Threads releases. “Solving the two big problems, application identification/engineering and repeatability, demands rapid knowledge dissemination and collaboration. 3DGPT and Threads solve both. Eventually, they’ll merge – AI-supported ad hoc collaboration. But the interest in 3DGPT and the demonstrated results of Threads show that they provide individual value too!”

So, there’s a roadmap and 3DGPT is the experiment. As often happens with additive manufacturing experiments, it may not pan out. But – and here’s why it’s worth the look – it could go somewhere major.

In tandem with more immediately realizable releases like Threads as well as existing project management software, knowledgeable users able to discern AI hallucinations from peer-reviewed results could use tools like 3DGPT to advance their AM workflows.

Industry Hesitation

But even if something like 3DGPT works…what’s the point? It’s all well and good for a company like Authentise to be able to claim first-to-market on the tailwinds of the ChatGPT hullabaloo, but is it relevant for those working in the industry today?

“I reckon it will be about five years before AI can, in a meaningful way, provide reliable quality,” says industry expert Rachel Park, who has been in AM since 1997.

A conversation with Park offers a much needed step back when it comes to matters like 3DGPT. There is potential – and she has seen decades of 3D printing potential rise and soar (as well as crash and burn). Some of the 3DGPT results simply “read like regurgitation,” she notes, and “for any company that wants to stand out, [using AI] is the exact opposite of what it should be doing. If that’s what a company is relying on for their marketing content, they’re going to fail.”

Indeed, generating marketing content – especially in the midst of pretty widespread layoffs across the entire tech sector that rarely leave full marketing teams intact – seems to be low-hanging fruit for the use of LLMs in tech companies.

Copywriting offers some seemingly obvious entry into exploiting new AI capabilities and bringing them into practice. Still, if the content is indeed regurgitated, it won’t sound fresh – because it isn’t. It’s demonstrably pulled from existing resources.

Thankfully, in the case of 3DGPT, those resources are clearly designated in a “References” explainer at the end of each response section.

Others have questioned more generally the usage, relatability and reliability of a tool like 3DGPT that’s supposed to be specifically designed for AM.

“Not sure I really understand the value of a chatbot with a 3D printing skin,” says Shawn Miely, an experienced AM product and content marketer. “[I would] love to know of a use case where there is more value in this tool than with ChatGPT which, based on my few queries, seems to produce better results.”

Authentise responded directly to Miely’s remarks, explaining (with remarks cleaned up slightly):

“Fully specialized models are the future…. Experts who want real answers will need more than general platitudes or in fact complete nonsense that general LLMs often provide.

If they get really valuable to experts, specialized LLMs can also be integrated into expert systems. We’re thinking about chatbots that understand what’s going wrong with a build based on printer data and use their specialized knowledge to suggest remediation strategies.

Of course we’re still a long way from that. This is just a start – without which we can’t learn what works and what doesn’t so please rate the responses so the system gets better…”

3DGPT v. ChatGPT

So, how does 3DGPT compare to plain old ChatGPT?

Trained specifically on expert additive manufacturing materials, 3DGPT offers references – and starts with a warning:

Beneath the question entry box, Authentise further warns:

“3DGPT may generate inaccurate or offensive information that doesn’t represent Authentise’s views. Please use it at your own risk, and always check the references provided.”

ChatGPT also carries warnings and requests feedback, as should all LLMs. Machine learning has to learn to improve, so such disclaimers and feedback loops should not be surprising.

That said, I went head-to-head offering prompts to 3DGPT and ChatGPT to experience the differences and similarities between these two LLMs. The most immediately notable points are that 3DGPT offers shorter responses following prompts where AM is the assumption, as well as including DOI details for reference materials.

ChatGPT tends to be more long-winded in its responses and more AM-specificity is required in writing the prompt since the platform is so generalized. It also offers no references.

As an initial baseline, I asked each LLM to tell me what the seven 3D printing technology processes are. For reference, we turn to the ASTM-defined classifications as the gold standard—otherwise there seem to be far more than seven types of 3D printing processes out there, with some coming down to simple branding.

