Wb-az/time-series-anomaly-detection-bilstm-pycaret

Unsupervised anomaly detection in vibration signal using PyCaret vs BiLSTM

42
/ 100
Emerging

This project helps operations engineers and maintenance teams identify abnormal patterns in vibration sensor data from industrial machinery, like bearings. It takes raw vibration time-series data and pinpoints when and where anomalies occur, enabling proactive maintenance and preventing costly equipment failures. The output is an indication of potential issues, allowing users to investigate specific data points or timeframes for early fault detection.

Use this if you need to automatically detect unusual behaviors in machine vibration sensor data for predictive maintenance, especially when historical anomaly labels are scarce.

Not ideal if your anomaly detection needs are outside of industrial vibration data or if you require an approach specifically for anomaly forecasting rather than detection.

predictive-maintenance vibration-analysis fault-diagnosis industrial-iot sensor-monitoring
No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

15

Forks

2

Language

Jupyter Notebook

License

MIT

Last pushed

Mar 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Wb-az/time-series-anomaly-detection-bilstm-pycaret"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.