Category

Fledge

Winning GT3 Racing with LF Edge’s Fledge

By Blog, Fledge, Use Cases

Optimizing machine operations using Industrial IoT Fledge with Google Cloud, ML and state-of-the-art digital twins and simulators

Gradient Racing is a professional auto racing team based in Austin, Texas.  One of Honda’s customers for NSX GT3 Evo, Gradient is committed to using cutting edge technology to gain an edge in GT racing.

Modern race cars have thousands of adjustable parameters in their suspension, aerodynamics, transmission and other systems.  Finding the perfect configuration of these parameters for a given driver, track and race strategy is key to winning races. In GT racing, this has been more art than science, with drivers making multiple test runs and working with the race team to adjust the car based on feel.

Like Formula One and Nascar, Gradient wanted to bring state-of-the-art simulation technology to bear on this problem, believing that it would allow them to configure the car far more precisely. To do this, they engaged Motorsports.ai, a leader in racing modeling.

Creating a Virtual Racing Environment

Motorsports.ai’s goal was to create a full simulation environment of the race: a simulated driver, a simulated car and a digital twin of the track.  While car simulation software was commercially available, Motorsports.ai decided to use machine learning technology to develop an AI driver that would react to conditions in the same way as Gradient’s human driver.

Motorsports.ai deployed the Linux Foundation’s Fledge for three functions.  First, to collect the massive amount of data required to train the machine learning system. Second, to validate the race simulations of car, driver and track.  Last, to help validate the digital twin of each race track.  Originally developed by Dianomic Systems, Fledge joined LF Edge, an umbrella organization that aims to establish an open, interoperable framework for edge computing independent of hardware, silicon, cloud, or operating system, last year. Fledge is an open-source Industrial IoT framework to collect sensor data, enhance it with meta information, run ML models on the edge and reliably transport data  to central or cloud-based processing systems. In a matter of weeks, Motorsports.ai developed the plugins needed to interface Fledge with the race car’s CAN Bus and Eclipse Cyclone DDS interfaces to over 2000 in-car sensors..

The human driver made multiple test runs on the track to determine his reaction to different conditions. Twenty times a second, Fledge collected readings on every aspect of car performance, as well as driver actions such as gas pedal and brake pressure, steering angle and gear changes.  Fledge enhanced each reading with the precise timestamp and GPS location of the car on the track.  Overall, Fledge collected more than 1GB of data on each test run, which it buffered and automatically transmitted to Google Cloud at the end of the run.  Motorsports.ai fed this data into TensorFlow running on a 20 node Google Kubernetes Engine cluster to validate the digital twin, and improve the accuracy of the predictions.

To build the model, Motorsports.ai integrated Fledge into a highly accurate simulation, and virtual prototyping environment to collect the same data as was collected in the physical car. Using TensorFlow, they then run distributed machine learning jobs using the KubeFlow framework on the aforementioned kubernetes cluster. Fledge is used to manage the sensor data from both the actual and virtual track runs. Motorsports.ai uses these results to provide predictions that ensure a competitive performance.

A key attribute for a digital twin is validation, and verification, which in this case requires precise mapping of the track surface type. The coefficient of friction between the car’s tires and track varies at each venue, the surface could be asphalt, concrete, painted, or all of the above. To identify the surface type for the digital twin, an Intel RealSense camera was deployed on the car, oriented to the track.  ML models running on the NVIDIA Jetson Xavier platform were then used to identify surface categories while Fledge added the telemetry, and timestamp to the ML models surface type category predictions.

Winning the Race

Gradient used the Motorsports.ai simulation to optimize suspension and alignment settings for every race in 2019.  The simulation enabled far more rigorous tuning than their previous manual method.  Instead of building a configuration based on a few laps and driver “feel”, they were able to run tens of thousands of simulations using precise measurement.  They were able to investigate conditions that had not yet been experienced on the actual track and ensure that they could compete effectively in them.

