FaultDiffusion: Few-Shot Fault Time Series Generation with Diffusion Model

TL;DR

FaultDiffusion introduces a diffusion-based framework for generating diverse and authentic fault time series in few-shot scenarios, addressing data scarcity in industrial fault diagnosis.

Contribution

The paper presents a novel diffusion model with a positive-negative difference adapter and diversity loss for improved fault data synthesis in few-shot settings.

Findings

Outperforms traditional methods in authenticity and diversity

Achieves state-of-the-art results on key benchmarks

Effectively models fault distributions with limited data

Abstract

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.