Probabilistic models for corrosion in structural reliability assessment - Part 2: Models based on mechanics

In Part 1 of this paper it was shown that statistical models using pooled data are of poor quality with very wide variability. The present paper considers probabilistic corrosion modelling based on corrosion mechanics principles and notes the effect of environmental and other factors that should be included in model development. These include temperature, dissolved oxygen, salinity, calcium carbonate and pH, water velocity, and marine growth. A new multi-phase, nonlinear mean value model is proposed for the corrosion of mild- and low-alloy steels under "at-sea" immersion conditions. Comments are made about calibration of the model and the further research required for complete model development is discussed.