Current technologies and the applications of data analytics for crude oil leak detection in surface pipelines

Abstract

Pipeline pressure monitoring has been the traditional and most popular leak detection approach, however, the delays with leak detection and localization coupled with the large number of false alarms led to the development of other sensor-based detection technologies. The Real Time Transient Model (RTTM) currently has the best performance metric, but it requires collection and analysis of large data volume which, in turn, has an impact in the detection speed. Several data mining (DM) methods have been used for leak detection algorithm development with each having its own advantages and shortcomings. Mathematical modelling is used for the generation of simulation data and this data is used to train the leak detection and localization models. Mathematical models and simulation software have also been shown to provide comparable results with experimental data with very high levels of accuracy. While the ANN and SVM require a large training dataset for development of accurate models, mathematical modelling has been shown to be able to generate the required datasets to justify the application of data analytics for the development of model-based leak detection systems for petroleum pipelines. This paper presents a review of key leak detection strategies for oil and gas pipelines, with a specific focus on crude oil applications, and presents the opportunities for the use of data analytics tools and mathematical modelling for the development of a robust real time leak detection and localization system for surface pipelines. Several case studies are also presented.