Intelligent worm gearbox fault diagnosis under various working conditions using vibration, sound and thermal features

Karabacak Y. E., Gürsel Özmen N., Gümüşel L.

APPLIED ACOUSTICS, cilt.186, 2022 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 186
  • Basım Tarihi: 2022
  • Doi Numarası: 10.1016/j.apacoust.2021.108463
  • Dergi Adı: APPLIED ACOUSTICS
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, PASCAL, Communication & Mass Media Index, Compendex, ICONDA Bibliographic, INSPEC, DIALNET
  • Anahtar Kelimeler: Fault detection, Condition monitoring, Vibration measurement, Sound measurement, Fault classification, Worm gears, Artificial neural networks, Support vector machines, ARTIFICIAL NEURAL-NETWORK, SUPPORT VECTOR MACHINE, BEARING FAULT, ROTATING MACHINERY, FEATURE-EXTRACTION, WEAR DEBRIS, PREDICTION, SIGNATURE
  • Karadeniz Teknik Üniversitesi Adresli: Evet

Özet

Worm gearboxes (WG) are frequently used in many areas of the industry. WG is different from other gearbox types and due to their working principles they are under high risk of wear and fault. Therefore, detection of faults that may occur in WG and taking measures accordingly are especially important for systems and facilities that require uninterrupted operation. This paper introduces an intelligent feature selection and classification method for fault diagnosis of WGs under different working conditions. The novelty of the study lies in the selection of feature sources and different loading and speed conditions for condition monitoring studies of WGs experimentally. Fault detection and classification were performed based on vibration, sound and thermal images data which were acquired and processed from the healthy and the faulty WG. Apart from classical studies, time and frequency domain features and thermal images features were extracted and evaluated singularly, dual or triple forms with ANN (Artificial Neural Network) and SVM (Support Vector Machines) classifiers. Reasonable classification performances for fault detection were observed when the features of all three sources used (99.2% with ANN and 98.7% with SVM). ANN and SVM classification performances are almost equal for fault classification (98.9% with SVM and 98.6% with ANN). The findings of the study would be a possible means for online condition monitoring of industrial plants, conveyors, elevators, etc. (C) 2021 Elsevier Ltd. All rights reserved.