IIoT is the future of workplace safety (Authentise Weekly News-In-Review – #118)

The increasingly connected systems in place at the factory floors are enabling safer workplaces. The most straightforward approach here is to don workers with sensors that can detect hazardous environment parameters like air quality and temperature or even automatically alert someone if they are injured. In most cases, however, it’s about bypassing the need for human workers to do dangerous tasks. Technologies like predictive analytics can do tremendous work in alerting supervisors before parts get broken and become hazards. Similar smart systems need to be put in place when cooperative robotics start working alongside human counterparts. Using machine learning and computer vision, safety can be guaranteed as robots can have comprehensive knowledge of their surroundings and predict human actions, as well as maximizing the robot’s effectiveness.

Using IIoT-Connected Devices for Worker Health & Safety

IBM announced collaborations with Garmin, Guardhat, Mitsufuji and SmartCone to help organizations monitor their workers’ safety with Watson IoT. Source: IBM

Workplace safety is important in any field. For example, in my line of work, I’m always vigilant of dangers from hot coffee, eye strain, or paper cuts. But in industrial environments such as the manufacturing, petrochemical, or mining industries, the potential dangers are more severe. That’s why researchers and engineers are exploring new ways to use industry 4.0 technology to protect the health and safety of industrial workers.

Read the full article here.

How IoT and Computer Vision Can Enhance Industrial Safety

Welder's safety is protected by IoT

Using IoT sensors can feed the algorithm with real-time data and allow it to make decisions on the spot. For example, if sensors detect gas leakage, increased temperatures or unwanted humidity, work can stop at once or at the very least inform the floor manager. These type of decisions are deterministic and don’t provide much insight into the future. Another way of creating a safer environment is to use the power of computers and machine learning. By creating different scenarios, the algorithm can sense the difference between what is safe and what is not.

Read the rest here.

Collaborative Robots Learn to Collaborate

An automated mobile robot (AMR) uses 3d vision and machine learning to navigate in a more natural manner past a person moving a cart in a warehouse aisle.

To be truly collaborative, robots must be capable of more than working safely alongside human beings. Russell Toris, director of robotics at Fetch Robotics, says robots also need to act (and “think”) more like people. This is particularly true of autonomous mobile robots (AMRs) like those manufactured by Fetch. Typically employed for material transport and data collection (such as counting inventory), these wheeled systems use vision sensors and navigation software to dynamically adapt to new environments and situations. Increasingly common in warehouses and distribution centers, this technology is likely to spread to other applications and industries, including our own.

Read the full article here.

 

Follow us on Twitter to keep updated on AM & IIoT related news as well as updates to Authentise’s services!

Data is king: what to expect from AMUG (Authentise Weekly News-In-Review – #115)

AMUG is here! We’re in the Expo at booth B37, come to say hi to our team!

Although not all AM companies have already revealed their cards right from the get-go, we already have a feeling for what is going to be a strong trend at this year’s user group event: data. Hardware has come to the point where optimizations need to happen elsewhere to see true production AM come to fruition. That means using smart frameworks and analytical software to iron out the deficiencies, making AM into a reliable production tool. Identifying defects before printing ever happens is key to minimize time and material loss. A collaboration between AlphaSTAR & Raytheon has created a workflow for the qualification of missile parts, thus not only perfecting the manufacturing process but also guaranteeing a part that is up to industry standards. We at Authentise have very recently announced a partnership with Microsoft to enable intuitive automations from within their Flow platform, further enhancing the power of our customer’s digital thread. Our guess is that it’s not the last we’ll hear of movement in data strategies from the event. Big players are investing more and more into machine learning and AI projects to get new insights into their operations and potential new avenues for innovation.

AlphaSTAR & Raytheon to present ‘Qualification of an AM Missile’ at AMUG 2019

[…] AlphaSTAR Corporation and Raytheon have cooperated on a project to predict the Additive Manufacturing Process and Service Loading of an as-built additively manufactured part. Using an ICMSE framework, and feeding through a building block Verification, Validation and Accreditation (VVA), the teams set out with the goal of identifying part issues before building the component, thus saving time, lowering risk and reducing scrap rate.

Read the full article at Metal AM.

Authentise Empowers Manufacturing Operators through Collaboration with Microsoft

Active Flow

Authentise has agreed to a multi-year collaboration with Microsoft to utilize Microsoft Azure and integrate Authentise’s workflow management system into Microsoft Flow. The integration with Flow, which goes live this week on the Microsoft Flow Gallery, gives operators directly involved in additive manufacturing quoting, production and analytics processes the opportunity to create their own automations without any coding knowledge.

Read the full press release here.

McDonald’s Bites On Big Data With $300 Million Acquisition

McDonald’s is set to announce that it has reached an agreement to acquire Dynamic Yield, a startup based in Tel Aviv that provides retailers with algorithmically driven “decision logic” technology. When you add an item to an online shopping cart, it’s the tech that nudges you about what other customers bought as well.

