Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Ultralow-power standoff acoustic leak detection

Michael P. Hasselbeck

TL;DR

Problem: detecting very small leaks in pressurized plumbing with autonomous, remote sensing is challenging for conventional contact sensors. Approach: the authors present an edge-processed acoustic detector that uses a Helmholtz resonator for frequency filtering and threshold-based spectral analysis to identify persistent leaks without cloud streaming. Contributions: a complete low-power hardware design (20–200 μW), reliable standoff detection beyond 10 m, the ability to detect leaks behind walls, and an alarmable, tunable decision framework suitable for wireless sensor networks. Significance: the solution enables wide-area, privacy-preserving leak monitoring in smart buildings and related facilities, with potential extension to gas leaks while maintaining very low data bandwidth.

Abstract

An automated, standoff acoustic leak detection scheme has been designed, built, and tested. It merges the principles of glass breakage and smoke detection to alert for the presence of leaks emanating from pressurized plumbing. A simulated water leak flowing at 0.15 l/min has been reliably detected at a standoff distance of more than 10 m. The device is also effective at identifying the presence of leaks located behind surfaces such as walls, doors, floors, and ceilings. The anticipated application is as an autonomous, battery-powered, remote wireless node. All signal processing and analysis takes place on the edge with no need to stream audio data to the cloud. Sensor status is conveyed on-demand with only a few bytes of information, requiring minimal bandwidth. Power consumption is the range of 20--200 micro-Watts, depending on the amount of environmental noise and desired sensor latency. To attain optimum sensitivity and reliability, the hardware operates at acoustic frequencies well above the range of human conversations, making eavesdropping impossible. Development has been done with water escaping from pressurized plumbing, but the sensor concept can be used effectively to detect gas leaks.

Ultralow-power standoff acoustic leak detection

TL;DR

Problem: detecting very small leaks in pressurized plumbing with autonomous, remote sensing is challenging for conventional contact sensors. Approach: the authors present an edge-processed acoustic detector that uses a Helmholtz resonator for frequency filtering and threshold-based spectral analysis to identify persistent leaks without cloud streaming. Contributions: a complete low-power hardware design (20–200 μW), reliable standoff detection beyond 10 m, the ability to detect leaks behind walls, and an alarmable, tunable decision framework suitable for wireless sensor networks. Significance: the solution enables wide-area, privacy-preserving leak monitoring in smart buildings and related facilities, with potential extension to gas leaks while maintaining very low data bandwidth.

Abstract

An automated, standoff acoustic leak detection scheme has been designed, built, and tested. It merges the principles of glass breakage and smoke detection to alert for the presence of leaks emanating from pressurized plumbing. A simulated water leak flowing at 0.15 l/min has been reliably detected at a standoff distance of more than 10 m. The device is also effective at identifying the presence of leaks located behind surfaces such as walls, doors, floors, and ceilings. The anticipated application is as an autonomous, battery-powered, remote wireless node. All signal processing and analysis takes place on the edge with no need to stream audio data to the cloud. Sensor status is conveyed on-demand with only a few bytes of information, requiring minimal bandwidth. Power consumption is the range of 20--200 micro-Watts, depending on the amount of environmental noise and desired sensor latency. To attain optimum sensitivity and reliability, the hardware operates at acoustic frequencies well above the range of human conversations, making eavesdropping impossible. Development has been done with water escaping from pressurized plumbing, but the sensor concept can be used effectively to detect gas leaks.

Paper Structure

This paper contains 11 sections, 4 equations, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Design
  3. Frequency Filtering
  4. Sensor Training
  5. Polling
  6. Statistical Analysis
  7. Performance Testing
  8. Free-Space Standoff Detection
  9. Leaks Behind Walls
  10. Conclusion
  11. Acknowledgments

Figures (4)

  • Figure 1: The sensor PCB measures 48 mm x 33 mm. A surface mount MEMS microphone is enclosed by a rectangular chamber to form a Helmholtz resonator (far left). The 7-pin connection header is used for programming the MCU, I$^2$C communication, and 3V3 dc power.
  • Figure 2: Design diagram of the Helmholtz resonator. A partially open rectangular chamber is placed over a MEMS microphone (red lines). The resonator wall thickness $t$ is not shown for clarity.
  • Figure 3: Two different plumbing leaks. Left: A dispersed spray appears at a loose fitting or crack. Right: A pinhole leak produces a Laminar jet. The leak on the left is much easier to detect because of its stronger high-frequency acoustics.
  • Figure 4: Photograph of partially completed test structure used to evaluate acoustic detection of water leaks behind gypsum board. Arrows show the fixed locations of two independently activated simulated leaks. A second gypsum board (not shown) seals the structure for testing.