A Machine Learning Approach for Gearbox System Fault Diagnosis
Jan Vrba,
Matous Cejnek,
Jakub Steinbach,
Zuzana Krbcova
Affiliations
Jan Vrba
Department of Computing and Control Engineering, Faculty of Chemical Engineering, University of Chemistry and Technology, Technicka 5, 166 28 Prague, Czech Republic
Matous Cejnek
Department of Instrumentation and Control Engineering, Faculty of Mechanical Engineering, Center of Advanced Aerospace Technology, Czech Technical University in Prague, Technicka Street 4, 166 07 Prague, Czech Republic
Jakub Steinbach
Department of Computing and Control Engineering, Faculty of Chemical Engineering, University of Chemistry and Technology, Technicka 5, 166 28 Prague, Czech Republic
Zuzana Krbcova
Department of Computing and Control Engineering, Faculty of Chemical Engineering, University of Chemistry and Technology, Technicka 5, 166 28 Prague, Czech Republic
This study proposes a fully automated gearbox fault diagnosis approach that does not require knowledge about the specific gearbox construction and its load. The proposed approach is based on evaluating an adaptive filter’s prediction error. The obtained prediction error’s standard deviation is further processed with a support-vector machine to classify the gearbox’s condition. The proposed method was cross-validated on a public dataset, segmented into 1760 test samples, against two other reference methods. The accuracy achieved by the proposed method was better than the accuracies of the reference methods. The accuracy of the proposed method was on average 9% higher compared to both reference methods for different support vector settings.
