Audio-based Anomaly Detection in Industrial Machines Using Deep One-Class Support Vector Data Description

TL;DR

This paper explores audio-based anomaly detection in industrial machines using deep SVDD, demonstrating improved accuracy and efficiency over autoencoders across various noise conditions.

Contribution

It introduces a deep SVDD approach with subspace dimension tuning for machine sound anomaly detection, outperforming autoencoders in accuracy and computational efficiency.

Findings

Deep SVDD achieves higher AUC scores than autoencoders.

Deep SVDD uses significantly fewer trainable parameters.

Performance varies with SNR levels, favoring deep SVDD.

Abstract

The frequent breakdowns and malfunctions of industrial equipment have driven increasing interest in utilizing cost-effective and easy-to-deploy sensors, such as microphones, for effective condition monitoring of machinery. Microphones offer a low-cost alternative to widely used condition monitoring sensors with their high bandwidth and capability to detect subtle anomalies that other sensors might have less sensitivity. In this study, we investigate malfunctioning industrial machines to evaluate and compare anomaly detection performance across different machine types and fault conditions. Log-Mel spectrograms of machinery sound are used as input, and the performance is evaluated using the area under the curve (AUC) score for two different methods: baseline dense autoencoder (AE) and one-class deep Support Vector Data Description (deep SVDD) with different subspace dimensions. Our results over the MIMII sound dataset demonstrate that the deep SVDD method with a subspace dimension of 2 provides superior anomaly detection performance, achieving average AUC scores of 0.84, 0.80, and 0.69 for 6 dB, 0 dB, and -6 dB signal-to-noise ratios (SNRs), respectively, compared to 0.82, 0.72, and 0.64 for the baseline model. Moreover, deep SVDD requires 7.4 times fewer trainable parameters than the baseline dense AE, emphasizing its advantage in both effectiveness and computational efficiency.