Using Data Models to Infer Root Causes
Capturing this week's zeitgeist
From “Lockheed Martin 3D Prints F-35 Simulator Cockpits”
“It’s a good representation of the capability of additive manufacturing and what the team can do when all of the functions work together. It also paves the way for any future large additive programs. With F-35 and F-16, we have a good baseline for what our capabilities are, and now we are diving deep into understanding how we can eliminate defects, streamline processes and increase efficiency”, shared Jared Stewart, Hardware Engineer Staff.
From “Microsoft Kills Its Industrial Metaverse Team After 4 Months”
In a surprising reversal, Microsoft has killed a team it formed four months ago to help customers use the metaverse in industrial settings, according to a person with direct knowledge of the matter. The group’s roughly 100 employees have all been laid off, the person said.
This week's most influential Industry 4.0 media
Using Data Models to Manage Your Digital Twins
A continuously evolving industrial knowledge graph is the foundation of creating industrial digital twins that solve real-world problems. Industrial digital twins are powerful representations of the physical world that can help you better understand how your assets are impacting your operations. A digital twin is only as useful as what you can do with it, and there is never only one all-encompassing digital twin. Your maintenance view of a physical installation will need to be different from the operational view, which is different from the engineering view for planning and construction.
Manufacturing Process Optimization in Times of Adversity
For the current era, we can usefully define manufacturing process optimization like this:
- Digitally connected plant teams learning and implementing data-driven strategies that impact their manufacturing processes to minimize cost and maximize production toward peak operational efficiency.
- Using data-to-value technologies that integrate seamlessly with their legacy systems and progressively automate an end-to-end, continuous improvement, production loop — freeing manufacturers from a reactive troubleshooting paradigm so they can layer in further innovations toward the smart factory.
Through the above process, machine learning workflows are able to solve current generation data-readiness and production process optimization issues while future-proofing operations. By easing cost pressures and driving up revenue via data-driven production efficiencies (and with increasingly data-mature plant personnel), the C-suite is free to develop strategies with innovation managers. Together, they can combat the broader external challenges experienced by many manufacturers today.
Boehringer Ingelheim: Healthy data creates a better world
⭐ Hunting For Hardware-Related Errors In Data Centers
The data center computational errors that Google and Meta engineers reported in 2021 have raised concerns regarding an unexpected cause — manufacturing defect levels on the order of 1,000 DPPM. Specific to a single core in a multi-core SoC, these hardware defects are difficult to isolate during data center operations and manufacturing test processes. In fact, SDEs can go undetected for months because the precise inputs and local environmental conditions (temperature, noise, voltage, clock frequency) have not yet been applied.
For instance, Google engineers noted ‘an innocuous change to a low-level library’ started to give wrong answers for a massive-scale data analysis pipeline. They went on to write, “Deeper investigation revealed that these instructions malfunctioned due to manufacturing defects, in a way that could only be detected by checking the results of these instructions against the expected results; these are ‘silent’ corrupt execution errors, or CEEs.”
Engineers at Google further confirmed their need for internal data, “Our understanding of CEE impacts is primarily empirical. We have observations of the form, ‘This code has miscomputed (or crashed) on that core.’ We can control what code runs on what cores, and we partially control operating conditions (frequency, voltage, temperature). From this, we can identify some mercurial cores. But because we have limited knowledge of the detailed underlying hardware, and no access to the hardware-supported test structures available to chip makers, we cannot infer much about root causes.”
📦 How AWS used ML to help Amazon fulfillment centers reduce downtime by 70%
The retail leader has announced it uses Amazon Monitron, an end-to-end machine learning (ML) system to detect abnormal behavior in industrial machinery — that launched in December 2020 — to provide predictive maintenance. As a result, Amazon has reduced unplanned downtime at the fulfillment centers by nearly 70%, which helps deliver more customer orders on time.
Monitron receives automatic temperature and vibration measurements every hour, detecting potential failures within hours, compared with 4 weeks for the previous manual techniques. In the year and a half since the fulfillment centers began using it, they have helped avoid about 7,300 confirmed issues across 88 fulfillment center sites across the world.
On the way to the industrial Metaverse
A recent Capgemini Research Institute report explored this potential in more depth; Total Immersion; How immersive experiences and the metaverse benefit customer experience and operations, found that 77% of consumers expect immersive experiences to impact how they interact with people, brands and services, but also that organizations recognize the broad opportunities it presents to drive value across the business, specifically in their internal operations.
As opposed to the static spaces of the consumer metaverse, the dynamic spaces of the industrial metaverse are complex and layered. This ever-evolving reality involves interactions on a deeper, more collaborative level. We suggest the dynamic experiences of the industrial metaverse are best exemplified by the next generation of digital twin technology.
Innolux, MiR250, Taiwan
Fast Recognition of Snap-Fit for Industrial Robot Using a Recurrent Neural Network
Snap-fit recognition is an essential capability for industrial robots in manufacturing. The goal is to protect fragile parts by quickly detecting snap-fit signals in the assembly. In this letter, we propose a fast recognition method of snap-fit for industrial robots. A snap-fit dataset generation strategy of automatically acquiring labels is presented in the presence of data collection is complicated. A multilayer recurrent neural network (RNN) is designed for snap-fit recognition. An extensive evaluation based on two different datasets shows that the proposed method makes reliable and fast recognitions. Real-time experiments on industrial robot also demonstrate the effectiveness of the proposed method.
Weekly mergers, partnerships, and funding events across industrial value chains
🖨️ Venture Investors Are Pumping Capital Into 3-D Printing Startups. Here’s Why.
