Streaming Video Analytics AI Assists Industrial Engineering

Video as a sensor has been a topic for several posts here at The Manufacturing Connection. One notable case study involved detecting unwanted critters wandering into the facility when gates were opened to allow train cars to enter or leave. Machine vision has been usable since the 1980s to detect flaws, presence, and other quality issues, as well as to guide robots.

Anurag Maunder, CEO and founder, and Subbu Kuchibhotla, VP Growth and Development, of a new company in the video streaming market called Sensable.

They told me this is the first vision platform built for industrial engineering. Almost all current vision and video applications involve narrowly focusing on a part or a piece of a machine. The idea of the Sensable platform is to broaden the focus of the camera, or combine multiple camera, such that an entire operation or segment of the plant can be viewed, captured, and analyzed.

My grandfather told me of the time he was summoned to the front office of the GM plant where he was a production superintendent. The US had entered World War II and his plant was converting to production of aircraft armaments. Production ramp up was slow. Management picked him to organize things and get production up to expectations. 

He explained to 8-year-old me how he went up on the mezzanine and watched the process. Guys were performing a process, dragging a crate of parts to the next operation across the department, where the next operation took place, and that operator dragged the crate across the facility to the next operation. He told me how he organized the process to minimize material handling. That and other things boosted production and won the war—well, anyway, he did his part. And I learned a lesson.

Now imagine that you don’t have people to just stand and observe and take notes over three shifts a day for a week or so. What if you could position a few cameras in strategic locations. The video is captured and run through analytics. Engineers, operators, and managers would not have to  manually parse through hours of video. They would be presented with data visualization designed to help them get to root causes of problems, assist worker ergonomics, improve safety, and boost productivity.

That is what the Sensable solution does.

Imagine another scenario. You are an operator on a production line. You have been trying to point out bottlenecks to production on your machine. Then engineers install streaming video pointing not just at a specific point on you or the machine but with wide enough scope to see the larger process. The video analytics point out the bottleneck. Voila. Vindicated. Proof in the data. 

The video is not for spying on employees. It is designed to help them. Just what true digital transformation is—an aid to decision making and continuous improvement.

Key spots:

  • Missed throughput targets—station utilization lower than expected, unplanned downtimes more than planned
  • Low process efficiency—cycle time variability, too many interruptions
  • Low operations visibility—safety challenges due to best practices violations, missed inspection or assembly steps

Use cases:

  • Manage work area or assembly line—real-time feedback, identify bottlenecks, performance reports by shift/day, remote visibility-ideal for managing off shifts
  • Perform long duration time studies—data-driven Kaizen setup/changeover analysis, run/analyzed over weeks, compare across time and facilities, store metrics for Kaizen, perform SMED analysis in large areas
  • Identify missed inspection steps with 360 degree analysis—rapidly identify root cause of defects, search for video clips associated with product assembly
  • Achieve healthier, safer, well trained workforce—capture near misses and best practice violations, capture the impact of fatigue by measuring throughput at beginning and end of shift, capture and share the best practices for training
  • Build realistic engineering standards—capture data for the entire shift or multiple shifts before creating a standard to be enforced 

AI Software for Robots and Flexible Automation

AI gathers so much media hype that I must curtail my natural bent toward contrarianism. Artificial Intelligence in its various forms has advanced many applications. However, its hype often exceeds the actual applicability. Some new products offer more potential than immediate use. Industrial and manufacturing announcements are often more immediately accessible than the more general one.

This news announces AI-based software that is now useful add-on for FANUC robots with some interesting use cases.

Micropsi Industries announced that its artificial intelligence (AI)-based software MIRAI is now compatible with numerous robots produced by FANUC. With MIRAI, FANUC customers can now add valuable hand-eye coordination to multiple FANUC industrial and collaborative robots (cobots) to handle difficult-to-automate functions such as cable plugging and assembly.

Using AI, the MIRAI controller generates robot movements directly and in real-time. Robot skills are trained, not programmed, in a few days through human demonstration, without requiring knowledge of programming or AI. To train a robot, a human repeatedly demonstrates a task by manually guiding the robot by the robot’s wrist. The recorded movements are then transformed into a skill.

Cable plugging applications such as flat ribbon cables for the electronics industry or industrial automotive connectors typically require a high degree of flexibility to accommodate shape instability, making it a difficult task for any robot. MIRAI makes this type of application possible, says Prof. Dominik Bösl, chief technology officer, Micropsi Industries.

Zebra Technologies Looks At Automotive Industry

[Note: If you had previously signed up to receive new posts via email, you’ve noticed that they stopped and then restarted. WordPress had notified me that this service had ended. I recently saw where it was active, but not supported. It’s on for as long as WordPress enables it or until you unsubscribe.