Read the full article on Wired.

 

Follow us on Twitter to keep updated on AM & IIoT related news as well as updates to Authentise’s services!

The problems, and solutions, to the IIoT (Authentise Weekly News-In-Review – #110)

The Industrial Internet of Things (IIoT) is taking hold on many industrial settings, and yet we are still far from reaping its true benefits. There are multiple reasons for this, and they have to do with the technical limitations of dealing with a large number of sensors and data, how to interpret it correctly and efficiently and how to create a reliable mesh network to tie it all together. AI may look promising for data handling and predictive systems. However, there are many angles to iron out before these make feasible solutions. AI’s prowess on self-teaching may fall short when, to be useful, it would have to learn and predict countless possibilities of a complex industrial setting. Established technologies, or novel combinations of them, can bring exciting opportunities to the table. RFID tagging for warehouse traceability is a dream come true for spoiling inventories while merging long-range connectivity with cloud services can satisfy a large portion of IIoT applications.

How IIoT and RFID deal with perishable inventory

Screen Shot 2019-02-25 at 11.17.42 AM

In North America alone, billions of dollars of food spoil before reaching customers each year. In the pharmaceutical industry, temperature-sensitive products are regularly damaged due to inappropriate shipping and storing conditions. To gain better visibility into the location and the condition of perishable inventory items, businesses can turn to RFID and IIoT technologies.

Read the full article at Smart Industry.

Is Artificial Intelligence the Answer for IIoT?

Many AI methods are self-taught, so they avoid the need for process mapping and other tedious analytical processes, making it seem to be the right fit for IIoT. Yet, only a few methods will apply. The most useful methods are not greedy for impossible amounts of data. They focus machine learning in explainable ways. The rest will fail badly.

Read more here.

Using LoRa and Google Cloud for IIoT Applications

Image of a gateway communicating with the cloud on LoRa

Pairing LoRa connectivity with the Google Cloud Platform (GCP) can serve a wide range of industrial IoT (IIoT) use cases. The longevity and resilience of LoRa paired with GCP’s robust architecture and commitment to scalable innovation provides industrial operators with the tools they need to build the world of tomorrow.

Read more here.

 

Follow us on Twitter to keep updated on AM & IIoT related news as well as updates to Authentise’s services!

How AI is changing the face of manufacturing, and much more (Authentise Weekly News-In-Review – Week 85)

As AI is getting a foothold in pretty much every corner of the digital world, industries like manufacturing have a lot to gain by employing its perks. We at Authentise know very well the power of machine learning and the many other tools that enable our customers to get deeper, insightful looks into their production and save time in production. The next generation in Additive AI will likely be in-print monitoring platforms. The way these technologies are affecting every industry scared people into thinking that there’s going to be less room for human employees. Not only will there be value in the collaboration between humans and AIs, but new types of jobs will be created because of it. On a side note, it’s also interesting to see how 3D printing is enabling new computing paradigms to be researched, closing the loop beautifully.

Kansas State University Researchers Develop AI System For 3D Printing Process Monitoring

Researchers from Kansas State University’s Department of Industrial and Manufacturing Systems Engineering (IMSE) have developed a new quality monitoring system for the 3D printing process. With integrated supervised machine learning, a camera, and image processing software, the researchers created a production quality monitoring system for assessing 3D printed parts in real-time.

Read the full article here.

New Supply Chain Jobs Are Emerging as AI Takes Hold

Companies are cutting supply chain complexity and accelerating responsiveness using the tools of artificial intelligence. Through AI, machine learning, robotics, and advanced analytics, firms are augmenting knowledge-intensive areas such as supply chain planning, customer order management, and inventory tracking. What does that mean for the supply chain workforce? It does not mean human workers will become obsolete. In fact, a new book by Paul Daugherty and H. James Wilson debunks the widespread misconception that AI systems will replace humans in one industry after another. While AI will be deployed to manage certain tasks, including higher-level decision making, the technology’s true power is in augmenting human capabilities — and that holds true in the supply chain.

Read the rest at Harvard Business Review.

This AI Calculates at the Speed of Light

Researchers from UCLA on Thursday revealed a 3D-printed, optical neural network that allows computers to solve complex mathematical computations at the speed of light. […] researchers believe this computing technique could shift the power of machine learning algorithms, the math that underlies many of the artificial intelligence applications in use today, into an entirely new gear.

Read the full article at Discover Magazine.

Follow us on Twitter to keep updated on AM & IIoT related news as well as updates to Authentise’s services!

