Damage identification for jacket offshore platforms using Transformer neural networks and random decrement technique

Abstract

A deep learning method is proposed to identify damages in jacket offshore platforms, which integrates the random decrement technique (RDT) and Transformer neural network. RDT is utilized to process the noisy strain response signals from various measurement points on the platform under random excitation, and the Transformer network is used to localize the damages and assess their severities. Numerical simulations and experimental studies are used to demonstrate that the proposed method is effective. The numerical model applied in this study is a jacket platform, including single and multiple damage cases in the entire section and partial section (two-fifths of the entire section) with minor severities (<5%), and different noise levels are considered. Additionally, the effect of measurement positions on identification accuracy of minor and major damage is discussed. Furthermore, the proposed method is validated by experimental studies using a jacket platform model fixed on a shaking table, where different severities of single and multiple damages are considered. Results of the numerical and experimental studies demonstrate that the proposed RDT-Transformer approach can accurately determine the location of structural damage and identify its severity.