You can subscribe to an occasional newsletter that I’ve been playing around with. It comes through my HEY.com email account. If you haven’t checked out Hey, give it a look. I haven’t moved my business email there, yet, but I like the new take on an email client. My email address there is [email protected] The newsletter is at https://world.hey.com/garymintchell and you subscribe there or get the RSS feed for your reader.]

Zebra Technologies Corp. is an interesting case study of a company building on a rather mundane, albeit useful, technology in a classic MBA strategy sort of way. I knew it for years as a label printer company—even sold a few in an earlier career. Now its technologies are found in many industries.

Along with the current meme of all God’s children doing research and reports (where have all the industry analysts gone?), here is a report Zebra compiled regarding attitudes and expectations of both consumers and managers in the automotive industry.

A couple of quick highlights:

  • Consumers are driving a growing environmental imperative in automotive manufacturing that decision-makers need to address: Eight-in-10 consumers say sustainability and eco-friendliness are key priorities in their vehicle purchase and lease decisions.
  • Navigating the increasing demand for EVs: More than half of consumers indicate their future preference is for a hybrid electric vehicle (HEV). However, navigating the growing demand comes with challenges as 68% of automotive industry decision-makers say they are under high pressure to produce next-generation (i.e., electric) vehicles.
  • Trust and transparency in automotive manufacturing is a must: Approximately 80% of consumers and fleet managers want to have end-to-end visibility during the manufacturing process.

Zebra Technologies Corporation released the findings of its Automotive Ecosystem Vision Study which confirmed automotive manufacturers are under pressure to accommodate growing consumer demands for sustainability and transparency throughout the manufacturing process and fleet managers’ need for the digitization of operations and supply chain. 

  • Despite a fluctuating economy, automotive manufacturers are ready to invest in technology innovation as seven-in-10 expect to increase their tech spend and six-in-10 plan to increase their manufacturing infrastructure spend in 2023.
  • Spanning multiple generations, consumers are a driving force behind automotive manufacturers’ acceleration to technology innovation as eight-in-10 say sustainability and eco-friendliness are key priorities in their vehicle purchase and lease decisions.
  • Consumers are also driving the growing emphasis on personalization – the ability to customize a vehicle to their liking. Nearly four-in-five consumers say personalization options factor into their decision to purchase a vehicle, and eight-in-10 fleet managers share these same requirements for sustainability and personalization. 
  • Three-fourths of automotive manufacturers say a top priority is to build strategic partnerships with tech companies for their next generation of production. 
  • Data and information transparency is highly important to consumers and fleet managers alike, and they’re seeking more visibility into the automotive ecosystem. When considering a vehicle for purchase or lease, 81% of consumers and 86% of fleet managers indicate they want to understand the origin of materials and parts on their vehicle.
  • Beyond gaining greater visibility into the automotive manufacturing process, once they have their vehicles, 88% of consumers and 86% of fleet managers want to understand how the data from their vehicles will be used by the automotive ecosystem. After a vehicle purchase, 83% of consumers and 84% of fleet managers expect ownership and control of the data their vehicle generates. 
  • A majority of consumers and fleet managers (80%) want end-to-end visibility during the manufacturing process. However, only about three-in-10 automotive industry decision-makers say they will prioritize connecting real-time data systems to enable a holistic view of operations and increase visibility across production and throughout the supply chain over the next five years. 
  • About one-third of original equipment manufacturers (OEMs) said autonomous mobile robots (AMRs), RFID, rugged handheld mobile computers and scanners as well as industrial machine vision will improve supply chain management while about one-third of suppliers cite mobile barcode label/thermal printers, wearable computers and location technology as the technologies to do so. 
  • Overall, seven-in-10 automotive industry decision-makers agree digital transformation is a strategic priority for their organization. In the next five years, they anticipate expanding their use of technology with 47% focused on additive manufacturing/3D printing and 45% on supply chain planning solutions. 

SiLC Technologies Launches Machine Vision Solution

LiDAR is on everyone’s mind these days relating autonomous vehicles—either cars or industrial vehicles. It is a cool light sensing technology first played around with in 1961 and getting lots of interest today. I received a news release from SiLC Technologies. The news is interesting. The release had the most superlatives per square inch of text of any I’ve ever seen. Here is the condensed version of this news that is worth your time to check if you have any interest in vision systems.

