# Multi-scale Fusion Fault Diagnosis Method Based on Two-Dimensionaliztion Sequence in Complex Scenarios

arXiv: https://arxiv.org/abs/2304.05198 · HTML: https://mlsanity.com/paper/2304.05198/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 29 references that are in the map.
- First posted on arXiv 11 Apr 2023.

## Builds on (most cited first, 10 of 10)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Importance Estimation for Neural Network Pruning](https://mlsanity.com/paper/1906.10771/) (2019)
- [CNN Features off-the-shelf: an Astounding Baseline for Recognition](https://mlsanity.com/paper/1403.6382/) (2014)
- [Local Descriptors Optimized for Average Precision](https://mlsanity.com/paper/1804.05312/) (2018)
- [Understanding Generalization and Optimization Performance of Deep CNNs](https://mlsanity.com/paper/1805.10767/) (2018)
- [Progressive Local Filter Pruning for Image Retrieval Acceleration](https://mlsanity.com/paper/2001.08878/) (2020)

## Abstract (arXiv)

Rolling bearings are critical components in rotating machinery, and their faults can cause severe damage. Early detection of abnormalities is crucial to prevent catastrophic accidents. Traditional and intelligent methods have been used to analyze time series data, but in real-life scenarios, sensor data is often noisy and cannot be accurately characterized in the time domain, leading to mode collapse in trained models. Two-dimensionalization methods such as the Gram angle field method (GAF) or interval sampling have been proposed, but they lack mathematical derivation and interpretability. This paper proposes an improved GAF combined with grayscale images for convolution scenarios. The main contributions include illustrating the feasibility of the approach in complex scenarios, widening the data set, and introducing an improved convolutional neural network method with a multi-scale feature fusion diffusion model and deep learning compression techniques for deployment in industrial scenarios.