Predictions of Machine Vibrations Using Artificial Neural Networks Trained by Gravitational Search Algorithm and Back-Propagation Algorithm

Abstract

Since the vibration is the main factor to result in machine faults, predictions of machine vibrations are necessary for improving operational efficiency, product quality, and safety. This raises the need to have an effective model that can be used to predict machine vibrations. In this study, an Artificial Neural Network (ANN) model along with Gravitational Search Algorithm (GSA) and a Back-Propagation (BP) Algorithm - Gradient Descent with Momentum (GDM) is proposed. We first identify the factors that may cause machine vibrations and then construct a dataset. The hybrid algorithm of improved GSA and GDM is then utilized to optimize the weights between layers and biases of the neural network. A real application is used to illustrate the applicability of the model. The results show that the proposed approach achieves a high accuracy. The results are also compared with those obtained from the ANN-based models trained by other algorithms. The comparative analysis indicates that the proposed model performs better than the others. It is expected that the proposed model may be used in the prediction of machine vibrations and can aid in the development of a novel approach for prediction issues faced in machine tools industry.