FaultDiffusion: Few-Shot Fault Time Series Generation with Diffusion Model
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918209289977856 |
|---|---|
| author | Xu, Yi Chen, Zhigang Wang, Rui Li, Yangfan Tang, Fengxiao Zhao, Ming Liu, Jiaqi |
| author_facet | Xu, Yi Chen, Zhigang Wang, Rui Li, Yangfan Tang, Fengxiao Zhao, Ming Liu, Jiaqi |
| contents | In industrial equipment monitoring, fault diagnosis is critical for ensuring system reliability and enabling predictive maintenance. However, the scarcity of fault data, due to the rarity of fault events and the high cost of data annotation, significantly hinders data-driven approaches. Existing time-series generation models, optimized for abundant normal data, struggle to capture fault distributions in few-shot scenarios, producing samples that lack authenticity and diversity due to the large domain gap and high intra-class variability of faults. To address this, we propose a novel few-shot fault time-series generation framework based on diffusion models. Our approach employs a positive-negative difference adapter, leveraging pre-trained normal data distributions to model the discrepancies between normal and fault domains for accurate fault synthesis. Additionally, a diversity loss is introduced to prevent mode collapse, encouraging the generation of diverse fault samples through inter-sample difference regularization. Experimental results demonstrate that our model significantly outperforms traditional methods in authenticity and diversity, achieving state-of-the-art performance on key benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_15174 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FaultDiffusion: Few-Shot Fault Time Series Generation with Diffusion Model Xu, Yi Chen, Zhigang Wang, Rui Li, Yangfan Tang, Fengxiao Zhao, Ming Liu, Jiaqi Machine Learning Artificial Intelligence In industrial equipment monitoring, fault diagnosis is critical for ensuring system reliability and enabling predictive maintenance. However, the scarcity of fault data, due to the rarity of fault events and the high cost of data annotation, significantly hinders data-driven approaches. Existing time-series generation models, optimized for abundant normal data, struggle to capture fault distributions in few-shot scenarios, producing samples that lack authenticity and diversity due to the large domain gap and high intra-class variability of faults. To address this, we propose a novel few-shot fault time-series generation framework based on diffusion models. Our approach employs a positive-negative difference adapter, leveraging pre-trained normal data distributions to model the discrepancies between normal and fault domains for accurate fault synthesis. Additionally, a diversity loss is introduced to prevent mode collapse, encouraging the generation of diverse fault samples through inter-sample difference regularization. Experimental results demonstrate that our model significantly outperforms traditional methods in authenticity and diversity, achieving state-of-the-art performance on key benchmarks. |
| title | FaultDiffusion: Few-Shot Fault Time Series Generation with Diffusion Model |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2511.15174 |