Acoustic Anomaly Detection for Machine Sounds based on Image Transfer Learning

TL;DR

This paper introduces a novel approach for acoustic machine malfunction detection using transfer learning from image classification neural networks, outperforming autoencoder-based methods in noisy factory environments.

Contribution

It proposes using pretrained image classification networks for feature extraction in acoustic anomaly detection, demonstrating improved performance over autoencoder methods.

Findings

ResNet features outperform AlexNet and SqueezeNet.

Gaussian Mixture Models and One-Class SVMs achieve top detection results.

Transfer learning enhances anomaly detection in noisy industrial settings.

Abstract

In industrial applications, the early detection of malfunctioning factory machinery is crucial. In this paper, we consider acoustic malfunction detection via transfer learning. Contrary to the majority of current approaches which are based on deep autoencoders, we propose to extract features using neural networks that were pretrained on the task of image classification. We then use these features to train a variety of anomaly detection models and show that this improves results compared to convolutional autoencoders in recordings of four different factory machines in noisy environments. Moreover, we find that features extracted from ResNet based networks yield better results than those from AlexNet and Squeezenet. In our setting, Gaussian Mixture Models and One-Class Support Vector Machines achieve the best anomaly detection performance.