For reference and per Loughborough University, citing ASTM F42 – Additive Manufacturing formulations classified in 2012,  the seven processes are:

• Vat photopolymerization
• Material jetting
• Binder jetting
• Material extrusion
• Powder bed fusion
• Sheet lamination
• Directed energy deposition

Per 3DGPT:

Me: What are the seven 3D printing technology processes?

3DGPT: Yes, the seven 3D printing technology processes are:

1. Vat photopolymerization (represented by stereolithography or SLA)
2. Material extrusion (represented by fused deposition modeling or FDM)
3. Powder bed fusion (represented by selective laser sintering or SLS)
4. Directed energy deposition (represented by laser metal deposition or LMD and laser engineered net shaping or LENS)
5. Sheet lamination (represented by laminated object manufacturing or LOM)
6. Material jetting (represented by multi-jet modeling or MJM)
7. Binder jetting (represented by 3D printing or 3DP)

References:

Title: Characterization of particulate matters and total VOC emissions from a binder jetting 3D printer

Authors: Nima Afshar-Mohajer, Chang-Yu Wu, Thomas Ladun, Didier A. Rajon, Yong Huang

Year: 2015.0

DOI: 10.1016/j.buildenv.2015.07.013

Turning next to ChatGPT, I asked the same question:

Me: What are the seven 3D printing technology processes?

ChatGPT:

There are several 3D printing technology processes, and while there are more than seven, I will mention seven commonly used ones:

Fused Deposition Modeling (FDM): FDM is the most widely used 3D printing process. It involves melting and extruding a thermoplastic filament through a heated nozzle, which deposits layers of material to create the object.

Stereolithography (SLA): SLA uses a vat of liquid photopolymer resin that is cured by a UV laser. The laser selectively solidifies the resin, layer by layer, to create the desired object.

Selective Laser Sintering (SLS): SLS employs a high-power laser to selectively fuse powdered material, typically nylon or metal, into a solid structure. The process repeats layer by layer until the complete object is formed.

Digital Light Processing (DLP): DLP is similar to SLA but uses a digital light projector to flash a single image of each layer onto a vat of liquid resin, solidifying it. It is faster than SLA but may have slightly lower resolution.

Electron Beam Melting (EBM): EBM uses a high-power electron beam to melt and fuse metallic powder together, creating fully dense metal parts. It is commonly used in metal additive manufacturing for industrial applications.

Selective Laser Melting (SLM): SLM is another metal 3D printing process that utilizes a high-powered laser to melt and fuse metal powder. It offers high precision and is used for producing complex metal parts.

Binder Jetting: In binder jetting, a liquid binder is selectively deposited onto a powdered material, layer by layer. The binder acts as an adhesive, binding the particles together to create the desired object. This process can be used with various materials, including metals, ceramics, and sand.

These are just a few examples of 3D printing technology processes, and there are others like PolyJet, Laminated Object Manufacturing (LOM), and more. Each process has its strengths and limitations, making them suitable for different applications and materials.

In this example, we can see that ChatGPT is much more thorough and has a bit more nuance – and much more explanation – to its response.

Interestingly, we also see more explanation even in the questions 3DGPT itself suggests as a starting point.

Me: What are the recommended workflow steps for Ti64?  ​

3DGPT: The recommended workflow steps for Ti64 depend on the specific application and the desired properties of the final part. However, some general steps for processing Ti64 include:

1. Design the part using CAD software.
2. Choose a suitable manufacturing process, such as SLM or EBM, based on the application and desired properties.
3. Prepare the Ti64 powder for the chosen process.
4. Set the process parameters, such as laser power and scanning speed, based on the desired microstructure and properties.
5. Build the part using the chosen process.
6. Post-process the part, if necessary, to improve its properties or surface finish.
7. Test the part to ensure it meets the required specifications.

It’s important to note that the processing of Ti64 with SLM and EBM results in microstructures containing α, a, and β phases, and the resulting properties will vary depending on the volume fraction of these phases and their morphology. Therefore, it’s crucial to carefully control the processing parameters to achieve the desired microstructure and properties.

