Strategy for diagnosing gear defects by digital twin-assisted supervised classification on a ball mill drivetrain (ISMA-USD-2022) - Archive ouverte HAL Access content directly
Conference Papers Year :

Strategy for diagnosing gear defects by digital twin-assisted supervised classification on a ball mill drivetrain (ISMA-USD-2022)

(1) , (1) , (2) , (1)
1
2

Abstract

This work, proposes a methodology for gear fault diagnosis, based on digital twin driven supervised classification. The challenge is to build a good classification model using a dataset combining both datasets from physical system and digital twin. Numerical data are based on a 24 D.O.F single stage gearbox model, updating by varying some parameters. The approach developed in this work is tested on two types of hybrid datasets; homogeneous and heterogeneous for training MLA’s. It allows to obtain diagnosis accuracy of gear defects about 0.86 and 0.95, with respectively, support vector machines (SVM) and k-nearest neighbors (KNN) algorithms. Training phase is ensured by dataset containing fist 25% (one historical state), and 50% experimental data (Two historical states) , completed respectively by 75%(Tree novel states to be detected) and 50% of numerical data (Two novel states to be detected) of training dataset.
Not file

Dates and versions

hal-03818472 , version 1 (17-10-2022)

Identifiers

  • HAL Id : hal-03818472 , version 1

Cite

Gauthier Ngandu Kalala, Xavier Chiementin, L. Rasolofondraibe, Abir Boujelben. Strategy for diagnosing gear defects by digital twin-assisted supervised classification on a ball mill drivetrain (ISMA-USD-2022). International Conference on Noise and Vibration Engineering (ISMA), KU Leuven, 2022, Leuven, Belgium. ⟨hal-03818472⟩
36 View
0 Download

Share

Gmail Facebook Twitter LinkedIn More