Mon. Jan 17th, 2022

Nobody wants to be the maintenance worker who has to walk through half a mile of damp corridors to check the pressure gauge on a valve somewhere. LiLz makes it possible to remotely monitor such clunky physical interfaces with a smart and practical application of machine learning.

The Japanese (especially Okinawan) startup has been around for a while – in fact, our colleagues at TC JP wrote them down. But despite the seemingly obvious value of its service, it hasn’t quite taken off yet. LiLz participated in CES as part of the country’s trading group along with a number of other companies listed here.

The device of LiLz looks a bit like a chubby tablet without a screen. It’s essentially a camera, light, and processing and communications chips packed into a large battery – enough power to last up to three year.

You mount the device so it can see the appropriate gauge or dial. After confirming image and signal, configure it in the app to interpret where it points to; it can read circular, semicircular and linear gauges, digital and scrolling or analog number displays, or things like colored warning lights. (The ML involved here is not trivial – I came across this interesting article while looking at it.)

Once set up, it sends the measurements live or intermittently to a central dashboard, or makes them available via API for quenching or recording elsewhere. The data goes out via LTE or Bluetooth.

Two Lilz cameras mounted on the ceiling of an industrial area.

Image Credits: LiLz

It is a solution aimed directly at infrastructure and heavy industry, often involving a lot of obsolete equipment located in hard-to-reach places: rooftops, underground (but not too deep or the signal cannot penetrate), in labyrinthine factories and warehouses , and so on.

Running these dials on a daily basis is not only tedious work for humans, but can also be dangerous. Using a robot is another way to automate it, but doesn’t a network of IoT devices seem more practical than a four-legged bot constantly moving around?

LiLz CTO Kuba Kolodziejczyk said the company has expanded rapidly after its 2020 debut and a $2.2 million Series A round in early 2021.

Screenshot of the Lilz interface showing measurements of a watch face created by the software.

Image Credits: LiLz

“We have grown from 240 cameras deployed by a few early adopters in 34 locations before June 2020 to 2,000 cameras now deployed in 320 locations for more than 100 customers, and we expect to grow to 5000 cameras,” he wrote in an email. to BestFitnessBands. “We now have a few customers using over a hundred cameras in one location.”

They started out focusing on basic building management but have now expanded to chemical and industrial plants, construction and manufacturing sites, public infrastructure and more due to customer demand, he added.

And the possibilities of the device are also increasing. They mainly iterated the software, allowing it to be updated remotely, improving accuracy and resistance to failure, and adding data sharing and other features. There is also a new explosion-proof (!) version of the hardware. Maybe they should start making phone cases as an afterthought.

New products are on the way, one for “sound search” and another for counting objects in view of the camera, but both are now in a very early stage. And new possibilities such as monitoring float and level meters.

Meanwhile, they’ve come to CES to reach out to potential customers outside of Japan. The show looks like a failure, but maybe some engineers and managers will read this and think “wow, that would be handy.” You can find more information on the shiny new English website here.

Learn more about CES 2022 at BestFitnessBands

Leave a Reply

Your email address will not be published. Required fields are marked *