An integrated support vector regression-imperialist competitive algorithm for reliability estimation of a shearing machine

In this study, a support vector regression (SVR) model is developed for reliability estimation. An imperialist competitive algorithm is applied for selecting the SVR parameters such as subset of, epsilon, and sigma. The proposed model is validated by applying it to a benchmark data set. Satisfactory performance of the proposed model with respect to the data set is demonstrated through a comparative study. A shearing machine operating at an electric tableau manufacturing company is considered a case study. A set of data representing the time-to-failure (TTF) of the shearing machine is used to calculate the cumulative TTF for reliability modelling. The experimental results indicate that the proposed model achieves high estimation accuracy.