21 July 2023 in IEEE Transactions on Industrial Electronics
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.
30 April 2024 in Computers in Industry
17 April 2023 in SPE Production & Operations
Summary: Timely detection of leak accidents plays an essential role in the safe operation and risk assessment of natural gas pipelines. However, the scarce leak data and complex operating conditions lead to small samples, data imbalance, and problems with confusing operating conditions. The reliance on leak data limits the recognition performance of the artificial intelligence classification method for leakage operating conditions. A leak detection method based on the unsupervised reconstruction of healthy flow data is established to address these problems. First, an unsupervised neural network is established to reconstruct healthy flow data from real natural gas pipelines. And a model update strategy based on active learning is designed to improve the model’s adaptability for time-varying pipelines. Next, a dynamic alarm threshold strategy that accounts for the knowledge of the experience and statistical characteristics of the data segments is suggested to prevent false alarms caused by ambiguous operating conditions. Finally, unlike most recent work that only considers simulated data or laboratory data, this paper conducts a leak case study on an actual natural gas pipeline in service to improve the robustness of the proposed method in the actual operating environment. The findings of this paper can be used as a reference to analyze pipeline behavior analysis based on pipeline flow trend characteristics and early alarm management.
14 May 2025 in IEEE Transactions on Automation Science and Engineering
In real-world industrial scenarios, fault detection faces the widely recognized challenge of data imbalance, which not only refers to the scarcity of fault data but also includes the imbalance in healthy data. This article is concerned with imbalanced open-set fault detection (IOSFD), a practical yet challenging scenario in industrial applications where multiple healthy operating conditions and multiple fault types are imbalanced. In this article, we propose a new contrastive conditional adversarial autoencoder for IOSFD. It constructs an end-to-end unified model based on multi-class known healthy and faulty data to address the reliance of traditional methods on fault samples, while optimizing with class-specific weighted forces to ensure equal attention to imbalanced known classes. Input and feature reconstruction conditioned on operating modes are utilized to learn a compact decision plane and achieve both unknown fault detection and known data classification. Significantly, we formulate the optimization objective of conditional reconstruction based on contrastive learning and introduce adversarial training to further enhance the model’s performance. The effectiveness of the proposed method is validated through real-world pipeline leak detection and Tennessee-Eastman multi-fault detection.
1 January 2026 in IEEE Transactions on Signal and Information Processing over Networks