AI for the factory of the future


Success story

Energy monitoring and abnormal behavior detection


Factories and other industrial facilities always at risk of mechanical failures and other technical malfunctions that can bring production to a halt and disrupt the entire supply chain. EasymAInt* by Probayes is a decision-assistance tool that helps head off failures before they occur.

The solution uses data from gulplug’s non-intrusive plug&play sensors to:

  • Detect equipment operating modes
  • Use power consumption data to automatically monitor industrial processes
  • Detect abnormal operating behavior
  • Generate an alert in the event of a malfunction

The project

We started by segmenting and clustering univariate electric power time series. One algorithm segments the time series into elementary sequences. A second algorithm groups these sequences into clusters. The clusters, which correspond to equipment operating modes (behaviors), are then annotated by business experts. The result is very accurate in-line process equipment monitoring.

The module that detects abnormal equipment behavior is built on an “autoencoder” deep learning model. A neural network compresses and decompresses the time sequences to reconstruct a sequence of input data as faithfully as possible.
The gap between the predicted time series and the actual series is what allows any abnormal behaviors to be detected.


We tested these approaches on different types of equipment at different industrial facilities, and they are effective when used together.

The segmentation step is useful in automating the detection and monitoring of equipment operating modes.

The module that detects abnormal behavior makes it possible to pinpoint problems that previously went undetected before they cause a malfunction.

“Lorem ipsum dolor sit amet, consectetur adipiscing elit. Fusce eu lacus diam. Cras congue, neque ac mattis efficitur, nibh ipsum fringilla nunc, sed iaculis neque odio non orci. Vestibulum ante ipsum primis in faucibus orci luctus et ultrices posuere cubilia Curae; Praesent lacinia, urna quis rhoncus lobortis, urna neque tempus tellus, quis auctor justo lectus vitae libero. Nulla non porta odio. Donec diam est, varius id ullamcorper a, efficitur nec libero”

Last name First name

Position – Company

The EasymAInt decision-assistance tool was developed in conjunction with gulplug

Logo de gulplug

Customer testimonial

Success stories

The EU MONSOON project

Bringing AI to the process industries: Rio Tinto-Aluminium Dunkerque & GLNPlast


Eramet is one of the world’s leading metal alloy producers. The Eramet plant in Knivesdal, Norway, produces silicomanganese alloys.

EasymAInt, solution de maintenance prédictive

À partir de capteurs plug&play, non intrusifs, EasymAInt permet de maitriser ses données, suivre ses équipements et réaliser de la maintenance prédictive