A remaining useful life estimation model of drop system based on data driven and Bayesian theory

In this study, an estimation method of remaining useful life (RUL) for drop system is proposed based on the principal component analysis method and the Bayesian inference method. Not only the life model of the nonlinear drop system is calculated according to the stress-strain curve for the cushioning material, but also the test data fusion is performed to update the health index data based on principal component analysis. Moreover, the Bayesian inference method is applied to establish the useful life model, which can consider the effects of uncertainties. Then, the Bayesian model of the drop system parameters can be established. Also, the posterior probability of model parameters can be obtained. Based on Markov Chain Monte Carlo strategy, the Metropolis Hastings method is utilized here to update the model parameters and estimate the distribution of the remaining useful life of the material at a given specific state. A case study is introduced to show the application of the proposed method.