# Similarity-aware VAE with wavelet-convolutional 1D-CNN for rolling bearing fault diagnosis

## TL;DR

This paper introduces a new framework for fault diagnosis in rolling bearings using an improved VAE and a wavelet-based CNN to handle imbalanced data and improve diagnostic accuracy.

## Contribution

The novel Similarity-Aware VAE with a similarity loss function and Wavelet-Convolutional 1D-CNN for multi-scale feature extraction is proposed.

## Key findings

- The framework effectively enhances data quality and balances imbalanced fault datasets.
- The method achieves robust diagnostic performance on public datasets.
- The approach has practical implications for industrial fault diagnosis.

## Abstract

To address the uneven distribution of fault categories in data sets for deep learning-based fault diagnosis, we propose a fault diagnosis framework combining an improved Variational Autoencoder (Similarity-Aware VAE) with a Wavelet-Convolutional 1D-CNN. The Similarity-Aware VAE employs a novel similarity loss function for data augmentation, measuring feature distances in high-dimensional space while automatically adjusting training parameters and weights through an enhanced attention mechanism to balance the dataset.The Wavelet-Convolutional 1D-CNN replaces the first convolutional layer of CNN with a Wavelet-Convolutional layer based on continuous wavelet transform, enabling multi-scale feature extraction for fault data analysis. Experimental validation using public datasets demonstrates that this method effectively enhances data quality while maintaining robust diagnostic performance, offering practical implications for industrial fault diagnosis.