Parallelized element-by-element architecture for structural analysis of flexible pipes using finite macroelements.

• Autor(a) principal: Toni, Fernando Geremias
• Data de Publicação: 2018
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Biblioteca Digital de Teses e Dissertações da USP
• Texto Completo: http://www.teses.usp.br/teses/disponiveis/3/3152/tde-19092018-093832/
• topic: Arquiteturas paralelas; Finite element method; Flexible pipes; Método dos elementos finitos; Métodos numéricos; Numerical methods; Parallel architectures; Tubos flexíveis

Flexible pipes are used in the offshore oil production to transport fluid and gas from the sea bead to the floating stations, and vice versa. These pipes have several concentric layers, of different materials, geometries and structural functions, since they are exposed to adverse operating environments, subjected to high internal and external pressures, high axial stresses and a series of dynamic loads. The local analysis is an important stage of a flexible pipe design and it consists on determining the stresses and strains distributions along the layers of the pipe. Multipurpose finite element packages are commonly used in the local analysis of flexible pipes, but they possess many limitations due to its generic nature, varying from the absence of specific tools for model creation to heavy restrictions of the number of degrees-of-freedom to make computational processing feasible. At the Polytechnic School of the University of São Paulo, within a research line in progress, several finite macroelements were formulated specifically for structural analysis of flexible pipes, taking into account their particularities, such as geometric patterns and layers assemblage. However, the numerical tools that implement these elements present very high memory and processing consumptions, limiting its usage for large-scale models. Therefore, this work has been motivated by memory and processing limitations of finite element structural analysis of flexible pipes for offshore applications. In this context, the Element-by-Element method, which does not require the global stiffness matrix, was chosen for its potential in memory reduction and processing capabilities, given its scalability and ease of parallelization. After an extensive literature review on numerical methods regarding the EBE method, it was chosen the Element-by-Element Diagonal Preconditioned Conjugate Gradient Method (EBE-PCG) algorithm. Aiming higher computational performance, the finite macroelements formulated by (PROVASI, 2013) were converted to the C++ language, implemented and parallelized in a new analysis tool, named as PipeFEM. The diagonal preconditioned EBE-PCG algorithm was implemented and parallelized with OpenMP. The scalability of the PCG algorithm is directly influenced by the efficiency of the matrix-vector product, an operation that, in the element-by-element method, is computed in a local basis with the blocks that comprise the model, and that requires synchronization techniques when performed in parallel. Four different synchronization strategies were developed, being the one based on geometric- and mesh- based mappings the most efficient of them. Numerical experiments showed a reduction of almost 92% in the EBE-PCG solution time of the parallelized version in comparison to the sequential one. In order to compare the efficiency of PipeFEM with the well-established finite element package ANSYS, a simplified flexible pipe was modeled in both software. PipeFEM was approximately 82 times faster than ANSYS to solve the problem, spending 24.27 seconds against 33 minutes and 18 seconds. In addition to this, PipeFEM required much less memory, 61.8MB against 6.8GB in ANSYS. In comparison to the dense version of MacroFEM, a reduction of more than three orders of magnitude was achieved in memory consumption. Despite the low the rate of convergence presented by the diagonal preconditioner, the implementation is very efficient in computational terms. Therefore, the objectives of this work were fulfilled with the development and application of the EBE method, allowing a reduction of memory and simulation costs.