CS-SHAP: Extending SHAP to Cyclic-Spectral Domain for Better Interpretability of Intelligent Fault Diagnosis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929706984538112 |
|---|---|
| author | Chen, Qian Dong, Xingjian Hu, Kui Chen, Kangkang Peng, Zhike Meng, Guang |
| author_facet | Chen, Qian Dong, Xingjian Hu, Kui Chen, Kangkang Peng, Zhike Meng, Guang |
| contents | Neural networks (NNs), with their powerful nonlinear mapping and end-to-end capabilities, are widely applied in mechanical intelligent fault diagnosis (IFD). However, as typical black-box models, they pose challenges in understanding their decision basis and logic, limiting their deployment in high-reliability scenarios. Hence, various methods have been proposed to enhance the interpretability of IFD. Among these, post-hoc approaches can provide explanations without changing model architecture, preserving its flexibility and scalability. However, existing post-hoc methods often suffer from limitations in explanation forms. They either require preprocessing that disrupts the end-to-end nature or overlook fault mechanisms, leading to suboptimal explanations. To address these issues, we derived the cyclic-spectral (CS) transform and proposed the CS-SHAP by extending Shapley additive explanations (SHAP) to the CS domain. CS-SHAP can evaluate contributions from both carrier and modulation frequencies, aligning more closely with fault mechanisms and delivering clearer and more accurate explanations. Three datasets are utilized to validate the superior interpretability of CS-SHAP, ensuring its correctness, reproducibility, and practical performance. With open-source code and outstanding interpretability, CS-SHAP has the potential to be widely adopted and become the post-hoc interpretability benchmark in IFD, even in other classification tasks. The code is available on https://github.com/ChenQian0618/CS-SHAP. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_06424 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CS-SHAP: Extending SHAP to Cyclic-Spectral Domain for Better Interpretability of Intelligent Fault Diagnosis Chen, Qian Dong, Xingjian Hu, Kui Chen, Kangkang Peng, Zhike Meng, Guang Machine Learning Artificial Intelligence Neural networks (NNs), with their powerful nonlinear mapping and end-to-end capabilities, are widely applied in mechanical intelligent fault diagnosis (IFD). However, as typical black-box models, they pose challenges in understanding their decision basis and logic, limiting their deployment in high-reliability scenarios. Hence, various methods have been proposed to enhance the interpretability of IFD. Among these, post-hoc approaches can provide explanations without changing model architecture, preserving its flexibility and scalability. However, existing post-hoc methods often suffer from limitations in explanation forms. They either require preprocessing that disrupts the end-to-end nature or overlook fault mechanisms, leading to suboptimal explanations. To address these issues, we derived the cyclic-spectral (CS) transform and proposed the CS-SHAP by extending Shapley additive explanations (SHAP) to the CS domain. CS-SHAP can evaluate contributions from both carrier and modulation frequencies, aligning more closely with fault mechanisms and delivering clearer and more accurate explanations. Three datasets are utilized to validate the superior interpretability of CS-SHAP, ensuring its correctness, reproducibility, and practical performance. With open-source code and outstanding interpretability, CS-SHAP has the potential to be widely adopted and become the post-hoc interpretability benchmark in IFD, even in other classification tasks. The code is available on https://github.com/ChenQian0618/CS-SHAP. |
| title | CS-SHAP: Extending SHAP to Cyclic-Spectral Domain for Better Interpretability of Intelligent Fault Diagnosis |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2502.06424 |