Can Data Connectivity Catapult AM Forward? (Authentise Weekly News-In-Review – Week 76)

AM is a manufacturing technology like many other but, unlike most, has numerous variables at play in making the final part. Most are controlled by the initial setup by the lab technician, but after that there is very little that goes in the way of making sure that the best result is achieved. In-print monitoring is crucial yet still hard to apply properly. Techniques like machine learning enable automated pinpointing of potential issues, stopping before precious time and resources are wasted. This will be made possible thanks to a slew of sensors that power computer-vision algorithms. The bandwidth required for these applications will be huge, something that coming 5G networks will be able to support, together with other IIoT applications previously impossible. In the future, self-correcting printers will make AM much more reliable and efficient. There is already so much that the data coming from printers can teach to improve operational performance. At Authentise we have developed smart analytical tools to help you leverage all that data, and are now moving towards letting you control printer directly, with remote and automated tools.

Machine Learning and Metal 3D Printing Combine for Real-Time Process Monitoring Algorithm

Two researchers from the College of Engineering at Carnegie Mellon University (CMU) have figured out how to combine 3D printing and machine learning for real-time process monitoring, a practice which can detect anomalies inside a part while it’s being 3D printed. Their research could one day lead to self-correcting 3D printers.

Read the full story here.

New whitepaper examines smart metrology for additive manufacturing

If factories are to become faster and more flexible, inspection is a bottleneck to overcome, especially in industries where 100% inspection is required. In this new whitepaper by Autodesk and Faro, smart metrology for the additive manufacturing industry. Components made by additive manufacturing technologies (AM) have more variables than machined parts. Faster inspection for additive manufacturing is more challenging because AM processes are not as accurate as cutting metal. Better metrology for AM will help reduce feedstock and costs.

Check out the whitepaper here.

How Will 5G Change Robotics and the IIoT?

As efficient and effective as 4G technology is, it pales in comparison to the faster, more reliable platform of 5G. If the new protocol meets its advertised speeds of 100 gigabits per second, this rates 5G at a speed of 1,000 times faster than 4G. Given the increasing size of datasets, the greater need for real-time data processing and more reliance on large-scale and long-term data storage, it’s easy to see how 5G benefits everyone.

Read the full article here.

 

Follow us on Twitter to keep updated on AM & IIoT related news as well as updates to Authentise’s services!

Rapid + TCT

We are going to be present at this year’s Rapid + TCT show from the 23rd to 26th of April in Fort Worth, Texas.

Our CEO Andre Wegner and Software Engineer Anusha Iyer will hold a speech titled “Machine Learning in Additive Manufacturing (Intermediate)”.

When: Wednesday, April 25

Time: 1:00 PM – 1:25 PM

Please don’t hesitate to reach us if you wish to discuss the future of AM production.

Business inquiries: Frank Speck, CMO – frank@authentise.com

The Trifecta of Manufacturing Agility: Software, Hardware and the IIOT (Authentise Weekly News-In-Review – Week 65)

The world of today’s economy requires businesses to keep a quick pace with the demands of the market. The globalization of products and services made it so that, to stay competitive, product iteration and deployment must be quick and effective. Fortunately, we have the technological foundation to enable this kind of model. A combination of hardware, software and analytical tools put businesses in the position to close the iterative circle of prototyping and manufacturing in a lean fashion. Manufacturing technologies like 3D printing and hybrid manufacturing platforms give the tools needed to experiment and ultimately produce finished goods for almost any circumstance. The digital world we have weaved enables CAD and software to travel and be shared, creating an ecosystem in which everyone is uplifted. Finally, the IIoT is empowering everyone through the might of data-driven insights, interconnecting information hotspots and putting processing power to work on spotting operational inefficiencies.

Engineers Create 4D Printer that Combines Four 3D Printing Techniques

Engineers Create 4D Printer that Combines Four 3D Printing Techniques

[3D printing] Still somewhat in its infancy, the last decade has witnessed a generous body of research that seeks to exploit its uses more than we could have ever imagined. One example comes from a team from the Georgia Institute of Technology, led by Professor H. Jerry Qi from the University’s George W. Woodruff School of Mechanical Engineering. Their aim was simple: 4D printing. Or put in a different way, to create a machine that combines multiple materials into one 3D printer.

Read the full article here and the paper here.

3D Life Launches 3D Anatomical Heart Library

Justin Ryan, Research Scientist at the Cardiac 3D Print Lab, Phoenix Children’s Hospital, holds a 3D printed heart model. Photo via Philips USA.

[3D Life] are meeting the demand for anatomical models by launching a 3D anatomical heart library, providing medical professionals with access to 3D printing. The USA’s National Institutes of Health offers a similar library covering a broader range of medical models freely available as .STL files, but without the printing services offered by 3D Life.

Leonardo Bilalis, Design Engineer, hopes that the library will promote “better knowledge of [how 3D printed] organs can be used for surgery preparation for complex problems”, “making operations shorter and more efficient.”

