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

hyperMILL 2024 CAD/CAM software suite

OPEN MIND Technologies has introduced its latest hyperMILL 2024 CAD/CAM software suite, which includes a range of powerful enhancements to its core toolpath capabilities, as well as new functionality for increased NC programming efficiency in applications ranging from 2.5D machining to 5-axis milling. New and enhanced capabilities include: Optimized Deep Hole Drilling, a new algorithm for 3- and 5-axis Rest Machining, an enhanced path layout for the 3D Plane Machining cycle, better error detection, and much more.
Learn more.

One-part epoxy changes from red to clear under UV

Master Bond UV15RCL is a low-viscosity, cationic-type UV-curing system with a special color-changing feature. The red material changes to clear once exposed to UV light, indicating that there is UV light access across the adhesive material. Although this change in color from red to clear does not indicate a full cure, it does confirm that the UV light has reached the polymer. This epoxy is an excellent electrical insulator. UV15RCL adheres well to metals, glass, ceramics, and many plastics, including acrylics and polycarbonates.
Learn more.

SPIROL Press-N-Lok™ Pin for plastic housings

The Press-N-Lok™ Pin was designed to permanently retain two plastic components to each other. As the pin is inserted, the plastic backfills into the area around the two opposing barbs, resulting in maximum retention. Assembly time is quicker, and it requires lower assembly equipment costs compared to screws and adhesives -- just Press-N-Lok™!
Learn more about the new Press-N-Lok™ Pin.

Why hybrid bearings are becoming the new industry standard

A combination of steel outer and inner rings with ceramic balls or rollers is giving hybrid bearings unique properties, making them suitable for use in a wide range of modern applications. SKF hybrid bearings make use of silicon nitride (twice as hard as bearing steel) rolling elements and are available as ball bearings, cylindrical roller bearings, and in custom designs. From electric erosion prevention to friction reduction and extended maintenance intervals, learn all about next-gen hybrid bearings.
Read the SKF technical article.

3M and Ansys train engineers on simulating adhesives

Ansys and 3M have created an advanced simulation training program enabling engineers to enhance the design and sustainability of their products when using tapes and adhesives as part of the design. Simulation enables engineers to validate engineering decisions when analyzing advanced polymeric materials -- especially when bonding components made of different materials. Understand the behavior of adhesives under real-world conditions for accurate modeling and design.
Read this informative Ansys blog.

New FATH T-slotted rail components in black from AutomationDirect

Automation-Direct has added a wide assortment of black-colored FATH T-slotted hardware components to match their SureFrame black anodized T-slotted rails, including: cube connectors (2D and 3D) and angle connectors, joining plates of many types, brackets, and pivot joints. Also included are foot consoles, linear bearings in silver and black, cam lever brakes, and L-handle brakes. FATH T-slotted hardware components are easy to install, allow for numerous T-slotted structure configurations, and have a 1-year warranty against defects.
Learn more.

Weird stuff: Moon dust simulant for 3D printing

Crafted from a lunar regolith simulant, Basalt Moon Dust Filamet™ (not a typo) available from The Virtual Foundry closely mirrors the makeup of lunar regolith found in mare regions of the Moon. It enables users with standard fused filament fabrication (FFF) 3D printers to print with unparalleled realism. Try out your ideas before you go for that big space contract, or help your kid get an A on that special science project.
Learn more.

Break the mold with custom injection molding by Rogan

With 90 years of industry experience, Rogan Corporation possesses the expertise to deliver custom injection molding solutions that set businesses apart. As a low-cost, high-volume solution, injection molding is the most widely used plastics manufacturing process. Rogan processes include single-shot, two-shot, overmolding, and assembly. Elevate your parts with secondary operations: drilling and tapping, hot stamping, special finishes, punch press, gluing, painting, and more.
Learn more.

