Designfax weekly eMagazine

Subscribe Today!

Archives

View Archives

Partners

Manufacturing Center
Product Spotlight

Modern Applications News
Metalworking Ideas For
Today's Job Shops

Tooling and Production
Strategies for large
metalworking plants

What's a SLIC Pin^®? Pin and cotter all in one!

The SLIC Pin (Self-Locking Implanted Cotter Pin) from Pivot Point is a pin and cotter all in one. This one-piece locking clevis pin is cost saving, fast, and secure. It functions as a quick locking pin wherever you need a fast-lock function. It features a spring-loaded plunger that functions as an easy insertion ramp. This revolutionary fastening pin is very popular and used successfully in a wide range of applications.
Learn more.

Engineering challenge: Which 3D-printed parts will fade?

How does prolonged exposure to intense UV light impact 3D-printed plastics? Will they fade? This is what Xometry's Director of Application Engineering, Greg Paulsen, set to find out. In this video, Paulsen performs comprehensive tests on samples manufactured using various additive processes, including FDM, SLS, SLA, PolyJet, DLS, and LSPc, to determine their UV resistance. Very informative. Some results may surprise you.
View the video.

Copper filament for 3D printing

Virtual Foundry, the company that brought us 3D-printable lunar regolith simulant, says its popular Copper Filamet™ (not a typo) is "back in stock and ready for your next project." This material is compatible with any open-architecture FDM/FFF 3D printer. After sintering, final parts are 100% pure copper. Also available as pellets. The company says this is one of the easiest materials to print and sinter. New Porcelain Filamet™ available too.
Learn more and get all the specs.

Copper foam -- so many advantages

Copper foam from Goodfellow combines the outstanding thermal conductivity of copper with the structural benefits of a metal foam. These features are of particular interest to design engineers working in the fields of medical products and devices, defense systems and manned flight, power generation, and the manufacture of semiconductor devices. This product has a true skeletal structure with no voids, inclusions, or entrapments. A perennial favorite of Designfax readers.
Learn more.

Full-color 3D-printing Design Guide from Xometry

With Xometry's PolyJet 3D-printing service, you can order full-color 3D prints easily. Their no-cost design guide will help you learn about different aspects of 3D printing colorful parts, how to create and add color to your models, and best practices to keep in mind when printing in full color. Learn how to take full advantage of the 600,000 unique colors available in this flexible additive process.
Get the Xometry guide.

Tech Tip: How to create high-quality STL files for 3D prints

Have you ever 3D printed a part that had flat spots or faceted surfaces where smooth curves were supposed to be? You are not alone, and it's not your 3D printer's fault. According to Markforged, the culprit is likely a lack of resolution in the STL file used to create the part.
Read this detailed and informative Markforged blog.

Test your knowledge: High-temp adhesives

Put your knowledge to the test by trying to answer these key questions on how to choose the right high-temperature-resistant adhesive. The technical experts from Master Bond cover critical information necessary for the selection process, including questions on glass transition temperature and service temperature range. Some of the answers may surprise even the savviest of engineers.
Take the quiz.

Engineer's Toolbox: How to pin a shaft and hub assembly properly

One of the primary benefits of using a coiled spring pin to affix a hub or gear to a shaft is the coiled pin's ability to prevent hole damage. Another is the coiled pin absorbs wider hole tolerances than any other press-fit pin. This translates to lower total manufacturing costs of the assembly. However, there are a few design guidelines that must be adhered to in order to achieve the maximum strength of the pinned system and prevent damage to the assembly.
Read this very informative SPIROL article.

What's new in Creo Parametric 11.0?

Creo Parametric 11.0 is packed with productivity-enhancing updates, and sometimes the smallest changes make the biggest impact in your daily workflows. Mark Potrzebowski, Technical Training Engineer, Rand 3D, runs through the newest functionality -- from improved surface modeling tools to smarter file management and model tree navigation. Videos provide extra instruction.
Read the full article.

What's so special about wave springs?

Don't settle for ordinary springs. Opt for Rotor Clip wave springs. A wave spring is a type of flat wire compression spring characterized by its unique waveform-like structure. Unlike traditional coil springs, wave springs offer an innovative solution to complex engineering challenges, producing forces from bending, not torsion. Their standout feature lies in their ability to compress and expand efficiently while occupying up to 50% less axial space than traditional compression springs. Experience the difference Rotor Clip wave springs can make in your applications today!
View the video.

New Standard Parts Handbook from JW Winco

JW Winco's printed Standard Parts Handbook is a comprehensive 2,184-page reference that supports designers and engineers with the largest selection of standard parts categorized into three main groups: operating, clamping, and machine parts. More than 75,000 standard parts can be found in this valuable resource, including toggle clamps, shaft collars, concealed multiple-joint hinges, and hygienically designed components.
Get your Standard Parts Handbook today.

Looking to save space in your designs?

Watch Smalley's quick explainer video to see how engineer Frank improved his product designs by switching from traditional coil springs to compact, efficient wave springs. Tasked with making his products smaller while keeping costs down, Frank found wave springs were the perfect solution.
View the video.

Top die casting design tips

You can improve the design and cost of your die cast parts with these top tips from Xometry's Joel Schadegg. Topics include: Fillets and Radii, Wall Thicknesses, Ribs and Metal Savers, Holes and Windows, Parting Lines, and more. Follow these recommendations so you have the highest chance of success with your project.
Read the full Xometry article.

What's the latest from 3D Systems? Innovations for different industries, processes

3D Systems unveiled several new solutions at the RAPID+TCT 2025 show in April designed to change the way industries innovate. From new 3D printers and materials for high-mix, low-volume applications to marked improvements in how investment casting can be done, learn what is the state of the art from the original inventors of 3D printing.
Read the full article.

