Machine-Learning-Based Wear Prediction in Journal Bearings under Start–Stop Conditions

Lubricants, vol. 12, pp. 290

Abstract

The present study aims to efficiently predict the wear volume of a journal bearing under start–stop operating conditions. For this purpose, the wear data generated with coupled mixed-elasto-hydrodynamic lubrication (mixed-EHL) and a wear simulation model of a journal bearing are used to develop a neural network (NN)-based surrogate model that is able to predict the wear volume based on the operational parameters. The suitability of different time series forecasting NN architectures, such as Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Nonlinear Autoregressive with Exogenous Inputs (NARX), is studied. The highest accuracy is achieved using the NARX network architectures.

Authors 4

1. Florian König corresponding Aachen Institute for Machine Elements and Systems Engineering

   RWTH Aachen University

   Affiliation as printed

   Institute for Machine Elements and Systems Engineering, RWTH Aachen University, Schinkelstrasse 10, 52062 Aachen, Germany

2. Florian Wirsing Aachen Institute for Machine Elements and Systems Engineering

   RWTH Aachen University

   Affiliation as printed

   Institute for Machine Elements and Systems Engineering, RWTH Aachen University, Schinkelstrasse 10, 52062 Aachen, Germany

3. Ankit Singh Aachen Institute for Machine Elements and Systems Engineering

   RWTH Aachen University

   Affiliation as printed

   Institute for Machine Elements and Systems Engineering, RWTH Aachen University, Schinkelstrasse 10, 52062 Aachen, Germany

4. Georg Jacobs Aachen Institute for Machine Elements and Systems Engineering

   RWTH Aachen University

   Affiliation as printed

   Institute for Machine Elements and Systems Engineering, RWTH Aachen University, Schinkelstrasse 10, 52062 Aachen, Germany