World's first current-carrying fastening technology

PEM^® eConnect™ current-carrying pins from Penn-Engineering provide superior electrical connections in applications that demand high performance from internal components, such as automotive electronics. This first-to-market tech provides repeatable, consistent electrical joints and superior installation unmatched by traditional fastening methods. Features include quick and secure automated installation, no hot spots or poor conductivity, and captivation options that include self-clinching and broaching styles.
Learn more about eConnect pins.

New interactive digital catalog from EXAIR

EXAIR's latest catalog offers readers an incredible source of innovative solutions for common industrial problems like conveying, cooling, cleaning, blowoff, drying, coating, and static buildup. This fully digital and interactive version of Catalog 35 is designed for easy browsing and added accessibility. Customers can view, download, print, and save either the full catalog or specific pages and sections. EXAIR products are designed to conserve compressed air and increase personnel safety in the process. Loaded with useful information.
Check out EXAIR's online catalog.

5 cost-saving design tips for CNC machining

Make sure your parts meet expectations the first time around. Xometry's director of application engineering, Greg Paulsen, presents five expert tips for cutting costs when designing custom CNC machined parts. This video covers corners and radii, designing for deep pockets, thread depths, thin walls, and more. Always excellent info from Paulsen at Xometry.
View the video.

What can you secure with a retaining ring? 20 examples

From the watch dial on your wrist to a wind turbine, no application is too small or too big for a Smalley retaining ring to secure. Light to heavy-duty loads? Carbon steel to exotic materials? No problem. See how retaining rings are used in slip clutches, bike locks, hip replacements, and even the Louvre Pyramid.
See the Smalley design applications.

Load fasteners with integrated RFID

A crane, rope, or chain may be required when something needs lifting -- plus anchoring points on the load. JW Winco offers a wide range of solutions to fasten the load securely, including: lifting eye bolts and rings (with or without rotation), eye rings with ball bearings, threaded lifting pins, shackles, lifting points for welding, and more. Some, such as the GN 581 Safety Swivel Lifting Eye Bolts, even have integrated RFID tags to clearly identify specific lifting points during wear and safety inspections and manage them digitally and without system interruption.
Learn more.

Couplings solve misalignments more precisely with targeted center designs

ALS Couplings from Miki Pulley feature a simplistic, three-piece construction and are available in three different types for more precisely handling parallel, angular, or axial misalignment applications. The key feature of this coupling design is its center element. Each of the three models has a center member that has a unique and durable material and shape. Also called a "spider," the center is designed to address and resolve the type of misalignment targeted. Ideal for unidirectional continuous movement or rapid bidirectional motion.
Learn more.

What is 3D-MID? Molded parts with integrated electronics from HARTING

3D-MID (three-dimensional mechatronic integrated devices) technology combines electronic and mechanical functionalities into a single, 3D component. It replaces the traditional printed circuit board and opens up many new opportunities. It takes injection-molded parts and uses laser-direct structuring to etch areas of conductor structures, which are filled with a copper plating process to create very precise electronic circuits. HARTING, the technology's developer, says it's "Like a PCB, but 3D." Tons of possibilities.
View the video.

Researchers show robots how to drive a car in just a few easy lessons

Imagine if robots could learn from watching demonstrations: You could show a domestic robot how to do routine chores or set a dinner table. In the workplace, you could train robots like new employees, showing them how to perform many duties. On the road, your self-driving car could learn how to drive safely by watching you drive around your neighborhood.

Making progress on that vision, researchers from the University of Southern California (USC) have designed a system that lets robots learn complicated tasks autonomously from a very small number of demonstrations -- even imperfect ones. The paper, titled "Learning from Demonstrations Using Signal Temporal Logic," was presented at the Conference on Robot Learning (CoRL), Nov. 18.

The researchers' system works by evaluating the quality of each demonstration, so it learns from the mistakes it sees, as well as the successes. While current state-of-art methods need at least 100 demonstrations to nail a specific task, this new method allows robots to learn from only a handful of demonstrations. It also allows robots to learn more intuitively, the way humans learn from each other; you watch someone execute a task, even imperfectly, then try yourself. It doesn't have to be a "perfect" demonstration for humans to glean knowledge from watching each other.