References:

Title: Microstructures and Mechanical Properties of Ti6Al4V Parts Fabricated by Selective Laser Melting and Electron Beam Melting

Authors: H. K. Rafi, N. V. Karthik, Haijun Gong, Thomas L. Starr, Brent E. Stucker

Year: 2013.0

DOI: 10.1007/s11665-013-0658-0

Title: Activated slip and twin systems in electron beam melted Ti-6Al-4V subjected to elevated and high strain rate dynamic deformations

Authors: Reza Alaghmandfard, Dharmendra Chalasani, Akindele Odeshi, Mohsen Mohammadi

Year: 2021.0

DOI: 10.1016/j.matchar.2020.110866

Here, 3DGPT does note limitations inherent in the question, noting that nuance is required in terms of application and final part properties. It is interesting here that using a suggested prompt generates this type of “Well, it depends…” response, but that’s more a broad point of interest.

Meanwhile, ChatGPT – for which I adjusted the prompt only to note “additive manufacturing” as a clear factor – also indicates need for specificity, while offering a broader (possibly more comprehensive) response:

Me: What are the recommended additive manufacturing workflow steps for Ti64?

ChatGPT:

The recommended additive manufacturing (AM) workflow steps for Ti64 (Titanium alloy) can vary depending on specific requirements and equipment used. However, here is a general outline of the key steps involved in the AM process for Ti64:

Design and Preprocessing:

Begin with a 3D CAD model of the desired object.

Perform design optimization and ensure the part is suitable for additive manufacturing.

Orient and position the part within the build volume to optimize build quality and minimize support structures.

Slice the CAD model into layers and generate the corresponding toolpath instructions for the AM machine.

Material Preparation:

Acquire high-quality Ti64 powder specifically formulated for AM processes.

Ensure the powder is stored and handled in a controlled environment to maintain its integrity.

Conduct powder characterization, including particle size analysis and quality control checks.

Build Setup:

Prepare the build platform or build chamber of the AM machine.

Apply a suitable substrate or baseplate to facilitate adhesion of the initial powder layers.

Load the Ti64 powder into the machine’s material delivery system.

Build Process:

Initiate the AM process according to the machine’s operating instructions.

Employ the specific AM technology for Ti64, such as selective laser melting (SLM) or electron beam melting (EBM).

Control process parameters such as laser power, scan speed, beam focus, and beam size to achieve the desired part quality.

Deposit and consolidate layers of Ti64 powder to build the object progressively.

Implement any necessary heat treatments, such as stress relief or post-processing, during the build process if required.

Post-processing:

Allow the built object to cool down gradually inside the build chamber.

Remove the built part from the build platform or chamber.

Perform necessary support structure removal, such as breaking or machining away any support material.

Conduct post-processing treatments like heat treatment, stress relief, or surface finishing to enhance the material properties and surface quality.

Perform quality control inspections, including dimensional verification, surface analysis, and non-destructive testing, to ensure the part meets the required specifications.

Finishing and Inspection:

Clean the finished part to remove any residual powder or support material.

Perform any additional surface finishing processes like polishing or coating if needed.

Conduct final inspections and quality assurance checks to verify the part’s dimensional accuracy, mechanical properties, and surface finish.

It is important to note that the specific parameters and procedures may vary depending on the AM machine, software, and process used. It is recommended to refer to the equipment manufacturer’s guidelines, material supplier recommendations, and industry best practices for detailed instructions when working with Ti64 or any other specific material in additive manufacturing.

Will AI Help Aim AM?

Ultimately, AI is simply another tool in the toolbox. Its efficacy depends on the user. More and more expertise is quickly popping up in terms of shaping “the best prompts” for chatbots as LLMs become more widespread. The Big Names in tech, from Google to Microsoft to Apple, are all getting in on the AI game. Given the proliferation of such offerings, it’s inevitable they will find more foothold in Industry 4.0 – and so into additive manufacturing.

Still, every mention of AI in AM is first met with the question why. Authentise’s release is realistic in that it includes warning labels as well as a nicely-timed workflow release indicating aspirational as well as grounded offerings in workflow management software. Overall, we as a whole have a lot to learn about the best applications for AI and how best to gear them for any industry, much less those like additive manufacturing that are themselves still relatively nascent.

So to answer our titular question: What can AI really do for 3D printing? Time will tell. Today, it will raise questions and help us think through our processes. In five years, as Park projects, there may well be impactful application in automation from AI.