David Schwarz / Ball Bearing Fault Detection Public

David Schwarz / Ball Bearing Fault Detection

Detect ball bearing faults using a subset of the Dataset for Sensorless Drive Diagnosis.

Audio

About this project

This project uses a subset of the Dataset for Sensorless Drive Diagnosis to train a compact classifier that identifies a ball bearing fault in a two-phase AC motor.

The raw data from the dataset is input current into the motor. This data is downsampled to 10kHz before training.

For more detail on the dataset, see the UCI Machine Learning Repository page or the paper below:

PASCHKE, Fabian ; BAYER, Christian ; BATOR, Martyna ; MÖNKS, Uwe ; DICKS, Alexander ; ENGE-ROSENBLATT, Olaf ; LOHWEG, Volker: Sensorlose Zustandsüberwachung an Synchronmotoren, Bd. 46. In: HOFFMANN, Frank; HÜLLERMEIER, Eyke (Hrsg.): Proceedings 23. Workshop Computational Intelligence. Karlsruhe : KIT Scientific Publishing, 2013 (Schriftenreihe des Instituts für Angewandte Informatik - Automatisierungstechnik am Karlsruher Institut für Technologie, 46), S. 211-225

Creating your first impulse (100% complete)

Acquire data

Every Machine Learning project starts with data. You can capture data from a development board or your phone, or import data you already collected.

Design an impulse

Teach the model to interpret previously unseen data, based on historical data. Use this to categorize new data, or to find anomalies in sensor readings.

Deploy

Package the complete impulse up, from signal processing code to trained model, and deploy it on your device. This ensures that the impulse runs with low latency and without requiring a network connection.

Download block output

Title Type Size
Raw data training data NPY file 1424 windows
Raw data training labels NPY file 1424 windows
Raw data testing data NPY file 148 windows
Raw data testing labels NPY file 148 windows
NN Classifier model TensorFlow Lite (float32) 260 KB
NN Classifier model TensorFlow Lite (int8 quantized) 67 KB
NN Classifier model TensorFlow SavedModel 246 KB
NN Classifier model Keras h5 model 241 KB

Clone project

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

Summary

Data collected
2m 39s

Project info

Project ID 114196
Project version 4
License No license attached