Interpretable multi-sensor attention fusion for early fault diagnosis and maintenance planning in vacuum diffusion bonding furnaces

Published: 9 November 2026| Version 1 | DOI: 10.17632/9tm7c833vw.1
Contributors:
, Yongli Wang

Description

This package contains the synthetic furnace dataset, trained model checkpoints, generated results, Docker environment, and analysis code required to reproduce the experiments, tables, and figures reported in the associated manuscript. All furnace cycles are simulated. Public CWRU benchmark data are downloaded at runtime from the official Bearing Data Center. The archive includes a README, fixed train-validation-test splits, random seeds, and SHA-256 checksums.

Files

Categories

Machine Learning, Sensor, Fault Diagnosis

Licence