Application of Support Vector Regression to predict the Remaining useful life of Polymerized Styrene Butadiene Rubber of cable insulation

Rubber is widely used in aviation, aerospace and other important fields. Monitoring properties of rubber and predicting its remaining life is the key to ensuring timely repair and replacement, and it is related to the safety and reliability of equipment. The traditional methods of life calculation is limited by the study of environment and mechanism. The data-driven is more concise and efficient and it can characterize the coupling effect of many factors for the life of rubber. Support Vector Machine (SVM) is a data-driven method for solving small sample and nonlinear problems with good robustness. In this paper the support vector regression(SVR) algorithm was applied to the prediction of rubber life. We used a certain type Polymerized Styrene Butadiene Rubber cable insulation as an example, the temperature and the concentration of oil mist were set as the features to predict the remaining life. The model was trained by accelerated aging test data, and its remaining life was calculated according to its break elongation retention rate at the end of life. Compared with the actual test results and the pridicted results of linear regression model, the applicability of the method was discussed.