Read more about it here.

IIoT Analytics are Just Numbers, Unless You Solve a Business Problem

IIoT-Analytics-are-Just-Numbers-Unless-You-Solve-a-Business-Problem

There is lots of excitement about analytics and machine learning. It’s moving through its hype-cycle but still faces many challenges. Putting aside other challenges, solving real business issues is still a major shortcoming. If your reporting and analytics is counting “things” – just buy a calculator. Find a business problem to solve, and then you will see real value.

 

Read the full article here.

 

Follow us on Twitter to keep updated on AM & IIoT related news as well as updates to Authentise’s services!

5 Ways You Can Use Data to Improve Your Additive Manufacturing Operations in 2018

In the run-up to the New Year, we’re summarizing our key learnings of 2017 into a quick checklist for your 2018 Additive Manufacturing IT endeavors. Taking these seriously will reduce your Total Cost of Ownership and make sure you are production ready.

Let’s start with the easiest:

 

Performance Measurement

The simplest initiative is to start measuring your Overall Equipment Efficiency, Failed Build levels or other Key Performance Indicators using data from your machines. With our Machine Analytics module, you can start today with an existing dashboard or incorporate the data into your own solutions.

 

Transparency

Many of you work in organizations that already operate many printers, though you might not know where they are, what they do and how often they do it. Using device data to track your assets and processes is the first step to creating a more transparent network and learning from your experience. Our Machine Analytics module includes a Gantt chart of all historical prints fed simply by data from machines.

 

Process Automation

To see immediate ROI from your data, start by identifying manual steps you could cut out with data: How can your sales team see when the printers are available? Can we alert customers or sales teams automatically if the print fails or once it goes into production? These and many other options are part of our MES solution.

 

Traceability

Additive production has many advantages over subtractive and other processes. Among them is your level of data access – let’s use it. Provide all required traceability documentation – and more – to your customers by extracting data from the machines and digitalizing process events. MES does this, and we’re augmenting it every day: We’re excited about announcements forthcoming in 2018.

Quality

This, of course, is the big one: Using all the data generated to draw conclusions about quality that could influence the incidence of testing. There’s still plenty of work to do, but it is never too late to start developing strategies to capture all that data in order to make the necessary abstractions.

 

Call us to discuss how we can help you optimize data to improve your additive manufacturing process in 2018. The industry has tremendous opportunities if we use it wisely.

Merry Christmas and a Happy New Year from the Authentise Team!

Machine-Driven Performance for the Digital Thread (Authentise Weekly News-In-Review – Week 32)

Machine-learning methods are transforming image recognition and problem-solving skills in computers with hardware and simulation algorithms that are capable of providing actionable insights. Businesses are already starting to employ these new tools to gain a more efficient and productive workflow, automating the digital thread beyond simple dematerialization, as well as stepping into smart decision-making.

Machine Learning “Surfnet” Creates 3D Models From 2D Images

The SurfNet process. Image via Purdue University Mechanical Engineering.
The SurfNet process. Image via Purdue University Mechanical Engineering.

New research has developed AI technology that can transform 2D images into 3D content. The method, called SurfNet, has great potential in the field of robotics and autonomous vehicles, as well as creating digital 3D content. The research was led by Purdue University’s Donald W. Feddersen Professor of Mechanical Engineering, Karthik Ramani.

Karthik Ramani explains this process:

“If you show it hundreds of thousands of shapes of something such as a car, if you then show it a 2D image of a car, it can reconstruct that model in 3D”.

Read more about Surfnet here.

 

MIT’s Robotic Arm 3D Printers Take The Stress Out of Architecture

4 self-supporting gridshell test designs, 3D printed in plastic using a robotic arm. Image via 3D Printing and Additive Manufacturing journal.

Stress Line Additive Manufacturing (SLAM) is an architectural 3D printing concept out of MIT. It challenges the typical FDM approach to construction, accounting for structural stresses caused by the act of depositing material layer-by-layer. […] In further development, the researchers will apply further architectural theory to the designs and make solid filled objects. They also hope to be able to integrate sensors into the system so the robotic arm intelligently adapts the design as it prints.

Read more about it at 3D Printing Industry.

 

Geometric search engines – How useful are they?

Digitisation presents challenges as well as opportunities: On the one hand we’re surrounded by more data than ever before, yet on the other, we have more efficient tools to manage the onslaught. […] In the process of searching for similar designs, while we have traditional search methods like text based and keyword based, they do fall short at times. Geometric Search Engines (GSEs) can significantly improve speed and efficiency of the digital thread in additive manufacturing to help solve these challenges.

Read the full article at Develop3D.

 

Don’t forget to come back next week for another news’ roundup. In the mean time, our Twitter feed should keep you updated with the latest AM/IIoT news!