Manivannan / Pipe Leakage detection Public

Target: Arduino Portenta H7 (Cortex-M7 480MHz) Clone this project

Welcome to Edge Impulse, the largest community of edge AI developers!
This is a public Edge Impulse project, use the navigation bar to see all data and models in this project; or clone to retrain or deploy to any edge device.

Pipe Leakage detection

Audio

About this project

This public Edge Impulse project does not have a README yet. Clone this project to add new data or retrain this project, or to deploy this project to a device.

Data (25 samples)

View all

water flow - normal.364dfboj

ID: 110197485

Label: water flow - leakage

Sample length: 30s

water flow - leakage.364dm39i.s3

ID: 110197471

Label: water flow - leakage

Sample length: 5s

water flow - leakage.364dp858.s4

ID: 110197476

Label: water flow - leakage

Sample length: 5s

Idle.364e13kj

ID: 110197481

Label: Idle

Sample length: 16s

water flow - leakage.364dp858.s7

ID: 110197473

Label: water flow - leakage

Sample length: 5s

water flow - leakage.364dm39i.s6

ID: 110197468

Label: water flow - leakage

Sample length: 3s

water flow - normal.364dsupp

ID: 110197482

Label: water flow - normal

Sample length: 35s

water flow - leakage.364dp858.s2

ID: 110197478

Label: water flow - leakage

Sample length: 5s

Model accuracy (Unoptimized (float32))

Validation set

99.1%

Test set

100.0%

On-device performance (Arduino Portenta H7 (Cortex-M7 480MHz), Quantized (int8))

Latency

133 ms.

Peak RAM usage

53.6K

Flash usage

51.6K

Run this model

On any device

Clone project

Dataset summary

Data collected

6m 6s

Sensor

audio @ 16KHz

Labels

Idle, water flow - leakage, water flow - normal

Project info

Project ID	111978
Project version	1
License	No license attached
No. of views	23,322
No. of clones	73