Residual Life Predictions From Vibration-Based Degradation Signals: A Neural Network Approach

TLDR

Maintenance of mechanical equipment relies on bearing inspection, and identifying current and future bearing conditions is essential to prevent unexpected failures, yet most research focuses on fault diagnosis rather than failure prediction. This study develops neural‑network models to predict bearing failures. An accelerated bearing test rig collects vibration data until failure, training neural networks to estimate operating times, and the models are then applied to validation bearings and compared with actual lives to compute prediction errors. The best model achieves 64 % of predictions within 10 % of actual life and 92 % within 20 %.

Abstract

Maintenance of mechanical and rotational equipment often includes bearing inspection and/or replacement. Thus, it is important to identify current as well as future conditions of bearings to avoid unexpected failure. Most published research in this area is focused on diagnosing bearing faults. In contrast, this paper develops neural-network-based models for predicting bearing failures. An experimental setup is developed to perform accelerated bearing tests where vibration information is collected from a number of bearings that are run until failure. This information is then used to train neural network models on predicting bearing operating times. Vibration data from a set of validation bearings are then applied to these network models. Resulting predictions are then used to estimate the bearing failure time. These predictions are then compared with the actual lives of the validation bearings and errors are computed to evaluate the effectiveness of each model. For the best model, we find that 64% of predictions are within 10% of actual bearing life, while 92% of predictions are within 20% of the actual life.