DecisionLevelFaultPrediction

• This repository includes code and simulation dataset in the paper: Ma, X., Yan, B., Wang, H., & Liao, H. (2023). Decision-level machinery fault prognosis using N-BEATS-based degradation feature prediction and reconstruction. Mechanical Systems and Signal Processing, 198, 110435.

Data

• wheeli_simulated.xlsx are the simulated vibration signals of wheel $i$, where $i=1,2,3,4$
  • Due to privacy issues, we do not provide the original data in real applications.
  • However, we provide the simulated data.
  • The simulated data are generated by manipulating the original data in real applications.

Requirements

• Python 3.9.7
• Numpy 1.20.3
• Pandas 1.3.4
• scipy
• time
• TensorFlow 2.7.0
• Keras 2.7.0
• sklearn 0.24.2
• NBEATS
• nbeats_pytorch
• torch

Codes

• proposed_simulation1_public.ipynb: proposed method in simulated case 1
  • Current state: first version upload.

Notes

• jupyterlab-toc is recommended for navigation, see how to add it in this issue.
• Email me if you have any questions: yanbingxin124@163.com