Palencia, O.G., Teixeira, A.P. and Guedes Soares, C. (2017), “Modelling of deterioration processes in ship structures through Dynamic Bayesian Networks”, 12th International Conference on Structural Safety & Reliability (ICOSSAR 2017), 6-10 August, TU Wien, Vienna, Austria, pp. 1936-1946

The paper studies the application of dynamic Bayesian Networks for modelling degradation processes in ship structures. The theoretical background on temporal models in general and Dynamic Bayesian Networks (DBN) in particular is presented. A DBN tool consisting of a Matlab code for performing inference is implemented and applied to develop the probabilistic model of the ultimate strength of a ship plate under compression subjected to corrosion degradation. A non-linear time dependent empirical corrosion model is adopted for predicting the corrosion wastage in ship plates. A series of simulated corrosion wastage measurements are used to increase the accuracy of the predictions. The results are validated against those obtained by Monte Carlo simulation. Finally, several parametric studies are conducted to investigate how changes in observations, in the interval between inspections, in the inference algorithm and in the prediction method for corrosion degradation affect the posterior probability distribution of the ultimate strength of the plate.

If you did not manage to obtain a copy of this paper: Request a copy of this article

For information about all CENTEC publications you can download: Download the Complete List of CENTEC Publications