{"id":1357,"date":"2021-12-14T16:38:54","date_gmt":"2021-12-14T16:38:54","guid":{"rendered":"https:\/\/salarydistribution.com\/machine-learning\/2021\/12\/14\/startup-surge-utility-feels-power-of-computer-vision-to-track-its-lines\/"},"modified":"2021-12-14T16:38:54","modified_gmt":"2021-12-14T16:38:54","slug":"startup-surge-utility-feels-power-of-computer-vision-to-track-its-lines","status":"publish","type":"post","link":"https:\/\/salarydistribution.com\/machine-learning\/2021\/12\/14\/startup-surge-utility-feels-power-of-computer-vision-to-track-its-lines\/","title":{"rendered":"Startup Surge: Utility Feels Power of Computer Vision to Track its Lines\u00a0"},"content":{"rendered":"
\n

It was the kind of message Connor McCluskey loves to find in his inbox.<\/p>\n

As a member of the product innovation team at FirstEnergy Corp. \u2014 an electric utility serving 6 million customers from central Ohio to the New Jersey coast \u2014 his job is to find technologies that open new revenue streams or cut costs.<\/p>\n

In the email, Chris Ricciuti, the founder of Noteworthy AI<\/a>, explained his ideas for using edge computing<\/a> to radically improve how utilities track their assets. For FirstEnergy, those assets include tens of millions of devices mounted on millions of poles across more than 269,000 miles of distribution lines.<\/p>\n

Bucket Trucks Become Smart Cameras<\/b><\/h2>\n

Ricciuti said his startup aimed to turn every truck in a utility\u2019s fleet into a smart camera that takes pictures of every pole it passes. What\u2019s more, Noteworthy AI\u2019s software would provide the location of the pole, identify the gear on it and help analyze its condition.<\/p>\n

\u201cI saw right away that this could be a game changer, so I called him,\u201d said McCluskey.<\/p>\n

In the U.S. alone, utilities own 185 million poles. They spend tens, if not hundreds, of millions of dollars a year trying to track the transformers, fuses and other devices on them, as well as the vegetation growing around them.<\/p>\n

Utilities typically send out workers each year to manually inspect a fraction of their distribution lines. It\u2019s an inventory that can take a decade, yet the condition of each device is critical to delivering power safely.<\/p>\n

5x More Images in 30 Days<\/b><\/h2>\n

In a pilot test last summer, Noteworthy AI showed how edge computing gets better results.<\/p>\n

In 30 days, two FirstEnergy trucks, outfitted with the startup\u2019s smart cameras, collected more than 5,000 high-res images of its poles. That expanded the utility\u2019s database more than fivefold.<\/p>\n

\u201cPeople were astounded at what we could do in such a short time frame,\u201d said McClusky.<\/p>\n

What\u2019s more, the pictures were of higher quality than those in the utility\u2019s database. That would help eliminate wasted trips when actual line conditions vary from what engineers expect to find.<\/p>\n

<\/p>\n

\"Noteworthy<\/p>\n

<\/a>

The startup\u2019s camera system can be mounted on a utility truck in less than an hour.<\/figcaption><\/figure>\n

Use Cases Multiply<\/b><\/h2>\n

News of the pilot program spread to other business units.<\/p>\n

A team that inspects FirstEnergy\u2019s 880,000 streetlights and another responsible for tracking vegetation growth around its lines wanted to try the technology. Both saw the value of having more and better data.<\/p>\n

So, an expanded pilot is in the works with more trucks over a larger area.<\/p>\n

It\u2019s too early to estimate the numbers, but McCluskey \u201cfelt right away we could find some significant cost savings with this technology \u2014 in a couple years I can imagine its use expanded to all our states,\u201d he said.<\/p>\n

An Inside Look at Edge Computing<\/b><\/h2>\n

In a unit the size of a small cake box that attaches to a truck with magnets or suction cups, Noteworthy AI packs two cameras and communications gear. It links to a smaller unit inside the cab that processes the images and AI on an NVIDIA Jetson Xavier NX<\/a>.<\/p>\n

\u201cWe developed a pretty sophisticated workflow that runs at the edge on Jetson,\u201d Ricciuti said.<\/p>\n

It uses seven AI models. One model looks for poles in images taken at 30 frames\/second. When it finds one, it triggers a higher res camera to take bursts of 60-megabyte pictures.<\/p>\n

Other models identify gear on the poles and determine which images to send to a database in the cloud.<\/p>\n

<\/p>\n

\"Noteworthy<\/p>\n

<\/a>

Designing a fast, resilient camera was even more challenging than implementing AI, said Ricciuti.<\/figcaption><\/figure>\n

\u201cWe\u2019re doing all this AI compute at the edge on Jetson, so we don\u2019t have to send all the images to the cloud \u2014 it\u2019s a huge cost savings,\u201d Ricciuti said.<\/p>\n

\u201cWith customer use cases growing, we\u2019ll graduate to products like Jetson AGX Orin<\/a> in the future \u2014 NVIDIA has been awesome in computing at the edge,\u201d he added.<\/p>\n

Software, Support Speeds Startup<\/b><\/h2>\n

The startup uses NVIDIA TensorRT<\/a>, code that keeps its AI models trim, so they run fast. It also employs the NVIDIA JetPack SDK<\/a> with drivers and libraries for computer vision and deep learning as well as ROS, an operating system, now accelerated on Jetson<\/a>.<\/p>\n

In addition, Ricciuti ticks off three benefits from being part of NVIDIA Inception<\/a>, a program designed to nurture cutting-edge startups.<\/p>\n

\u201cWhen we have engineering questions, we get introduced to technical people who unblock us; we meet potential customers when we\u2019re ready to go to market; and we get computer credits for GPUs in the cloud to train our models,\u201d he said.<\/p>\n

AI Spells Digital Transformation<\/b><\/h2>\n

The GPUs, software and support help Ricciuti do the work he loves: finding ways AI can transform legacy practices at large, regulated companies.<\/p>\n

\u201cWe\u2019re just seeing the tip of the iceberg of what we can do as people are being forced to innovate in the face of problems like climate change, and we\u2019re getting a lot of interest from utilities with large distribution networks,\u201d he said.<\/p>\n

Learn more about how NVIDIA is accelerating innovation in the energy industry<\/a>.<\/p>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

https:\/\/blogs.nvidia.com\/blog\/2021\/12\/14\/power-utility-ai-edge\/<\/p>\n","protected":false},"author":0,"featured_media":1358,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[3],"tags":[],"_links":{"self":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts\/1357"}],"collection":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/comments?post=1357"}],"version-history":[{"count":0,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts\/1357\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/media\/1358"}],"wp:attachment":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/media?parent=1357"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/categories?post=1357"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/tags?post=1357"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}