본문 바로가기

Anomaly Detection in Industrial Machine Sounds Using High-Frequency Features and Gate Recurrent Unit Networks

문서 유형
연구출판물 · 학술지 논문
등재
SCIEScopus
저널 순위
JCR Q2Scopus Q1
저널
IEEE ACCESS13 · pp.77165 · 2025
피인용
Web of Science 2Scopus 6
FWCI (Scopus)
0.83
JCR IF
JCR 2024 3.6
ISSN
2169-3536

저자

  1. 레티투흐엉제1저자교신저자Pusan Natl Univ, Blockchain Platform Res Ctr, Pusan 609735, South Korea
  2. 아디푸트라 안드로 아프릴라Pusan Natl Univ, Sch Comp Sci & Engn, Pusan 609735, South Korea
  3. 윤지원Pusan Natl Univ, Sch Comp Sci & Engn, Pusan 609735, South Korea
  4. 김호원교신저자Pusan Natl Univ, Sch Comp Sci & Engn, Pusan 609735, South Korea

초록

Detecting anomalies in industrial sound is critical for maintaining operational efficiency, preventing costly equipment failures, and ensuring workplace safety. However, it presents significant challenges due to the complexity and variability of industrial environments, including background noise and fluctuating operating conditions. This paper proposes a comprehensive approach that leverages machine learning (ML) and deep learning (DL) techniques to address these challenges. Using three datasets, the Malfunctioning Industrial Machine Investigation and Inspection for Domain Generalization 2022 (MIMII DG 2022), the Detection and Classification of Acoustic Scenes and Events (DCASE) 2022, and DCASE 2024, we evaluate the performance of various ML and DL models under different experimental conditions. Our study focuses on feature extraction methods such as Mel-spectrograms and Mel-frequency Cepstral Coefficients (MFCCs) to capture critical acoustic characteristics of industrial machinery. Both supervised ML and DL techniques are employed to explore effective anomaly detection strategies. Extensive experimentation and evaluation using metrics such as confusion matrix, accuracy, precision, recall, and F1 score highlight the effectiveness of our approach in real-world industrial scenarios. Experimental results demonstrate that eXtreme Gradient Boosting (XGBoost) outperforms Support Vector Machine (SVM) and Decision Tree (DT) models in the ML approach across both feature sets. In the DL approach, Gated Recurrent Units (GRU) perform better on MFCC features than Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) networks. GRU emerges as the best-performing model on testing datasets, achieving a precision of 99.56% and an F1 score of 99.55% on the DCASE 2024 dataset, a precision of 94% and an F1 score of 93.95% on the DCASE 2022 dataset, and a precision of 92.2% and an F1 score of 92.06% on the MIMII DG 2022 dataset. These results underscore the potential of DL for real-time industrial sound analysis in predictive maintenance, offering significant improvements over traditional methods.

키워드

Anomalous sound detectionsupervised learninghigh-frequency featureMel-SpectrogramMel-frequency cepstral coefficientsgated recurrent unitsLEARNING APPROACHLSTM

식별자

Scopus EID
2-s2.0-105004036774
WoS UID
001483789800017