Using a SVM to evaluate damage to vibration isolators in an elastic raft system

Abstract

Predicting damage to vibration isolators in a raft experiencing heavy shock loadings from explosions is an important task when designing a raft system. It is also vital to be able to research the vulnerability of heavily shocked floating rafts. The conventional approach to prediction has been unreliable, especially when the allowable values or ultimate values of vibration isolators of supposedly uniform standard in a raft actually have differing and uncertain values due to defective workmanship. A new model for predicting damage to vibration isolators in a shocked floating raft system is presented in this paper. It is based on a support vector machine(SVM), which uses Artificial Intelligence to characterize complicated nonlinear mapping between the impacting environment and damage to the vibration isolators. The effectiveness of the new method for predicting damage was illustrated by numerical simulations, and shown to be effective when relevant parameters of the model were chosen reasonably. The effect determining parameters, including kernel function and penalty factors, has on prediction results is also discussed. It can be concluded that the SVM will probably become a valid tool to study damage or vulnerability in a shocked raft system.