Using Temporal Convolutional Autoencoders for Sound-Based Fault Detection in Industrial Machinery
TL;DR
This work detects anomalies by introducing a feature engineering pipeline that structures univariate acoustic signals into sequential multivariate representations via Mel Frequency Cepstral Coefficients (MFCCs) and confirms the effectiveness of sequential reconstruction-based models for continuous machine operations while highlighting specific open challenges in acoustic industrial monitoring.
Abstract
We propose using two deep autoencoder architectures, i.e. the Temporal Convolutional Network Autoencoder (TCN-AE) and Wasserstein Autoencoder with Generative Adversarial Network (WAE-GAN), to perform anomaly detection in the industrial context. In this work, we detect anomalies by introducing a feature engineering pipeline that structures univariate acoustic signals into sequential multivariate representations via Mel Frequency Cepstral Coefficients (MFCCs). The trained models were evaluated using 10-fold cross-validation, and their performances were assessed through an empirical analysis of hyperparameter sensitivity, mapping prominent structural configurations for each neural architecture. The optimized TCN-AE showed superior performance, achieving an average AUC-ROC of 0.8716 for pump devices and 0.7834 for fan devices, thereby surpassing state-of-the-art literature benchmarks, while also demonstrating robust performance for the slider device with an average AUC-ROC of 0.9646. Both architectures presented limitations with the valve device due to its highly transient behavior. The results achieved confirm the effectiveness of sequential reconstruction-based models for continuous machine operations while highlighting specific open challenges in acoustic industrial monitoring.