CoopASD: Cooperative Machine Anomalous Sound Detection with Privacy Concerns

TL;DR

CoopASD introduces a privacy-preserving, decentralized machine anomalous sound detection framework that enables multiple factories to collaboratively develop robust ASD models without sharing raw data.

Contribution

The paper proposes a novel federated learning framework for ASD that handles non-iid data and domain shifts, improving privacy and scalability in industrial settings.

Findings

Achieves competitive performance with only 0.08% degradation compared to centralized models.

Effectively stabilizes models under non-iid and domain shift conditions.

Demonstrates the practicality of privacy-preserving collaborative ASD in real-world factories.

Abstract

Machine anomalous sound detection (ASD) has emerged as one of the most promising applications in the Industrial Internet of Things (IIoT) due to its unprecedented efficacy in mitigating risks of malfunctions and promoting production efficiency. Previous works mainly investigated the machine ASD task under centralized settings. However, developing the ASD system under decentralized settings is crucial in practice, since the machine data are dispersed in various factories and the data should not be explicitly shared due to privacy concerns. To enable these factories to cooperatively develop a scalable ASD model while preserving their privacy, we propose a novel framework named CoopASD, where each factory trains an ASD model on its local dataset, and a central server aggregates these local models periodically. We employ a pre-trained model as the backbone of the ASD model to improve its robustness and develop specialized techniques to stabilize the model under a completely non-iid and domain shift setting. Compared with previous state-of-the-art (SOTA) models trained in centralized settings, CoopASD showcases competitive results with negligible degradation of 0.08%. We also conduct extensive ablation studies to demonstrate the effectiveness of CoopASD.