For example, for tire camber alone they ran 244 simulations, testing the camber of each tire at 0.1° increments through a range of -3.0° to +3.0°.  All told, Gradient simulated more than 10,000 track runs for each race, orders of magnitude more than would have been possible using a human driver.

The results showed on the scoreboard. Gradient broke the Circuit of the Americas track record by over 1.1 seconds and the Mid-Ohio Sports Car Course record by more than 1 second. They continued their success at other races and took home the national GTB1 championship title of the 2019 Pirelli Triple Trofeo.

To learn more about Fledge, visit https://www.lfedge.org/projects/fledge/, get the code here, or engage with the community on Slack (#fledge).  To learn more about LF Edge, visit https://www.lfedge.org/.

LF Edge Member Spotlight: Dianomic

By Blog, Fledge, Member Spotlight

The LF Edge community is comprised of a diverse set of member companies that represent the IoT, Enterprise, Cloud and Telco Edge. The Member Spotlight blog series highlights these members and how they are contributing to and leveraging open source edge solutions. Today, we sat down with Tom Arthur, CEO at Dianomic, and one of the creators of Fledge, to discuss the importance of a growing ecosystem, their Industrial IoT framework, the impact LF Edge has made and what the future holds for the company.

Can you tell us a little about your organization?

Our company name is Dianomic Systems.  It is derived from the Greek word dianomi meaning distribution.  As you may have guessed, edge computing is a challenging distributed computing problem.

The fragmentation and distribution of industrial data, networking, processing, security and storage makes managing it complicated.  Simplifying industrial IoT application and system development with a ubiquitous open source stack, standards, and community is our mission.

With our community, we created FogLAMP in 2018 then contributed all the code to the LF Edge’s Project Fledge to help address the industrial data problem.  Fledge is a stack of integrated microservices that operate from sensor to cloud (the edge).  These services connect any sensor or machine data, aggregate data, buffer data, transform data, filter data, execute AI/ML operations, alert, visualize and forward data to any cloud or on-prem destination.

 

Why is your organization adopting an open source approach?

 The LAMP stack is largely responsible for the success of web application development.   Almost every web, ecommerce and social network developer consumed it.  Dianomic believes a similar open source stack is required for Operational Technology (OT) to help drive Industrial 4.0 application development.   This is the Fledge community’s mission.

We already have several public use cases and many not yet public proving the open source approach works.

At Jacksonville Energy Authority (JEA), they deployed Fledge to monitor substation transformer’s oil pumps, oil temperature, cooling fans, ambient air temperature and hydrogen gas.  They are now also testing infrared cameras to monitor heat other heat sources in the substation and in their water business monitoring pumps and bearings.   Using Fledge’s PHP based plugin architecture they developed a KAFKA north connection to be their single pub-sub system for all their IIoT data requirements.   The goal is complete predictive and conditional monitoring of all non-SCADA systems.  This KAFKA north service was then contributed to the Fledge stack for the community and supported by Dianomic.   Fledge is then tightly integrated with both their OSIsoft PI systems (that monitors SCADA and DCS systems) and their Oracle ERP and maintenance systems.

At General Atomics (a General Dynamics spin-out), the maker of the U.S. Airforce’s Predator drone, Fledge is used to help monitor the manufacturing quality of the fuselage, wings and stabilizers.   These components are made of composites where heat and humidity are tightly controlled.   Fledge is used with industrial grade explosion proof sensors to “green light” a process once appropriate temp and humidity levels are achieved.  Once again, using the plugin architecture, GA was able to tightly integrate the data and events with systems monitoring the rest of the factory keeping track of everything in context of the entire aircraft being built.   These integrations are also part of the Fledge stack today. 

Why did you join LF Edge and what sort of impact do you think LF Edge has on the edge, networking, and IoT industries?

There is no better organization to help govern, build communities and market the benefits of a Linux based OT equivalent of the LAMP stack.

What do you see as the top benefits of being part of the LF Edge community?

Working hand-in-hand with the premier computing, data management and networking companies that share the same passion and vision for open source projects to fundamentally help industrial developers build better machines, plants, factories and businesses.