Investors are drawn to these companies because they are on the verge of being able to use their technology to manufacture components at scale for critical sectors such as semiconductors and aerospace. For many, that would mean transforming from being a niche product manufacturer to being a mass producer, investors say.
Investors are also attracted to these startups’ ability to provide industrial companies with a simpler supply chain, which could help them address parts shortages amid geopolitical challenges and reduce dependency on foreign suppliers, Prof. Toyserkani said. Additive manufacturing startups also say their methods can help companies cut costs and have lower environmental impacts because less waste goes into producing things, he added.
🖨️ Fabric8Labs Closes $50M Series B Financing for Electrochemical Additive Manufacturing Technology
Fabric8Labs, pioneer of electrochemical additive manufacturing, today announced the close of a $50M Series B investment round led by New Enterprise Associates (NEA), with participation from existing investors, including Intel Capital, imec.XPAND, SE Ventures, TDK Ventures, and Lam Capital. The new infusion of capital will be used to scale the company’s proprietary Electrochemical Additive Manufacturing (ECAM) technology and establish a pilot production facility.
🔋♻️🚙 Redwood Materials lands $2B conditional loan from DOE
Battery materials and recycling startup Redwood Materials has secured a conditional commitment for a $2 billion loan from the Department of Energy as part of the Biden administration’s bid to build up a supply chain for EVs in the United States. This latest financial boost will help Redwood reach its goal to produce 100 GWh annually of ultra-thin battery-grade copper foil and cathode active materials from both new and recycled feedstocks — enough battery materials to domestically produce more than a million electric vehicles a year.
🔋🚙 Ionblox increases Series B to $32m with investment from Lilium, Applied Ventures, Temasek and Catalus Capital
Ionblox, a next-generation lithium-ion battery company announced a second close of its Series B round at an increased $32 million. Strategic partners include original investors Lilium and Applied Ventures who were joined by Temasek and Catalus Capital. The company will use the increased Series B funding to scale its technology, develop advanced high-power cells for electric aviation, and prototype fast-charge cells for Electric Vehicles.
🔋🚙 Liminal Raises $17.5 Million in Series A2 Funding to Catalyze Production of Safe, Reliable, High-Quality EV Batteries
Liminal, a battery manufacturing intelligence company, today announced a $17.5 million Series A2 funding round, led by climate tech fund ArcTern Ventures, joined by new investors Northvolt and Ecosystem Integrity Fund, and with continued support from Chrysalix Venture Capital, Good Growth Capital, University of Tokyo Edge Capital Partners, Volta Energy Technologies, Impact Science Ventures, and Helios Climate Ventures. Liminal will use this funding to scale its EchoStat® inspection systems into factory-integrated solutions for global battery manufacturers, tapping into the rapidly growing demand for safe, reliable, and more affordable EV batteries.
Industrial Cybersecurity Innovator Opscura Receives $9.4M in Series A Funding as Critical Operations Transform
Opscura Inc., an innovator in industrial control system (ICS) cybersecurity, announced today it has received $9.4M in Series A funding as it scales to engage further U.S. partners and customers seeking to protect and connect their critical operations. Founded in Spain as Enigmedia, the new global entity Opscura is also launching a new brand, global management team, and product upgrades in addition to the capital infusion led by Anzu Partners, with investments from Dreamit and Mundi Ventures.
Opscura’s technology adds a unique layer to the industrial cybersecurity ecosystem as manufacturers require greater efficiencies to protect thousands of vulnerable legacy devices they cannot take offline, and as the rapid build-out of new renewable energy critical infrastructure continues. To reduce the pervasive risks of ransomware, unauthorized access, and data theft, Opscura’s patented cloaking technology obscures deeper operational technology (OT) Level 2 network and Layer 2 data without disrupting operations.
✈️ Aviation startup Aiir Innovations raises over €2M to transform engine maintenance
Aiir Innovations, a leading startup in artificial intelligence (AI) for the visual inspection of aircraft engines, has raised €2.1M in an oversubscribed investment round. Led by VC fund Borski Fund, with the participation of HearstLab Europe and existing shareholder Mainport Innovation Fund. Aiir Innovations will use the investment to grow its remote-first team and expand globally, and set a new standard for engine inspections. Bart Vredebregt, CEO & Co-Founder, added “We are excited to work with investors that have a global reach and share our vision on company culture and diversity.”
⚗️🧠 Mattiq Launches With Revolutionary Approach to Developing Sustainable Materials
Mattiq, the developer of a revolutionary approach to sustainably produce chemicals and fuels poised to transform industries from energy to consumer products, today announced its launch alongside securing $15 million in seed funding, led by Boston-based venture capital firm Material Impact. Formerly known as Stoicheia, Mattiq also announced it has hired veteran Silicon Valley executive and entrepreneur Jeff Erhardt as Chief Executive Officer.
By synthesizing and evaluating millions of potential combinations in parallel, Mattiq’s integrated technology platform streamlines the historically fragmented development of novel materials powering a variety of products and solutions. At the same time, this work generates unprecedented amounts of high quality data that is enabling Mattiq to build the world’s most powerful materials AI.
RIIICO secures $1.5 million to advance AI-powered digital twins in manufacturing
German startup RIIICO has raised $1.5 million in a pre-seed funding round led by Earlybird Venture Capital and US-based investors to push AI-driven digital twin creation forward. RIIICO’s advanced segmentation AI and meshing algorithms help manufacturers to translate their shopfloor reality directly into a transparent digital 3D model. The results are used across the factory software landscape for simulating the virtual start of production or different VR and AR applications.