Solve the problem of water and gas leaks with the combination of Artificial Intelligence applied to IoT technology.
This is the ambitious technological vision of Onyax, an innovative company with 25 years of experience in the field of telecommunications, able to give a concrete and digitalized response to the needs of gas and water network operators in the Leakage and Anomaly Detection areas.
This is how the EVALD project was born, able to exploit the great potential of Onyax’s ACE cloud platform, already used by several utilities in the country to remotely monitor their plants, with the help of a network of IoT devices with integrated battery and low power consumption.
The solution, which has aroused great interest in technology, was presented in mid-June on the stage of the WeMakeFuture 2023 in Rimini, the largest European event on innovation and technology, through a speech given by Eng. Gian Paolo Quarta (CEO of Onyax) named “Artificial Intelligence and IoT ecosystems for leak detection in water and gas distribution networks”.
An innovative method, favored by Artificial Intelligence
EVALD, acronym for Electro-Vibro-Acoustic-Leakage-Detect, was created to manage data from IoT devices, deep learning algorithms and numerical modelling techniques with acoustic, pressure, electrical and vibrational analysis in a unique digital ecosystem.
The idea behind the EVALD project, born out of Onyax’s continuous experimentation in the field of distribution networks, was not to limit itself exclusively to the identification of acoustic anomalies through a passive approach, as in most traditional leak detection systems and currently on the market, but to consider an active acoustic analysis supported by various electrical, pressure and vibrational sources.
The “active” listening approach used by Onyax is perfected through a valuable technological collaboration with the Department of Electronics, Information and Bioengineering of the Politecnico di Milano, consists in deliberately injecting a sound inside the water/gas network and through the TUBE-T3 IoT device with integrated hydrophone, listening to it at different points by obtaining the average flow, thus analysing the frequency deviation of the received signal and excluding possible environmental noise.
This Audio Analysis technique, coupled with the network node-related quantities (pressure, temperature and vibration) already acquired in distribution networks through the installation of Onyax IoT devices, allows the creation and subsequent “progressive training” of the network’s digital twin built using artificial intelligence models, in order to identify with a higher degree of precision the areas most likely to leak or so-called “false positives”.
The advantages of EVALD: even predictive actions with cathodic protection
The advantages of this new solution, which combines IoT and artificial intelligence, can be found first and foremost in the ability to reduce the error rate of leakage detection, allowing operators to carry out targeted measurement campaigns even before moving entire teams dedicated to acoustic analysis into the field.
This is joined by:
- the energy advantage. Installation of devices with long battery life and low energy consumption with minimal operator intervention and consequent sustainable approach.
- the technological advantage. The data constantly received from the installed devices allows for an ever-increasing accuracy of analysis and, in fact, an ever more faithful realisation of the digital twin of the physical network.
- the predictive advantage. With networks made of steel and protected with cathodic protection techniques, in addition to assessing the actual protection of water and gas pipelines, for example through the BLACKBOX-CAT device, predictive techniques can be applied both on the life of sacrificial anodes and understanding whether a process of reduction, coating removal or corrosion of the pipeline is beginning, all indicators of future leakage.