Machine Learning for Subsea Pipeline Reeling Mechanics

Abstract

Installation of subsea pipelines using reeling process is an attractive method. The pipeline is welded in long segments, typically several kilometers in length, and reeled onto a large diameter drum. The pipeline is then transported onto such reel to the offshore site where it is unreeled and lowered on the seabed. The deformation imposed on the pipeline while spooled onto the drum needs to be controlled so that local buckling is avoided. Mitigation of such failure is generally provided by proper pipeline design & reeling operation parameters. Buckling stems from excessive strain concentration near the circumferential weld area resulting from strength discontinuity at pipeline joints, mainly depending on steel wall thickness and yield strength. This requires the characterization of critical mismatches obtained by trial and error. Such method is a long process since each “trial” requires a complete Finite Element Analysis run. Such simulations are complex and lengthy. Occasionally, this can drive the selection of the pipeline minimum wall thickness, which is a key parameter for progressing the project. The timeframe of such method is therefore not compatible with such a key decision. The paper discusses the use of approximation models to capitalize on the data and alleviate the design cost. To do so, design of experiments and automation of the computational tool chain are implemented. It is demonstrated that initial complex chain of FEA computational process can be replaced using design space description and exploration techniques such as design of experiments combined with advanced statistical regression techniques in order to provide an approximation model. This paper presents the implementation of such methodology and the results are discussed.