What sort of contributions has your team made to the community, ecosystem through LF Edge participation?

Dianomic, Google, OSIsoft, industrial system integrators and industrial companies have all contributed to Fledge.  The LF Edge’s project Fledge started when Dianomic contributed the entire FogLAMP stack in winter of 2019.    At that time, the code was in its 8th release and had been commercially deployed in energy, manufacturing and mining operations.  Today, Fledge has ~30,000 commits and averages ~5000 commits/month.

What do you think sets LF Edge apart from other industry alliances?

The Linux Foundation’s history of delivering commercial grade open source software combined with the list of LF Edge membership is simply the best.   Members are serious and passionate about quality open source software, building strong communities and the markets served.

How will LF Edge help your business?

Of course, open source code with Apache 2 licensing is a great start for most software development today.  In Fledge’s case, the code is in its eighth release and deployed in industrial use cases for over a year.   Industrial developers can have more features, faster time to market and higher quality as their starting point!

 

Additionally, contributing FogLAMP to the Fledge project under LF Edge governance adds extra assurance and insurance for the developer.   They can feel confident in their decision to use and contribute to Fledge knowing the LF is backing the project and they remain in control of their own destiny with no cloud or other vendor locks.

What advice would you give to someone considering joining LF Edge?

Open Source is new to manufacturers and manufacturing is new to the Linux Foundation. So, the Fledge community consists of manufacturers, industrial equipment suppliers, integrators, OT system suppliers and technology suppliers.    Join us – help us, help you accelerate Industrial 4.0 adoption. It’s going to be fun!

To learn more about Fledge, visit the project page here.

 

 

 

 

LF Edge in 2020: Looking back and Revving forward

By Akraino Edge Stack, Baetyl, Blog, EdgeX Foundry, Fledge, Home Edge, Open Glossary of Edge Computing, Project EVE

Written by Melissa Evers-Hood, LF Edge Governing Board Chair 

Dear Community,

Happy New Year! As we kick off 2020, I wanted to send a note of thanks and recognition to each of you for a wonderful 2019, which marked several meaningful accomplishments for this organization.  LF Edge was launched in Jan 2019 with an aim to unify the edge communities across IOT, Telco, Enterprise and Cloud providing aligned open source edge frameworks for Infrastructure and Applications.

Our accomplishments include:

  • EdgeX Foundry has blossomed this year in participation, downloads, and use cases. EdgeX, as folks commonly call it, also graduated to Impact project stage and surpassed 1.5 million container downloads in 2019.
  • Akraino, which also reached Impact stage this year, is preparing for it’s second release with 5 new blueprints for R2, with updates to 9 of the existing 10 R1 blueprints already released. Most notably, its broadening its blueprint profile to include new blueprints for Connected Vehicles and AR/VR, truly becoming a viable framework across edge applications.
  • At the Growth Stage, Open Glossary provides common terminology and ecosystem mapping for the complex Edge environment. In 2019, the Glossary Project shipped 2.0 of the Glossary, which was integrated into the 2020 State of the Edge Report. The Glossary Project began the process of helping to standardize terminology across all LF Edge projects, and also launched the LF Edge Landscape Project: https://landscape.lfedge.org/.
  • Also at the Growth Stage, Project Eve allows cloud-native development practices in IOT and edge applications. EVE’s most recent release, 4.5.1 (which was gifted on December 25, 2019), provides a brand new initramfs based installer, ACRN tech preview, and ARM/HiKey support.
  • The Home Edge project, targeted to enable a home edge computing framework, announced their Baobab release in November. The Home Edge Project has initiated cross-project collaboration with EdgeX Foundry (secure data storage) and Project EVE (containerized OS).
  • We also added 2 additional projects this year.
    • Baetyl which provides an open source edge computing platform.
    • Fledge which is an open source framework and community for the industrial edge focused on critical operations, predictive maintenance, situational awareness and safety. Fledge has recently begun cross-project collaboration with Project EVE and Akraino, with more information available here.
  • Our reach has broadened with 9k articles, almost 50k new users, and 6.7M social media impressions.

