FIDOs act as data collection tools which, when deployed in water mains can be used to identify the various data signatures created by leaks and highlight the leak and its location.


FIDO is an initial implementation of Neil Edward’s white paper (Applying Differential Analysis and Machine Learning techniques to temporal data series in order to determine fluid leakage from pipelines) which explains why when multiple similar data sources are compared to each other they will give much more accurate reporting of variances (leaks) than a single data source performing absolute measurements can achieve.

FIDOs act as data collection tools which, when deployed in water mains can be used to identify the various data signatures created by leaks and highlight the leak and its location.

Three FIDOs are deployed and run simultaneously down the test section following each other a few metres apart with each collecting movement (rotation, acceleration), audio, visual and pressure information for the duration of their journey.

Data collected by FIDO is uploaded to a cloud analysis platform for processing and the output is a marked up KML file for importing in to google maps to display the specific geographic locations where to undertake ground works in order to resolve identified leak conditions.

Multiple post collection analysis techniques are used, and improved algorithms are always being developed as real fix data is acquired and re applied to old data to look for other data patterns. For example; you may run two successive tests at different pressures to identify the optimum operational pressure.

Key Benefits

At present large numbers of the ‘digs’ are dry and find nothing resulting in large amounts of wasted effort.

FIDO seeks to resolve this by giving accurate identification of the size and location of leaks detected in a normally pressurised system using multiple recorded data streams and differential analysis to give unprecedented sensitivity – without the need for wasteful, exploratory ‘digs’.


How it works

Investigation is conducted in the following stages:

1. Identify problem sections – using existing network analysis techniques, sections where significant leakage is occurring can be identified.

2. Insert FIDO – once the section to be scanned is known, a collection net is placed in the extraction point to eliminate any risk of losing the FIDOs. Secondly, the FIDOs are inserted upstream at the upstream insertion point (usually a hydrant location) and they then flow through the pipework. Finally, they are retrieved from the extraction point.

3. Data is uploaded to cloud for analysis - FIDOs are wireless and can upload their data without upsetting their physical integrity and then wiped ready for reuse. The insertion and extraction point GPS information is entered at this point.

4. Analysis – Once a data set is uploaded several numerical techniques are deployed to initially remove the spin and rotational data from the data streams leaving a single line. Anomalies of movement or turbulence are seen as deviations from an expected trajectory and the accompanying audio stream is processed to show leak locations and is also available directly to the operator for manual listening to confirm any findings.

5. Output – a KML data file is produced based on the insertion and extraction points and by extrapolating all the data points in between a correction factor can be used to give an accurate 3D map representation.

Whether you are a water company wanting to reduce the cost, effort, and wastage of current methods of leak detection, or a service provider looking to enhance your current service offerings to the water industry, FIDO provides a unique enabling capability to faster, more accurate leak detection results.

Purchase a license for full unlimited access to all innovation profiles on LEO

  • Direct connection to thousands of more innovations
  • Access to market Experts and Universities
  • Filter relevant solutions into your own dedicated Network