Leak Detection for Natural Gas Gathering Pipelines Under Multiple Operating Conditions Using RP-1dConvLSTM-AE and Multimodel Decision

Real-time leak detection for natural gas gathering pipelines is critical to guarantee the safe transportation of energy in the source of production. Since leak samples are scarce in real pipelines, modeling healthy data becomes one of the mainstream solutions. However, due to the lack of prior knowledge of leaks, more effective feature learning for multivariate time series (MTS) of pipeline data is a prerequisite for reliable leak detection. Moreover, in-service gathering pipelines usually involve multiple operating conditions (MOCs), where the leak characteristics of MOCs could be significantly different. This poses a serious challenge to accurate leak detection. To address the abovementioned problems, we propose a hybrid leak detection method for gathering pipelines under MOCs. First, anomaly processing and long–short sequence construction are designed to provide high-quality data for leak detection. Then, reconstruction- and prediction-one-dimensional convolutional long short-term memory autoencoder is proposed to enhance the feature learning for MTS. Based on the learned features, a multimodel decision scheme with one-class support vector machine is developed to deal with leak detection under MOCs. Finally, experimental results on supervisory control and data acquisition data obtained from real-world natural gas gathering pipelines demonstrate the effectiveness of the proposed method.