hubtru/Minape
Multimodal Isotropic Neural Architecture with Patch Embedding to both time series and image data for classification purposes.
This project helps manufacturing engineers and operations managers automatically assess the wear state of milling machine tools. By inputting images of the tool itself and three spectrograms representing vibration data (X, Y, Z axes), the system classifies the tool's condition as 'Sharp', 'Used', or 'Dulled'. This allows for proactive maintenance and optimal tool replacement, preventing costly downtime and product defects.
No commits in the last 6 months.
Use this if you need to reliably classify the wear state of industrial cutting tools, like milling machine flank tools, using a combination of visual and vibration data.
Not ideal if you're looking for predictive maintenance solutions beyond classification, such as estimating remaining useful life or detecting anomalies, as these are future research goals.
Stars
9
Forks
2
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Sep 09, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/hubtru/Minape"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yzhao062/pyod
A Python Library for Outlier and Anomaly Detection, Integrating Classical and Deep Learning Techniques
unit8co/darts
A python library for user-friendly forecasting and anomaly detection on time series.
elki-project/elki
ELKI Data Mining Toolkit
raphaelvallat/antropy
AntroPy: entropy and complexity of (EEG) time-series in Python
Minqi824/ADBench
Official Implement of "ADBench: Anomaly Detection Benchmark", NeurIPS 2022.