Research on Pitting Depth Prediction Model of 316L Instrument Tube in Oil-Bearing Marine Environment

Abstract

In order to improve the prediction accuracy of pitting depth of 316L stainless steel instrument pipe in oily marine atmosphere， a direct discrete grey pitting depth prediction model (SCPSO-DDGM (1，1， λ)) based on improved particle swarm algorithm optimization was established.First， using pitting corrosion data from exposure experiments as an example， the DDGM (1， 1) model was established， and the model was dynamically improved by applying a new information-based variable weight weakening buffer operator and dimension-equivalent gray number supplementation.Then，a nonlinear variation inertia weight and sine-cosine learning factors were used to enhance the optimization ability and convergence speed of the Particle Swarm Optimization (PSO) algorithm， while a Gaussian perturbation strategy was introduced to improve PSO's ability to escape local optima.The SCPSO was then employed to optimize the weight parameter λ in the improved DDGM (1， 1，λ) model.Finally， simulation calculations were performed in MATLAB to analyze and compare the prediction results of the SCPSO-DDGM(1， 1， λ) model with those of the GM (1，1)，DDGM (1，1) and PSO-DDGM (1，1，λ) models.Results showed that during the time period of the study， the predicted depth of the optimized new model was highly consistent with the actual depth， and its performance was better than that of the comparison model.Overall， it was proved that the SCPSO-DDGM (1，1， λ) model can effectively predict the pitting depth of instrument tubes， which provides new ideas and methods for the corrosion research of instrument tubes.

Keywords

• oil-bearing marine atmospheric environment； 316l stainless steel instrument tube； pitting depth； improved particle swarm optimization (scpso)； ddgm (1，1， λ) model