Search for Author, Title, Keyword
Defect Categorization of Ribbon Blender Worm Gearbox Worm Wheel and Bearing Based on Artificial Neural Network
More details
Hide details
Department of Mechanical Engineering, MET’s Institute of Engineering, India
Department of Mechanical Engineering, Bramha Valley College of Engineering and Research Institute, India
Department of Computer Engineering, Brahma Valley College of Engineering and Research Institute, India
Department of Mechanical, S.N.D. College of Engineering & Research Centre, India
Submission date: 2023-12-05
Final revision date: 2023-12-31
Acceptance date: 2024-02-26
Online publication date: 2024-03-01
Publication date: 2024-03-01
Corresponding author
Raghavendra Rajendra Barshikar   

Department of Mechanical Engineering, MET’s Institute of Engineering, Adgaon, Nashik, India
Eksploatacja i Niezawodność – Maintenance and Reliability 2024;26(2):185371
  • Study of ribbon blender worm gearbox vibration signatures at different condition.
  • Usefulness of categorising coalesced i.e. combined worm gear and bearing faults in enhanced productivity, flexibility and agility.
  • Advantages of ANN for defect categorization over SVM.
There is a demand for worm gearboxes in diversified industrial fields that include machinery such as escalators, ribbon blenders, pulverisers, bowl mills, etc. because of their peculiar characteristics like torque and quick retardation. The most commonly occurring defects in a worm gear box are scratches that develop in the worm gear and in bearings. Early defect categorization is required to prevent a sudden breakdown that would decrease production. The defect is depicted in different cases, which include defects in the gear tooth and the outer and inner races of the bearing. In another case, the defect is considered in the gear tooth as well as the bearing. The severity is designated using the ANN. The experiments were performed under these conditions with a good worm gearbox to capture vibration response signatures. Using these values as an input to the ANN, the model is trained. Experimental results show that vibration amplitude increases with fault progression in the worm gearbox, and the trained ANN model effectively categorizes worm gearbox faults with an accuracy of 97.12%.
Journals System - logo
Scroll to top