Selection of Best Classification Algorithm for Fault Diagnosis of Bearing using Vibration Signature Analysis
Pavan Agrawal1, Pratesh Jayaswal2
1Pavan Agrawal, Department of Mechanical Engineering, Madhav Institute of Technology and Science, Gwalior (M.P), India.
2Dr. Pratesh Jayaswal, Department of Mechanical Engineering, Madhav Institute of Technology and Science, Gwalior (M.P), India.
Manuscript received on 07 March 2019 | Revised Manuscript received on 20 March 2019 | Manuscript published on 30 March 2019 | PP: 538-546 | Volume-8 Issue-5, March 2019 | Retrieval Number: D3181028419/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The selection of an appropriate classification algorithm is an important issue that should be addressed in the fault diagnosis of the bearing. The vibration signatures of healthy and faulty bearings in running conditions have been acquired in time domain using FFT analyzer and convert into wavelets. The most valuable statistical features of different bearing signals are extracted from morlet wavelets and were fed to classification algorithms to classify the bearing faults. Four machine learning techniques such as artificial neural network (ANN), decision tree (DT), k- nearest neighbor (kNN), and support vector machine (SVM) are utilized as classification algorithms. Finally SVM reports the better classification outcomes than others.
Keyword: ANN, DT, Knn, Rolling Element Bearing, Statistical Features, SVM.
Scope of the Article: Classification