The Identification of the Natural Frequency of Rolling Bearing Rotor System Based on Combined Genetic Neural Network
During identifying the natural frequency of the rolling bearing rotor system, due to the complex non-linear relationship between the factors which influence the natural frequency, it is hard to establish a complete and accurate theoretical model. Based on the self-learning ability and approximation of non-linear mapping capability of the artificial neural network (ANN) and the powerful ability of global optimization of the genetic algorithm (GA), the paper establishes combined genetic neural network (GA–ANN) through optimizing the ANN by GA. This method establishes the mapping between a rolling bearing rotor system natural frequency and the various parameters, which reduces the calculation of the workload greatly for the study of the similar rotor structure’s natural frequency. Through using the network model to predict the natural frequency of rolling bearing rotor system under different parameters, we finally find that the predicted values are in good agreement with the experimental data, which indicates that the method is powerful in identification.
T. R. Ma et al., "The Identification of the Natural Frequency of Rolling Bearing Rotor System Based on Combined Genetic Neural Network", Applied Mechanics and Materials, Vols. 29-32, pp. 436-441, 2010