WE RECOGNIZE

BROKEN MACHINES

USING SOUND

WE RECOGNIZE

BROKEN MACHINES

USING SOUND

We use AI methods to understanding audio signals

 

We developed a diagnostic technology for early detection of broken machines. Humans are frequently used during the quality controls of air-conditioning, gearbox, etc. We can automate the analysis using our digital brain, which emulates auditory cortex. We focus on the early detection and prediction of mechanical malfunction on any machinery. The unique pre-processing of the input data allows the neural network to learn and identify the important features quickly with high confidence.

02

ACCURACY

We can identify the mechanical issues using a few seconds of the sound with more than 99.95% accuracy.

02

LARGE DATA SET

We have processed 1.5 TB of training audio data for one of our clients.

02

OUR CUSTOMERS

We are proud that all customers stay with us. Unfortunately their lawyers like NDA.

We are bringing innovations in the areas of:

#1

REVOLUTIONARY
PREDICTIVE MAINTENANCE

We monitor the sounds and other parameters of the machine and use probabilistic methods to determine the risk of an outage of each individual device. That’s the revolution of the predictive maintenance – individualized monitoring.

#2

REAL-TIME
ANOMALY DETECTION

Innovative digitization and analytic platform that enables manufacturers to check their critical machinery. The integrated hardware and software platform automatically gathers data in real time and continuously assess the equipment health.

#3

REMOTE
EQUIPMENT DIAGNOSTICS

The lack of a preventive maintenance increases the risk of costly unplanned downtime. The existing equipment doesn’t provide effective monitoring of mechanical malfunctions. We believe sound analysis is the simplest method of malfunction diagnostics.

You’re looking at model NB.6

How does

our magic

work

Sound Recording

Our Neuron box is monitoring and recording the sounds and other parameters of the machine

Neural Network

Passing all data trough tailored deep neural network to determine the risk of an outage of each individual device

Problem detection

We detect unusual or anomalous behaviors in real-time, vizualize them and send notification to responsible person

Still confused? Check our video below

We are professionals

Our team consists of dedicated experts in IoT, Machine learning and also with experiences from the area of Genetic research on developing a unique way of processing the sound. We spent years of work and hours of computational power to develop our technology.

We are continuously improving our algorithm and working with our clients to improve the revolutionary predictive maintenance of mechanical malfunction. Make it individual, real-time and perfectly accurate.

Latest news

Check Out Our New Product Demo Unit

For our potential customers, to make it easier for them to understand how our technology works, we designed a brand new product demo unit. Browse the slideshow for more pictures...   Made from two small electric engines (one okay, the other...

We Introduce New NeuronBox NB6 IoT Device

Our brand new NeuronBox NB6 IoT device is an industrial grade edge computing device equipped with the audio digitalization capabilities. Browse for more pictures...   The Key Product Features: Standalone analytical IoT unit with variable...

Let’s get in touch

Headquarters

71-75 Shelton Street, Covent Garden
London WC2H 9JQ, ENGLAND

Our office

Bubenské nábřeží 306/13, Building 24 – Startup Market
170 04 Prague, Czech Republic

pavel.konecny@neuronsw.com

+420 604 182 351 | +420 603 884 011

1 + 5 =

This project has received funding from the European Union`s Horizon 2020 research and innovation programme under grant agreement No 808225.

Giving back to communities. Everyone from small businesses to large companies can Pledge 1% of the profit, time, product and/or equity.