eddardd/CrossDomainFaultDiagnosis

Repository containing the code for the experiments and examples of my Bachelor Thesis: Cross Domain Fault Detection through Optimal Transport

40
/ 100
Emerging

This project helps operations engineers and process control specialists diagnose equipment faults in dynamic systems, like chemical reactors or tank systems, without needing to collect dangerous real-world fault data. It takes simulated operational data and, using advanced optimal transport methods, adapts it to predict faults accurately in real processes. This allows for safer and more efficient development of automated fault diagnosis systems.

No commits in the last 6 months.

Use this if you need to train fault diagnosis systems for industrial processes, but collecting real fault data is costly, risky, or impractical.

Not ideal if your system's operational data distribution doesn't significantly differ between simulation and reality, or if you already have ample real-world fault data.

industrial-control process-engineering fault-diagnosis predictive-maintenance chemical-engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

26

Forks

8

Language

Jupyter Notebook

License

MIT

Last pushed

Aug 03, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/eddardd/CrossDomainFaultDiagnosis"

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