  • SiLC Technologies Inc. (SiLC) announced the launch of the Eyeonic Vision System.
  • High resolution
  • High precision
  • Long range
  • Turnkey solution
  • Targeted to robotics, autonomous vehicles, smart cameras and other advanced products
  • Integrated silicon photonics chip
  • Roughly 10 milli-degrees of angular resolution
  • mm-level precision
  • integrates all photonics functions needed to enable a coherent vision sensor

Neural Networks Explained

I become a little jaded over all the marketing hype around Artificial Intelligence (AI). Yes, it is an important technology. No, it’s not really all that intelligent, yet. I lost a programmer in my department in 1989 who was going to specialize in AI. Engineers addressed some SME meetings I attended in the 1990s explaining neural networks and motion control.

Emily Newton at Revolutionized has posted an informative article on neural nets and deep learning that is worth a look.

The average person doesn’t spend much time thinking about the structure of their brain unless it starts causing problems. They don’t wonder what the various folds and valleys do or what it feels like when their neurons fire. Most are content to understand that they have a functioning brain in their head. What happens when you compare your brain to what you might find on a computer? What are neural networks and deep learning and what is the connection between the two?

Emily Newton, Revolutionized

Rockwell Automation Smart Machine, Safety, Security Announcements

The Rockwell Automation PR team must have worked overtime following November’s Automation Fair. Here are a number of releases on new products and services. These cover a spectrum of technology areas that further reveal the breadth of Rockwell’s reach. 

  • Smart Machine Development
  • GuardLink with EtherNet/IP
  • FactoryTalk Logix Echo
  • Cyber Endpoint Protection Services

Simplify Smart Machine Development with Improved Micro800 Controllers and Design Software

Machine builders can save engineering time and costs with the enhanced Allen-Bradley Micro850 and Micro870 2080-Lx0E controllers using the latest Connected Components Workbench software from Rockwell Automation.

  • Class 1 implicit messaging capability up to eight EtherNet/IP devices support
  • Streamline integration of controller to drives, supporting PowerFlex 520 series and Kinetix 5100 drives over EtherNet/IP with pre-defined tags and pre-developed user-defined function block (UDFB) instructions.
  • Connected Components Workbench software version 21 required.

GuardLink 2.0 with new EtherNet/IP Interface

  • GuardLink 2.0 offers advanced diagnostics by way of the new Allen-Bradley 432ES GuardLink EtherNet/IP On-Machine Interface or a combination of Dual GuardLink Relay and EtherNet/IP Interface. 
  • GuardLink 2.0 protocol also enables safety-rated control device status reporting and automatic diagnostic reporting to an HMI using CIP Safety over EtherNet/IP.
  • Connect up to 96 safety devices via three independent safety channels. 
  • The interface can cascade power to additional interfaces and can keep track of timing and frequency of events to improve maintenance and create process efficiencies. 
  • The 432ES supports linear, star and Device Level Ring topologies while meeting safety ratings up to SIL 3, Cat 4 PLe.

New Capabilities in Emulation and Support with First expansion of FactoryTalk Logix Echo

  • Attention was dedicated to improving testing, giving users access to more than 20 variations of the 5580 ControlLogix platform at their disposal.
  • FactoryTalk Logix Echo simplifies the emulator experience by providing users the opportunity to download directly to FactoryTalk Logix Echo without modifications. 
  • Having the emulation of the 5580 ControlLogix Ethernet port means that to other software, FactoryTalk Logix Echo looks like another controller, offering flexibility to expand your emulation to visualization or other controllers.
  • Version 2 will be the first emulation platform to support safety controllers by introducing GuardLogix 5580 controller catalogs. 
  • The inaugural version supported one 17 slot chassis, but the latest release now supports the creation and communication of multiple chassis with one FactoryTalk Logix Echo license. 

Comprehensive Endpoint Protection Services

  • For organizations to secure their operations and reduce cyber threats, a successful cybersecurity strategy requires solutions to secure endpoints – any device that is connected to a network outside of its firewall, including laptops, HMIs, switches, IoT devices, and more.
  • Rockwell Automation and CrowdStrike are providing manufacturers with comprehensive Endpoint Protection Services, combining Rockwell Automation’s Industrial Cybersecurity Services and CrowdStrike Falcon platform to monitor, protect, investigate, and respond to incidents. 
  • Purpose-built in the cloud with a single lightweight-agent architecture, the CrowdStrike Falcon platform delivers rapid and scalable deployment, superior protection and performance, reduced complexity, and immediate time-to-value.
  • When customers choose the CrowdStrike Falcon platform through Rockwell Automation, they receive the industry-leading software coupled with OT-specific Falcon policies, developed by Rockwell Automation cybersecurity specialists, and backed by software and phone support. 
  • Endpoint Protection fits into the expansive Rockwell Automation portfolio of Managed Services along with Incident Response and Threat Detection to provide customers with a holistic cybersecurity solution.

Follow this blog

Get a weekly email of all new posts.