Skip to main content

AI system listens to your engine and tells you if you’re running into problems

A lot of the most high-profile applications of deep learning technology involve aspects of computer vision, such as cutting-edge facial-recognition technology. However, an innovative artificial intelligence startup from Israel is looking to apply those same neural networks and smart algorithms to another area — acoustics. Better yet, they are doing so to help users spot early warning signs that machines, such as cars, may be about to fail.

“I was on a train about three years ago, going back to my hotel after a business meeting,” 3DSignals CEO Amnon Shenfeld told Digital Trends. “The train suddenly started making strange noises. These weren’t the usual sounds that trains make, but something out of the ordinary. It was the same week that a train had overturned in Spain, injuring a lot of people. Everyone stopped talking and was getting very worried. I had the thought that maybe if there was a train mechanic or engineer sitting on the train, they could tell us if the noise was normal and, if not, where it was coming from and whether it could be safely ignored.”

Recommended Videos

From that slightly scary scenario (from which he emerged unscathed), Shenfeld came up with the idea behind the company called 3DSignals. The company’s goal? To harness the latest AI machine learning technology to understand the noise patterns made by machines running into trouble and relating them back to users via their smartphone or tablet.

Properly trained, Shenfeld said that the company’s deep-learning algorithms are able to identify and predict specific problems with an accuracy rate of 98 percent.

To do this, machinery for monitoring has to be kitted out with the company’s proprietary hardware: Consisting of a connected processing unit and an ultrasonic microphone five times more sensitive than the human ear. While the human range is between 20Hz and 20kHz, 3DSignals’ custom mic can detect sounds ranging up to 100kHz.

The 3DSignals sensor and data collector kit in its industrial casing. Image used with permission by copyright holder

Shenfeld said his company never set out to create its own hardware, but had to in order to carry out its mission statement. After all, as pioneering technologist Alan Kay once said, people serious about software need to build their own hardware. “We went on Google and searched for ultrasonic, cloud-connected, ruggedized microphones, but we couldn’t find what we wanted,” Shenfeld said. “So right now we’re manufacturing the only device of its type that can be used for remote monitoring via acoustics.”

At present, 3DSignals is busy speaking with leading European carmakers about using the technology both in cars as well as to monitor auto factory machinery. It is also being used to monitor other non-auto industrial machinery like circular cutting blades in mills and hydroelectric turbines in power plants. The tech will be shown off on January 23 as part of the IoT Tech Expo in London.

“You know that saying about whether or not a tree that falls in the forest makes any sound?” Shenfeld said. “Well, we want to update the question to what happens to a machine that fails with no engineer standing next to it? We think we have the answer.”

Luke Dormehl
Former Digital Trends Contributor
I'm a UK-based tech writer covering Cool Tech at Digital Trends. I've also written for Fast Company, Wired, the Guardian…
Your A.I. smart assistant could one day tell if you’re lonely
roku ultra vs amazon fire tv nvidia shield apple siri

 

Your A.I. assistant can do plenty of things for you, whether that’s answering questions, cuing up the perfect song at the right time, making restaurant bookings, or many other tasks. Could it also work out whether you’re lonely?

Read more
A.I. can tell if you’re a good surgeon just by scanning your brain
brain with computer text scrolling artificial intelligence

 

Could a brain scan be the best way to tell a top-notch surgeon? Well, kind of. Researchers at Rensselaer Polytechnic Institute and the University at Buffalo have developed Brain-NET, a deep learning A.I. tool that can accurately predict a surgeon’s certification scores based on their neuroimaging data.

Read more
ChatGPT’s awesome Deep Research gets a light version and goes free for all
Deep Research option for ChatGPT.

There’s a lot of AI hype floating around, and it seems every brand wants to cram it into their products. But there are a few remarkably useful tools, as well, though they are pretty expensive. ChatGPT’s Deep Research is one such feature, and it seems OpenAI is finally feeling a bit generous about it. 

The company has created a lightweight version of Deep Research that is powered by its new o4-mini language model. OpenAI says this variant is “more cost-efficient while preserving high quality.” More importantly, it is available to use for free without any subscription caveat. 

Read more