AI sensors will listen to Prague’s metro escalators for mechanical problems

Preventive maintenance will become more targeted and efficient, reducing out-of-service times

Raymond Johnston

Written by Raymond Johnston
Published on 26.02.2021 11:00 (updated on 26.02.2021)

The Prague Public Transit Company (DPP) has begun working with Czech high-tech firm Neuron Soundware on predictive maintenance for metro escalators.

The project will use 189 sensors to continually monitor the sounds from 21 escalators in Prague’s metro system. The software will use artificial intelligence (AI) to interpret unusual sound patterns that might mean parts require maintenance.

The idea is something similar to an auto mechanic listening to an engine to try to determine what the problem is. Only in this case the sensors can be placed in spots that are difficult for a human to easily reach on a regular basis, and the changes in sound can be detected before a potential problem reaches a critical stage.

This will allow DPP to focus on specific machinery in its inspection so they can improve monitoring of wear and tear, and replace or repair defective parts before they cause the escalator to break down.

“Like all machinery in the transport system, escalators can break down, which can lead to delays in a critical part of the transport infrastructure. We want to embrace digitalization in monitoring our equipment, which is why we chose a solution where sensors collect acoustic data and process it using AI,” Petr Vondráček, head of DPP’s metro transportation service system, said in a press release..

“This allows us to monitor the equipment remotely and send a specialist out if our Neuron Soundware equipment warns us of a change in the condition of the escalator parts,” he added.

Difficulty accessing equipment, the need to make repairs outside ordinary operations, and long waiting times for replacement parts all make escalator maintenance complicated.

“Certain escalator components are found in places difficult for a human to access, often with no phone signal or internet connectivity. For cases such as this we developed a version of our equipment that allows us to process the signal completely in the end unit, at the location where the sound is recorded,” Neuron Soundware CEO Pavel Konečný said.

“We make use of a reliable, ultimately less costly data processing solution on-site in a microcomputer with no need to send terabytes of data from each machine to the cloud,” he added.

Konečný founded Neuron Soundware in Prague in 2016 as a way to help industrial businesses operate their machines more efficiently and sustainably. The concept was named “Idea of the Year 2016” in the Czech Republic for solution combining AI and IoT (internet of things).

Many of Prague’s metro escalators are Soviet models that date to the 1980s. DPP has been slowly replacing them with newer, safer and more efficient models, as the old ones have outlived their service life. Currently, the Na Knížecí of the Metro D stop at Anděl is under renovation until August 2021.

The metro station at Náměstí Míru has the longest escalator in the European Union, with a length of 87 meters and a vertical span 43.5 meters. It takes 2 minutes and 21 seconds to ascend without walking.