From "leak-before-break" to operational decisions: what peer-reviewed studies show.

Why we’re sharing this

Adelitics exists because we’re not comfortable with “trust us” technology. For more than a decade, our team has been developing and validating domain-specific machine learning and signal analytics for water networks, rather than relying on generic AI tools. These methods have been tested in real operational monitoring environments and published in peer-reviewed research.

This short article summarises a few practical takeaways from our published work. (If you’d like PDFs, contact us. Where licensing restricts hosting, we’ll share what we can.)

1) Early acoustic change can precede major failure

A consistent theme across permanent monitoring research is that changes in acoustic behaviour can appear before catastrophic rupture, offering a pathway to earlier intervention and reduced disruption. Studies focused on detecting emerging through-wall cracks and early warning signals support this “pre-failure signal” concept in operational water distribution contexts.

What this means in plain terms: If you can detect how acoustic behaviour changes over time, you can begin to move from reacting after failure to intervening before escalation.

2) Real networks aren’t tidy, so analytics must work with messy, noisy data

In operating networks, background activity is constant: pumps, demand shifts, weather, and everyday use all contribute to noise. That’s why modern approaches increasingly use classification and anomaly detection to help separate true anomalies from routine variation.

One peer-reviewed study using a convolutional neural network (CNN) achieved 92% classification accuracy across 1,098 acoustic files from 34 sensors, including 32 confirmed leak events.

So what? Higher-confidence classification can help reduce time spent chasing false alarms and improve the signal-to-action pathway.

3) Location matters, especially for long assets

Detection alone isn’t enough. If you can’t narrow down where to look, field response gets expensive fast.

A field study on proactive condition assessment reports transmission-scale location performance using hydroacoustic noise methods (non-invasive, non-destructive) and discusses identifying features and changes along longer pipe sections.

So what? This supports a practical workflow: screen broadly then target inspection, rather than disruptive investigation everywhere.

4) The bigger point: this isn’t “AI because it’s trendy”

There’s a lot of “AI marketing” in infrastructure right now. Our view is simple: if it’s not validated in the field, in messy operational conditions, it’s not ready to guide decisions. 

The goal is not “more data”.

It’s decision-grade insight that operators can act on confidently.

Why this matters for utilities

Taken together, these findings suggest that leak-before-break monitoring is becoming operationally viable.

Permanent acoustic monitoring, combined with machine learning classification and improved localisation techniques, enables utilities to:

• detect emerging failures earlier

• reduce unnecessary field investigation

• prioritise inspection and repair

• extend the life of ageing pipe assets

In practical terms, the shift is from reactive repair after failure to structured early intervention based on signal change.

References (DOIs)

1. M Stephens, J Gong, C Zhang, A Marchi, L Dix, MF Lambert (2020)  Leak-Before-Break Main Failure Prevention for Water Distribution Pipes Using Acoustic Smart Water Technologies: Case Study in Adelaide.  doi:10.1061/(ASCE)WR.1943-5452.0001266
   

2. Gong, J., Lambert, M.F., Stephens, M.L. et al. (2020)  Detection of Emerging through-Wall Cracks for Pipe Break Early Warning in Water Distribution Systems Using Permanent Acoustic Monitoring and Acoustic Wave Analysis.  doi:10.1007/s11269-020-02560-1
   

3. Zhang C, Alexander BJ, Stephens ML, Lambert MF, Gong J. (2023)  A convolutional neural network for pipe crack and leak detection in smart water network.  doi:10.1177/14759217221080198
   

4. Zeng W, Nguyen STN, Lambert M, Gong J. (2024)  Field study on proactive pipe condition assessment using hydroacoustic noise.  doi:10.1177/14759217241284729