FaultDiffusion: Few-Shot Fault Time Series Generation with Diffusion Model
This work addresses the challenge of fault diagnosis in industrial systems by enabling more effective data-driven approaches through improved synthetic fault data generation, though it is incremental as it builds on existing diffusion models.
The paper tackled the problem of generating fault time series data for industrial equipment monitoring under few-shot conditions, where fault data is scarce, by proposing a diffusion model framework with a positive-negative difference adapter and diversity loss, achieving state-of-the-art performance in authenticity and diversity on key benchmarks.
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.