David Schwarz / Ball Bearing Fault Detection
Detect ball bearing faults using a subset of the Dataset for Sensorless Drive Diagnosis.
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
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
Summary
Data collected
2m 39sProject info
| Project ID | 48672 |
| Project version | 4 |
| License | No license attached |
