Multiproduct Pipeline Leak Detection and Localization System Using Artificial Intelligence

Abstract

The modeling and simulation of a leak detection system with incidence localization for a multiproduct unidirectional flow pipeline is presented in this paper. The research work employs the pressure profile of the pipeline using artificial intelligence (AI) with pressure sensors situated at regular intervals (100 m) along the pipeline. A pipeline of total length 1500 m was modeled with pressure sensors placed along the pipeline. The pressure along the line was measured as a time series data which was then used to train an artificial neural network (ANN) in order to detect leaks. To localize leaks, disturbance (leak) of different sizes was created at intervals along the pipe, which yielded different pressure profiles from the normal operation. This provides the required data for the learning algorithm. In this work, the Darcy–Weisbach equation was used to model the leak detection and localization while the Bernoulli and Colebrook equations were modeled for laminar and turbulent flow, respectively. The model was developed and simulated in Simulink/MATLAB 2017a, and real-time pressure was then adopted to estimate the functionality of the developed (simulated) system. The result shows that different products (fluids) produce different pressure profiles. The developed algorithm is suitable for a multiproduct pipeline. The evaluation of the model shows that leaks can be accurately detected with an accuracy of 98.56%.