I am excited about the work ahead in 2020, especially as we celebrate our one year anniversary this month. We laid the foundation last year – offered a solution to unite the various edge communities – and now, with your support and contributions, we’re ready to move to the next phase.

LF Edge is co-hosting Open Networking & Edge Summit in April and our teams are working hard on several cross-project demos and solutions. We’re planning meetups and other F2F opportunities at the show, so this conference will be a must.

Our focus as a community will be to continue to expand our developers and end users.  We will do this through having agile communities, that collaborate openly, create secure, updateable, production ready code, and work together as one. We also expect that there will be new projects to join and integrate.  As we walk into this bright future, working as a unified body will demonstrate that the fastest path to Edge products is through LF Edge.

I look forward to working with each of you in ‘20 and seeing you in Los Angeles this April at ONES!

Melissa

LF Edge Continues Rapid Growth as New Projects, Members Collaborate at Open Source Edge

By Announcement, Baetyl, Fledge

 

 

  • “Baetyl” and “Fledge” join LF Edge ranks as newest projects, expands LF Edge’s reach across geographies and industries
  • IOTA Foundation, SAIC Foundation (TESRA), Thunder Software, and Zenlayercommit to innovating at the open source edge by joining as members
  • LF Edge helps open source move to commercialization with Akraino RI, EdgeX Foundry Edinburgh release and Open Glossary of Edge Computing v2.0

ANTWERP, Belgium — Open Networking Summit Europe —  September 23, 2019 LF Edge, an umbrella organization within the Linux Foundation that aims to establish an open, interoperable framework for edge computing independent of hardware, silicon, cloud, or operating system, today announced continued project momentum with the addition of two new projects and four new members.

Baetyl, an existing project contributed by Baidu and previously known as “OpenEdge,” extends cloud computing, data and services seamlessly to edge devices. Fledge, an existing project contributed by Dianomic and previously known as “Fog Lamp,”  is an open source framework and community for the industrial edge focused on critical operations. Baetyl and Fledge join the organization’s founding projects: Akraino Edge Stack, EdgeX Foundry, Home Edge, Open Glossary of Edge Computing, and Project EVE. Concurrently,  IOTA Foundation, SAIC Foundation (TESRA), Thunder Software, and Zenlayer join as General members.

“It’s incredible to witness such strong industry support for collaborative innovation to create an open source framework at the edge,” said Arpit Joshipura, general manager, Networking, Automation, Edge & IoT, the Linux Foundation. “In just nine months, LF Edge has seen tremendous growth across the board. We couldn’t be more pleased to welcome our newest members and projects.  Added expertise in industrial edge, manufacturing, energy, and more brings the community and ecosystem closer to a more comprehensive edge stack, delivering shared innovation across technology sectors at the edge.”

Launched in January of this year, LF Edge’s seven projects support emerging edge applications across areas such as non-traditional video and connected things that require lower latency, and  faster processing and mobility. By forming a software stack that brings the best of cloud, enterprise and telecom, LF Edge helps to unify a fragmented edge market around a common, open vision for the future of the industry.

About the Newest Projects

Previously known as “OpenEdge” and initiated by Baidu, Baetyl is China’s first open source edge computing platform and is now part of the LF Edge umbrella of projects. It  seamlessly extends cloud computing, data and services to edge devices, enabling developers to build light, secure and scalable edge applications. The result is stronger processing power delivered to edge devices like smart home appliances, wearables and other IoT devices.  Baetyl joins LF Edge as a Stage 1 project.

“In the era of 5G and IoT, edge computing will have tremendous opportunities to play a role in all fields and industries,” said Watson Yin, Vice President of Baidu and the General Manager of the Intelligent Cloud business group. “As a founding member of LF Edge, Baidu Intelligent Cloud decided to donate Baetyl, the intelligent edge computing framework, to the community, hoping to reciprocate the open-source community while continuously contributing cutting-edge technologies to the global technology ecosystem.  The leading edge-computing technology and framework will further accelerate the implementation of cloud + AI in a wider range of industries with a bigger scale and lead the global AI industry into a new chapter of industrialized production.”

