Transferable Pipeline Rupture Detection Using Multiple Artificial Intelligence Classifiers During Transient Operations

Abstract

Abstract There are several challenges associated with existing pipeline rupture detection systems, including an inability to accurately detect during transient conditions (such as changes in pump operating points), an inability to easily transfer from one pipeline configuration to another, and relatively slow response times. To address these challenges, we employ multiple artificial intelligence (AI) classifiers that rely on pattern recognition instead of traditional operator-set thresholds. AI techniques, consisting of two-dimensional (2D) convolutional neural networks (CNN) and adaptive neuro fuzzy interface systems (ANFISs), are used to mimic processes performed by operators during a rupture event. This includes both visualization (using CNN) and rule-based decision making (using ANFIS). The system provides a level of reasoning to an operator through the use of rule-based AI. Pump station sensor data is nondimensionalized prior to AI processing, enabling pipeline configurations outside of the training dataset, independent of geometry, length, and medium. AI algorithms undergo testing and training using two data sets: laboratory-collected flow loop data that mimics transient pump-station operations and real operator data that include simulated ruptures using the real time transient model (RTTM). The multiple AI classifier results are fused together to provide higher reliability especially detecting ruptures from pipeline data not used in the training process.