Kutluhan Aktar / AI-assisted Pipeline Diagnostics Public

Kutluhan Aktar / AI-assisted Pipeline Diagnostics

This is your Edge Impulse project. From here you acquire new training data, design impulses and train models.

About this project

Project Description

This model detects pipeline diagnostic classes based on the mmWave data parameters extracted from a 60GHz mmWave radar module:

  • Clogged
  • Cracked
  • Leakage

After building my neural network model, I deployed my model as an Arduino library and uploaded it to Nicla Vision. Also, I employed Nicla Vision to capture images of deformed pipes for further examination and communicate with the web application I developed to generate a pre-formatted CSV file from the stored data records and display the model detection results.


Download block output

Title Type Size
CSV Wizard config JSON file 388 Bytes
Raw data training data NPY file 180 windows
Raw data training labels NPY file 180 windows
Raw data testing data NPY file 30 windows
Raw data testing labels NPY file 30 windows
Classifier model TensorFlow Lite (float32) 13 KB
Classifier model TensorFlow Lite (int8 quantized) 5 KB
Classifier model TensorFlow SavedModel 18 KB
Classifier model Keras h5 model 12 KB

Clone project

You are viewing a public Edge Impulse project. Clone this project to add data or make changes.

Run this model

Scan QR code or launch in browser


Data collected
3m 30s

Project info

Project ID 214371
Project version 1
License Apache 2.0