Adjacent Neighborhood Transformer-based Diffusion Model for Anomaly Detection under Incomplete Industrial Data Sources

Anomaly detection in an industrial setting is crucial for operational monitoring, yet it remains challenging under incomplete data conditions. Common issues, such as sensor failures, data transmission loss, and storage malfunctions, often result in missing data, complicating the detection of anomalies, particularly when these are localized within specific regions. To address the challenges, this paper proposes DiffANT, an unsupervised anomaly detection method that integrates a diffusion model with the Adjacent Neighborhood Transformer (ANT). Specifically, DiffANT begins by applying various data masking techniques to simulate realistic missing values that reflect real-world industrial scenarios. The ANT utilizes a Transformer encoder architecture augmented with an adjacent neighborhood attention mechanism. It effectively focuses on relevant non-immediate vicinities to enhance anomaly detection. DiffANT then reconstructs the original data from randomly sampled noise through diffusion and denoising processes and utilizes a multi-level reconstruction strategy to refine the generated samples. We demonstrate the efficacy of DiffANT through extensive experiments in diverse industrial applications, such as secure water treatment and server machine monitoring. The results indicate that DiffANT consistently outperforms state-of-the-art methods in detecting anomalies in time series data, regardless of whether the data is incomplete.