Clever! Indexing plungers with chamfered pins

JW Winco has developed a new type of indexing plunger -- GN 824 -- that can independently latch into edges and grooves. This is made possible by a chamfered plunger pin. When the chamfered pin encounters a raised latching geometry, it retracts and then springs back out again once it reaches the latching point. This new indexing plunger can be ordered with axial thread for fastening and a black plastic knob for operating the indexing plunger. In a clever design, the plunger pin can be adjusted by 360 degrees to ensure that it encounters the mating surface perpendicularly. This hardware is well suited for transport frames, mechanisms, or covers that need to be locked in place quickly and securely, especially without the need for manual intervention.
Learn more.

Artificial intelligence system finds 'recipes' for producing new and novel materials by poring through millions of research papers

A new artificial-intelligence system aims to pore through research papers to deduce "recipes" for producing particular materials. [Image: Chelsea Turner/MIT]

 

 

By Larry Hardesty, MIT

In recent years, research efforts such as the Materials Genome Initiative and the Materials Project have produced a wealth of computational tools for designing new materials useful for a range of applications, from energy and electronics to aeronautics and civil engineering.

But developing processes for producing those materials has continued to depend on a combination of experience, intuition, and manual literature reviews.

A team of researchers at MIT, the University of Massachusetts at Amherst, and the University of California at Berkeley hopes to close that materials-science automation gap with a new artificial-intelligence system that would pore through research papers to deduce "recipes" for producing particular materials.

"Computational materials scientists have made a lot of progress in the ‘what' to make -- what material to design based on desired properties," says Elsa Olivetti, the Atlantic Richfield Assistant Professor of Energy Studies in MIT's Department of Materials Science and Engineering (DMSE). "But because of that success, the bottleneck has shifted to, ‘Okay, now how do I make it?'"

The researchers envision a database that contains materials recipes extracted from millions of papers. Scientists and engineers could enter the name of a target material and any other criteria -- precursor materials, reaction conditions, fabrication processes -- and pull up suggested recipes.

As a step toward realizing that vision, Olivetti and her colleagues have developed a machine-learning system that can analyze a research paper, deduce which of its paragraphs contain materials recipes, and classify the words in those paragraphs according to their roles within the recipes: names of target materials, numeric quantities, names of pieces of equipment, operating conditions, descriptive adjectives, and the like.

In a paper appearing in the latest issue of the journal Chemistry of Materials, they also demonstrate that a machine-learning system can analyze the extracted data to infer general characteristics of classes of materials -- such as the different temperature ranges that their synthesis requires -- or particular characteristics of individual materials -- such as the different physical forms they will take when their fabrication conditions vary.

Olivetti is the senior author on the paper, and she's joined by Edward Kim, an MIT graduate student in DMSE; Kevin Huang, a DMSE postdoc; Adam Saunders and Andrew McCallum, computer scientists at UMass Amherst; and Gerbrand Ceder, a Chancellor's Professor in the Department of Materials Science and Engineering at Berkeley.

Filling in the gaps
The researchers trained their system using a combination of supervised and unsupervised machine-learning techniques. "Supervised" means that the training data fed to the system is first annotated by humans; the system tries to find correlations between the raw data and the annotations. "Unsupervised" means that the training data is unannotated, and the system instead learns to cluster data together according to structural similarities.

Because materials-recipe extraction is a new area of research, Olivetti and her colleagues didn't have the luxury of large, annotated data sets accumulated over years by diverse teams of researchers. Instead, they had to annotate their data themselves -- ultimately, about 100 papers.

By machine-learning standards, that's a pretty small data set. To improve it, they used an algorithm developed at Google called Word2vec. Word2vec looks at the contexts in which words occur -- the words' syntactic roles within sentences and the other words around them -- and groups together words that tend to have similar contexts. So, for instance, if one paper contained the sentence "We heated the titanium tetracholoride to 500 C," and another contained the sentence "The sodium hydroxide was heated to 500 C," Word2vec would group "titanium tetracholoride" and "sodium hydroxide" together.

With Word2vec, the researchers were able to greatly expand their training set, since the machine-learning system could infer that a label attached to any given word was likely to apply to other words clustered with it. Instead of 100 papers, the researchers could thus train their system on around 640,000 papers.

Tip of the iceberg
To test the system's accuracy, however, they had to rely on the labeled data, since they had no criterion for evaluating its performance on the unlabeled data. In those tests, the system was able to identify with 99 percent accuracy the paragraphs that contained recipes and to label with 86 percent accuracy the words within those paragraphs.

The researchers hope that further work will improve the system's accuracy, and in ongoing work they are exploring a battery of deep learning techniques that can make further generalizations about the structure of materials recipes, with the goal of automatically devising recipes for materials not considered in the existing literature.

Much of Olivetti's prior research has concentrated on finding more cost-effective and environmentally responsible ways to produce useful materials, and she hopes that a database of materials recipes could abet that project.

"This is landmark work," says Ram Seshadri, the Fred and Linda R. Wudl Professor of Materials Science at the University of California at Santa Barbara. "The authors have taken on the difficult and ambitious challenge of capturing, through AI methods, strategies employed for the preparation of new materials. The work demonstrates the power of machine learning, but it would be accurate to say that the eventual judge of success or failure would require convincing practitioners that the utility of such methods can enable them to abandon their more instinctual approaches."

This research was supported by the National Science Foundation, Office of Naval Research, the Department of Energy, and seed support through the MIT Energy Initiative. Kim was partially supported by Natural Sciences and Engineering Research Council of Canada.

Published December 2017

Rate this article