Study on pavement design based on MC-SVM method of reliability

Aiming at reliability analysis problems with implicit performance functions and strongly nonlinear features in the pavement engineering, a new method for reliability analysis based on mente carlo(MC) theory and support vector machine(SVM) is developed. Due to strongly nonlinear mapping ability of SVM, the SVM model is employed to establish the nonlinear mapping relationship between basic random variables and engineering structural response action. SVM model is learned by samples generated from uniform design method and FLAC3D programs. The learned SVM model is integrated with Monte Carlo method to calculate the failure probability and reliability. The validity of the proposed method is verified by one pavement engineering examples, it has better precision and high efficiency. The results are in good agreement with the actual situations, and the experience and method could benefit other similar projects.