# TFN: An Interpretable Neural Network with Time-Frequency Transform Embedded for Intelligent Fault Diagnosis

arXiv: https://arxiv.org/abs/2209.01992 · HTML: https://mlsanity.com/paper/2209.01992/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 49 references that are in the map.
- First posted on arXiv 5 Sep 2022.

## Builds on (most cited first, 16 of 16)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [A Survey on Neural Network Interpretability](https://mlsanity.com/paper/2012.14261/) (2020)
- [Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives](https://mlsanity.com/paper/1802.07623/) (2018)
- [Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions](https://mlsanity.com/paper/1710.04806/) (2017)
- [Visual Interpretability for Deep Learning: a Survey](https://mlsanity.com/paper/1802.00614/) (2018)
- [On Interpretability of Artificial Neural Networks: A Survey](https://mlsanity.com/paper/2001.02522/) (2020)
- [Fully Learnable Deep Wavelet Transform for Unsupervised Monitoring of High-Frequency Time Series](https://mlsanity.com/paper/2105.00899/) (2021)
- [WaveletKernelNet: An Interpretable Deep Neural Network for Industrial Intelligent Diagnosis](https://mlsanity.com/paper/1911.07925/) (2019)
- [Interpretable Convolutional Filters with SincNet](https://mlsanity.com/paper/1811.09725/) (2018)
- [Deep Learning Algorithms for Rotating Machinery Intelligent Diagnosis: An Open Source Benchmark Study](https://mlsanity.com/paper/2003.03315/) (2020)
- [Using Filter Banks in Convolutional Neural Networks for Texture Classification](https://mlsanity.com/paper/1601.02919/) (2016)
- [Rethinking 3D LiDAR Point Cloud Segmentation](https://mlsanity.com/paper/2008.03928/) (2020)

## Built on by (most cited first, 3 of 3)

- [Interpreting What Typical Fault Signals Look Like via Prototype-matching](https://mlsanity.com/paper/2403.07033/) (2024)
- [CS-SHAP: Extending SHAP to Cyclic-Spectral Domain for Better Interpretability of Intelligent Fault Diagnosis](https://mlsanity.com/paper/2502.06424/) (2025)
- [Modulated differentiable STFT and balanced spectrum metric for freight train wheelset bearing cross-machine transfer monitoring under speed fluctuations](https://mlsanity.com/paper/2406.11917/) (2024)

## Abstract (arXiv)

Convolutional Neural Networks (CNNs) are widely used in fault diagnosis of mechanical systems due to their powerful feature extraction and classification capabilities. However, the CNN is a typical black-box model, and the mechanism of CNN's decision-making are not clear, which limits its application in high-reliability-required fault diagnosis scenarios. To tackle this issue, we propose a novel interpretable neural network termed as Time-Frequency Network (TFN), where the physically meaningful time-frequency transform (TFT) method is embedded into the traditional convolutional layer as an adaptive preprocessing layer. This preprocessing layer named as time-frequency convolutional (TFconv) layer, is constrained by a well-designed kernel function to extract fault-related time-frequency information. It not only improves the diagnostic performance but also reveals the logical foundation of the CNN prediction in the frequency domain. Different TFT methods correspond to different kernel functions of the TFconv layer. In this study, four typical TFT methods are considered to formulate the TFNs and their effectiveness and interpretability are proved through three mechanical fault diagnosis experiments. Experimental results also show that the proposed TFconv layer can be easily generalized to other CNNs with different depths. The code of TFN is available on https://github.com/ChenQian0618/TFN.