Fledge is an open source framework and community for the industrial edge focused on critical operations, predictive maintenance, situational awareness and safety. Contributed by Dianomic and formerly known as “FogLAMP,” Fledge is architected to integrate IIoT, sensors and modern machines all sharing a common set of administration and application APIs with industrial “brown field” systems and the cloud. Fledge developers build smarter, better, cheaper industrial manufacturing solutions  to accelerate Industrial 4.0 adoption. Fledge joins as a Stage 1 project.

Fledge works closely with both Project EVE and Akraino. Project EVE provides system and orchestration services and a container runtime for Fledge applications and services. Fledge’s verticals (manufacturing, energy, etc.) are starting to roll out 5G and private LTE networks; using Akraino blueprints, Fledge applications and services can be consistently managed as they utilize 5G and private LTE networks.

“The LF Edge’s efforts for an open, interoperable framework for the edge is especially needed for the industrial factory, plant and mine where most every brown field system, piece of equipment or sensor uses its own proprietary protocols and data definitions,”  said Tom Arthur, CEO and co-founder of Dianomic Systems. “Fledge was architected and built with the help of suppliers and operators in energy, oil and gas, manufacturing, mining, food processing and pharmaceutical industries.  Being designed specifically for the industrial edge, Fledge is the ideal LF Edge framework for industrial operators, system integrators and equipment providers to embed, deploy, contribute and build a thriving industrial open source community.”

“OSIsoft has been building software to break down the silos in industrial systems but with IoT these silos are multiplying to smart equipment, new sensors, and many other sources of data. We have supported the construction of Fledge by Dianomic Systems.  Fledge is an open source tool that presents these data to the outside world and look forward to vastly increasing the scope of data that we can all ‘see.’ This is integral to the fields of automation, energy conservation, safety and health,” said Pat Kennedy, Founder and CEO OSIsoft.

Quotes from New Members

“Edge computing plays a vital role with the process of unprecedented connected world leading by 5G networks,” said Pengcheng Zou, CTO of ThunderSoft. “ThunderSoft is a world leading OS technology provider. With EdgeX Foundry, which is the world‘s leading open interoperability platform for global IoT Edge ecosystem, we are able to provide developers with efficient, stable and easy-to-use EdgeOS software and hardware reference designs, as well as end-to-end commercial solutions. We are delighted to work with Linux Foundation and LF Edge to empower innovation and application across varies industries.”

“At Zenlayer, we truly believe that when we work together is when we do our best work. That’s why I’m so enthusiastic about LF Edge’s dedication to creating open-source standards for edge computing and networking. By having the global community collaborate, we will create a better-connected world.”

LF Edge is onsite at the Open Networking Summit (ONS) Europe in Antwerp, Belgium this week, which features an Edge track. Project activity includes an exhibition booth featuring LF Edge project demonstrations and 14 technical sessions within the main conference track. More details are available here: https://www.lfedge.org/event/open-networking-summit-ons-europe/

More details on Baetly and Fledgeas well as LF Edge as a whole are available here: www.lfedge.org.

About The Linux Foundation

Founded in 2000, the Linux Foundation is supported by more than 1,000 members and is the world’s leading home for collaboration on open source software, open standards, open data, and open hardware. Linux Foundation’s projects are critical to the world’s infrastructure including Linux, Kubernetes, Node.js, and more.  The Linux Foundation’s methodology focuses on leveraging best practices and addressing the needs of contributors, users and solution providers to create sustainable models for open collaboration. For more information, please visit us at linuxfoundation.org.

# # #

The Linux Foundation has registered trademarks and uses trademarks. For a list of trademarks of The Linux Foundation, please see our trademark usage page: https://www.linuxfoundation.org/trademark-usage. Linux is a registered trademark of Linus Torvalds.