Big Data Infrastructure for the Pipeline Integrity Assessment Process in the Oil Industry

Abstract

Oil is an essential material in the daily life. Society and economy are intimately linked to the fossil fuel. Nonetheless, in order to use the oil, it needs to be previously processed and transformed into oil derivatives, such as gasoline, kerosene, oils, gas, among others. For which the crude oil has to be transported form the wells to the different processing stations. Oil is transported by several methods, however, pipelines are the most common method used worldwide due to its reliability and effectiveness. Regardless pipeline systems are considered safe, they are not flawless and might fail, promoting economic loses, environmental damages and human loss. In order to prevent these failures, oil industry is continuously investing resources and efforts in the development of Risk Assessment Algorithms to prevent them. These Algorithms usually are based on data related to the pipeline systems to shed some light creating projections and estimations towards the future. Some of these efforts are carried to the development and research risk models, nonetheless, the industry is focusing on new computer technologies to obtain the greater outcome from the data. Big Data is a computational tool set which is creating paths in science where there were none. This is the reason why this project has the purpose of integrate Big Data elements and apply them into the oil industry's Risk Assessments in order to optimize decision making process through structuration an intelligent data exploitation.