Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Planing It by Ear: Convolutional Neural Networks for Acoustic Anomaly Detection in Industrial Wood Planers

Anthony Deschênes, Rémi Georges, Cem Subakan, Bruna Ugulino, Antoine Henry, Michael Morin

TL;DR

The paper tackles the challenge of detecting anomalies in wood-planer acoustics amid skilled-labor shortages by leveraging deep learning on mel-spectrogram representations. It introduces two architectures, a convolutional autoencoder with skip connections (Skip-CAE) and a Skip-CAE with transformer-based attention (Skip-CAE-Transformer), and demonstrates their superiority over baselines such as the DCASE autoencoder, One-Class SVM, and Isolation Forest on a new real-world industrial dataset. The authors release a large open dataset of planer sounds and show that the transformer-augmented model achieves the best performance (AUC up to 0.875), with strong per-anomaly-type results, including effective detection of stuck and uneven boards. This work advances practical acoustic anomaly detection for industrial settings, offering decision-support potential for novice operators and aligning with Industry 4.0 toward intelligent, audio-based monitoring.

Abstract

In recent years, the wood product industry has been facing a skilled labor shortage. The result is more frequent sudden failures, resulting in additional costs for these companies already operating in a very competitive market. Moreover, sawmills are challenging environments for machinery and sensors. Given that experienced machine operators may be able to diagnose defects or malfunctions, one possible way of assisting novice operators is through acoustic monitoring. As a step towards the automation of wood-processing equipment and decision support systems for machine operators, in this paper, we explore using a deep convolutional autoencoder for acoustic anomaly detection of wood planers on a new real-life dataset. Specifically, our convolutional autoencoder with skip connections (Skip-CAE) and our Skip-CAE transformer outperform the DCASE autoencoder baseline, one-class SVM, isolation forest and a published convolutional autoencoder architecture, respectively obtaining an area under the ROC curve of 0.846 and 0.875 on a dataset of real-factory planer sounds. Moreover, we show that adding skip connections and attention mechanism under the form of a transformer encoder-decoder helps to further improve the anomaly detection capabilities.

Planing It by Ear: Convolutional Neural Networks for Acoustic Anomaly Detection in Industrial Wood Planers

TL;DR

The paper tackles the challenge of detecting anomalies in wood-planer acoustics amid skilled-labor shortages by leveraging deep learning on mel-spectrogram representations. It introduces two architectures, a convolutional autoencoder with skip connections (Skip-CAE) and a Skip-CAE with transformer-based attention (Skip-CAE-Transformer), and demonstrates their superiority over baselines such as the DCASE autoencoder, One-Class SVM, and Isolation Forest on a new real-world industrial dataset. The authors release a large open dataset of planer sounds and show that the transformer-augmented model achieves the best performance (AUC up to 0.875), with strong per-anomaly-type results, including effective detection of stuck and uneven boards. This work advances practical acoustic anomaly detection for industrial settings, offering decision-support potential for novice operators and aligning with Industry 4.0 toward intelligent, audio-based monitoring.

Abstract

In recent years, the wood product industry has been facing a skilled labor shortage. The result is more frequent sudden failures, resulting in additional costs for these companies already operating in a very competitive market. Moreover, sawmills are challenging environments for machinery and sensors. Given that experienced machine operators may be able to diagnose defects or malfunctions, one possible way of assisting novice operators is through acoustic monitoring. As a step towards the automation of wood-processing equipment and decision support systems for machine operators, in this paper, we explore using a deep convolutional autoencoder for acoustic anomaly detection of wood planers on a new real-life dataset. Specifically, our convolutional autoencoder with skip connections (Skip-CAE) and our Skip-CAE transformer outperform the DCASE autoencoder baseline, one-class SVM, isolation forest and a published convolutional autoencoder architecture, respectively obtaining an area under the ROC curve of 0.846 and 0.875 on a dataset of real-factory planer sounds. Moreover, we show that adding skip connections and attention mechanism under the form of a transformer encoder-decoder helps to further improve the anomaly detection capabilities.
Paper Structure (8 sections, 4 figures, 2 tables)

This paper contains 8 sections, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Background on Wood-Processing Equipment Monitoring and Acoustic Anomaly Detection
  3. Real Planing Mill Dataset
  4. Building the Anomaly Detection Models
  5. Experiments: Evaluating the Models
  6. Results for all anomalies
  7. Results per anomaly type
  8. Conclusion

Figures (4)

  • Figure 1: Architecture of the CAE with skip connections
  • Figure 2: Architecture of the CAE with skip connections and transformer
  • Figure 3: ROC curves, AUC and pAUC of the different models on the evaluation set
  • Figure 4: Mel spectogram of an anomaly (broken board) and the reconstructed mel spectograms of the neural network models with their reconstruction errors