souaddev/Dynamic-time-warping-based-anomaly-detection-for-industrial-control-system

An approach for anomaly detection in Industrial Control Systems (ICS), using Water Treatment Dataset (SWaT). The implementation incorporates cutting-edge machine learning techniques, including Isolation Forest and Autoencoder models, augmented by Dynamic Time Warping (DTW) algorithm.

21
/ 100
Experimental

This tool helps operations engineers and plant managers monitor critical industrial control systems for unusual behavior. It analyzes sensor data from systems like water treatment plants to identify anomalies, providing early warnings of potential equipment malfunctions or security breaches. The output is an alert indicating when something abnormal is detected within the system's operational data.

No commits in the last 6 months.

Use this if you manage industrial control systems and need an automated way to detect subtle, time-series-based anomalies that might indicate operational problems or cyber threats.

Not ideal if you are looking for a general-purpose anomaly detection tool for non-industrial time-series data or if your system doesn't generate continuous sensor readings.

industrial-control-systems operational-technology SCADA cyber-physical-security predictive-maintenance
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 8 / 25
Community 9 / 25

How are scores calculated?

Stars

7

Forks

1

Language

Jupyter Notebook

License

Last pushed

Feb 05, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/souaddev/Dynamic-time-warping-based-anomaly-detection-for-industrial-control-system"

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