Abstract
In asset management of infrastructures, it is important to forecast their deterioration conditions. A multistage Weibull deterioration hazard model and its maximum likelihood estimation were developed in 2005 as a deterioration forecasting method considering elapsed years from initial time points. However, this method requires enormous estimation time. Hence a Markov deterioration hazard model, which expresses the deterioration process assuming its time stationarity, has been employed in the majority of practical cases owing to smallness of a computational load. In this paper, the authors propose a Bayesian estimation method (MCMC method) of the multi-stage Weibull deterioration hazard model using a quasi Monte Carlo method in order to reduce the computational load. Lastly, the effectiveness of this study can be discussed in the case study targeting expansion joints.
