Disentangling Physical Parameters for Anomalous Sound Detection Under Domain Shifts

TL;DR

This paper introduces a novel method using disentangled normalizing flows to detect anomalous sounds in machines under domain shifts, significantly reducing false positives and improving detection accuracy.

Contribution

It proposes constraining latent variables in normalizing flows to represent physical parameters, enabling invariant feature learning under domain shifts.

Findings

Disentangled velocity as a physical parameter improved AUC by 13.2%.

Invariant latent space reduced false positives in anomaly detection.

Method outperformed conventional approaches under domain shifts.

Abstract

To develop a sound-monitoring system for machines, a method for detecting anomalous sound under domain shifts is proposed. A domain shift occurs when a machine's physical parameters change. Because a domain shift changes the distribution of normal sound data, conventional unsupervised anomaly detection methods can output false positives. To solve this problem, the proposed method constrains some latent variables of a normalizing flows (NF) model to represent physical parameters, which enables disentanglement of the factors of domain shifts and learning of a latent space that is invariant with respect to these domain shifts. Anomaly scores calculated from this domain-shift-invariant latent space are unaffected by such shifts, which reduces false positives and improves the detection performance. Experiments were conducted with sound data from a slide rail under different operation velocities. The results show that the proposed method disentangled the velocity to obtain a latent space that was invariant with respect to domain shifts, which improved the AUC by 13.2% for Glow with a single block and 2.6% for Glow with multiple blocks.