Summary In this study, an integrated machine learning (ML) model was proposed that allows to identify the risk of organic precipitation damage and estimate the asphaltene onset pressure (AOP). In addition, an estimation of the association parameters to estimate the AOP using a Cubic-Plus-Association (CPA) equation of state (EoS) using stochastics (Monte Carlo) and ML approach was carried out. To predict the asphaltene damage risk the asphaltene stability class index (ASCI) data and the in-situ live crude oil densities were used along with the support vector machines (SVM) method. To propose the AOP-ML model a dataset of 53 samples was considered, evaluating different ML methods. In both cases, 80 % of the dataset was used to train the model, whereas 20% was to validate it. In the Monte Carlo (MC) simulations, 6 fluids taken from literature were used. The ML classification model had a perfect accuracy (100 %), which was compared to conventional compositional asphaltene screening models, with a classification accuracy of 33% for the resin/asphaltene ratio, 29% for ASI, 67% for CII, and 88% for de Boer plot. The AOP-ML model described properly the 77% of the variation of the experimental AOP of the 6 fluids evaluated using a stepwise bidirectional linear regression with 9 input features. Finally, the MC results indicated that several combinations of association energies and volumes reproduce the experimental AOP, obtaining a linear model for estimating the cross-interaction energy with a coefficient of determination of 0.934. This study provides disruptive findings since it opens the possibility of formulating predictive EoS, obtaining the association parameters from a fluid's compositional and structural characteristics. This approach is an opportunity for a comprehensive understanding of asphaltene precipitation damage that allows to understand the mechanisms of formation damage and therefore look for promising solutions to restore the productivity of fields affected by asphaltene precipitation formation damage.
ECOPETROL S.A. has been working since 2006 in Pipeline Integrity Management Process. In that process, the threat related to climate and external forces play an important role, because of the vulnerability of ECOPETROL pipelines to this threat, not only by the geomorphology of Colombia, but also because of the strong impact of climate phenomenon such as “La Niña”, that consists in an unusual quantity of rain precipitation, represented in the increasing of slopes instability that affects the rights of way. Due to these events and the evolution of optical strain sensors monitoring technology, ECOPETROL has introduced an instrumentation pipeline program for monitoring the strain and advanced in the understanding of the behavior of pipelines. This paper describes the technology selected, the criteria used to select the monitoring sites and the thresholds stress/strain. The results of monitoring are discussed for a particular case.
The Colombian petroleum pipelines go through different types of geomorphologies and geological settings; so that the pipeline system is exposed to a variety of processes such as landslides, erosion, scour, sedimentation, and karstification. In order to prevent some of the effects caused by these processes, geotechnical remedial works have been designed and implemented over time. However, in some cases the remedial actions have not exhibited a proper behavior. For this reason, a better understanding of local conditions is required in order to conceive more effective solutions. This paper provides an overview of a methodological framework for geotechnical assessment and design of mitigation measures based on the evaluation of geological and geomorphological aspects, computational tools, and data processing. Finally, the characteristics of an existing and unsuccessful mitigation civil work are described, and a brief summary of the relevant geotechnical aspects of the proposed design are presented.
At the end of 2018, a large-scale landslide was identified near the Right of Way of one of the pipelines operated by Cenit Transporte y Logística de Hidrocarburos. In this zone it was possible to identify a populated area and a river. At the beginning the depth of the Landslide did not represent a hazard to the pipeline due to the Horizontal Directional Drilling technique applied when the pipeline was built. A monitoring program was developed through inclinometers and piezometers and In-Line Inspections were carried out to identify any disturbance in the alignment of the pipeline. From the monitoring program and In-Line Inspection data it was possible to confirm interaction between the landslide and the pipeline. A perpendicular force to the pipeline alignment produces a bending strain at two points, and landslide interact with the pipeline along a length of 170 m. The depth of the landslide failure surface was in between 17 to 22 m, and the pipeline was about 15 m deep. Due to this interaction, it was necessary to develop a risk assessment to identify a safe limit displacement. For a while, this allowed us to design both a temporal innovative solution considering a flexible pipeline and a definitive solution to build the new segment of the pipeline which was deeper than the last one, through the Horizontal Directional Drilling technique.
Since 2004, the Geotechnical Professional Team (EPGEO) from the Regional Association of Oil and Gas Companies in Latin America and the Caribbean (Asociación Regional de Empresas de Petróleo y Gas Natural en Latinoamérica y el Caribe, ARPEL) has been working on a knowledge management-related project for the Oil & Gas industry, consisting in the creation of three technical guides on Pipeline Integrity Management given the occurrence of geohazards in Hydrocarbon Transportation Systems. This initiative comprises the creation of 3 guides related to: i) Guide 1: Monitoring Geohazards for Pipeline Integrity, ii) Guide 2: Geotechnical Mitigation Works in Pipelines, iii) Guide 3: Geotechnical Risk in Pipelines. The EPGEO published Guide 1 in 2016 and made a presentation at the 2017 IPG (IPG2017-2538), while Guide 2 will be completed by 2021. Guide 3 will be created in 2021–2023. This document shows the methodology and contents for preparing the first two guides, focusing on Guide 2, which comprises different alternatives, analyses and technical solutions to the occurrence of geohazards that might affect the integrity of a pipeline transportation system.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.