Natural rubber components fatigue life estimation through an extreme learning machine

Abstract

In engineering applications, natural rubber components are subjected to continuous alternating loads, resulting in fatigue failure. Although some theoretical models are used for the fatigue life estimation of rubber materials, they do not comprehensively consider the influence of multiple factors. In the present study, a model based on the extreme learning machine is established to estimate the fatigue life of natural rubber specimens. The mechanical load, peak engineering strain, ambient temperature, and shore hardness of natural rubber specimens are used as the input variables while the measured average fatigue life is used as the output variable of the extreme learning machine model. The performed analyses reveal that the regression results and predicted life of the established extreme learning machine model are encouraging. The backpropagation neural network model and the support vector machine model are implemented to evaluate the performance of the established model. It is concluded that the extreme learning machine model is superior to the backpropagation neural network and support vector machine models in accuracy and efficiency. The extreme learning machine model provides an effective means for accurately predicting the fatigue life of natural rubber components.