"Many machine learning and reinforcement learning systems require large amounts of data data and hundreds of demonstrations -- you need a human to demonstrate over and over again, which is not feasible," said lead author Aniruddh Puranic, a Ph.D. student in computer science at the USC Viterbi School of Engineering. "Also, most people don't have programming knowledge to explicitly state what the robot needs to do, and a human cannot possibly demonstrate everything that a robot needs to know. What if the robot encounters something it hasn't seen before? This is a key challenge."

VIDEO: Using the USC researchers' method, an autonomous driving system would still be able to learn safe driving skills from "watching" imperfect demonstrations, such this driving demonstration on a racetrack. [Source credits: Driver demonstrations were provided through the Udacity Self-Driving Car Simulator/USC]

Learning from demonstrations
Learning from demonstrations is becoming increasingly popular in obtaining effective robot control policies -- which control the robot's movements -- for complex tasks. However, it is susceptible to imperfections in demonstrations and also raises safety concerns as robots may learn unsafe or undesirable actions.

Also, not all demonstrations are equal: Some demonstrations are a better indicator of desired behavior than others, and the quality of the demonstrations often depends on the expertise of the user providing the demonstrations.

To address these issues, the researchers integrated "signal temporal logic" or STL to evaluate the quality of demonstrations and automatically rank them to create inherent rewards.

In other words, even if some parts of the demonstrations do not make any sense based on the logic requirements, using this method, the robot can still learn from the imperfect parts. In a way, the system is coming to its own conclusion about the accuracy or success of a demonstration.

"Let's say robots learn from different types of demonstrations -- it could be a hands-on demonstration, videos, or simulations -- if I do something that is very unsafe, standard approaches will do one of two things. Either they will completely disregard it, or even worse, the robot will learn the wrong thing," said co-author Stefanos Nikolaidis, a USC Viterbi assistant professor of computer science.

"In contrast, in a very intelligent way, this work uses some common-sense reasoning in the form of logic to understand which parts of the demonstration are good and which parts are not. In essence, this is exactly what humans do."

Take, for example, a driving demonstration where someone skips a stop sign. This would be ranked lower by the system than a demonstration of a good driver. But, if during this demonstration, the driver does something intelligent -- for instance, applies their brakes to avoid a crash -- the robot will still learn from this smart action.

Adapting to human preferences
Signal temporal logic is an expressive mathematical symbolic language that enables robotic reasoning about current and future outcomes. While previous research in this area has used "linear temporal logic," STL is preferable in this case, said Jyo Deshmukh, a former Toyota engineer and USC Viterbi assistant professor of computer science.

"When we go into the world of cyber physical systems, like robots and self-driving cars, where time is crucial, linear temporal logic becomes a bit cumbersome, because it reasons about sequences of true/false values for variables, while STL allows reasoning about physical signals," said Deshmukh.

Puranic, who is advised by Deshmukh, came up with the idea after taking a hands-on robotics class with Nikolaidis, who has been working on developing robots to learn from YouTube videos. The trio decided to test it out. All three said they were surprised by the extent of the system's success, and the professors both credit Puranic for his hard work.

"Compared to a state-of-the-art algorithm being used extensively in many robotics applications, you see an order of magnitude difference in how many demonstrations are required," said Nikolaidis.

The system was tested using a Minecraft-style game simulator, but the researchers said the system could also learn from driving simulators and eventually even videos. Next, the researchers hope to try it out on real robots. They said this approach is well suited for applications where maps are known beforehand but there are dynamic obstacles in the map: robots in household environments, warehouses, or even space-exploration rovers.

"If we want robots to be good teammates and help people, first they need to learn and adapt to human preference very efficiently," said Nikolaidis. "Our method provides that."

Source: University of Southern California

Published November 2020

Rate this article