Print Email Facebook Twitter Towards deep probabilistic graph neural network for natural gas leak detection and localization without labeled anomaly data Title Towards deep probabilistic graph neural network for natural gas leak detection and localization without labeled anomaly data Author Zhang, Xinqi (China University of Petroleum (East China)) Shi, Jihao (China University of Petroleum (East China); The Hong Kong Polytechnic University) Huang, Xinyan (The Hong Kong Polytechnic University) Xiao, Fu (The Hong Kong Polytechnic University) Yang, M. (TU Delft Safety and Security Science) Huang, Jiawei (China University of Petroleum (East China)) Yin, Xiaokang (The Hong Kong Polytechnic University) Sohail Usmani, Asif (The Hong Kong Polytechnic University) Chen, Guoming (China University of Petroleum (East China)) Date 2023 Abstract Deep learning has been widely applied to automated leakage detection and location of natural gas pipe networks. Prevalent deep learning approaches do not consider the spatial dependency of sensors, which limits leakage detection performance. Graph deep learning is a promising alternative to prevailing approaches as it can model spatial dependency. However, the challenge of collecting real-world anomaly data for training limits the accuracy and robustness of currently used graph deep learning approaches. This study proposes a deep probabilistic graph neural network in which attention-based graph neural network is built to model spatial sensor dependency. Variational Bayesian inference is integrated to model the posterior distribution of sensor dependency so that the leakage can be localized. An urban natural gas pipe network experiment is employed to construct the benchmark dataset, in which normal time-series data is applied to develop our proposed model while anomaly leakage data is used for performance comparison between our model and other state-of-the-art models. The results demonstrate that our model exhibits competitive detection accuracy (AUC) = 0.9484, while the additional uncertainty interval provides more comprehensive leakage detection information compared to state-of-the-art deep learning models. In addition, our model's posterior distribution enhances the leakage localization with the accuracy of positioning (PAc) = 0.8, which is higher than that of other state-of-the-art graph deep learning models. This study provides a comprehensive and robust alternative for subsequent decision-making to mitigate natural gas leakage from pipe networks. Subject Digital twinGraph deep learningLeakage detectionLeakage localizationVariation Bayesian Inference To reference this document use: http://resolver.tudelft.nl/uuid:88161c48-f59a-481c-ba61-4ab5ef2d9474 DOI https://doi.org/10.1016/j.eswa.2023.120542 Embargo date 2023-11-30 ISSN 0957-4174 Source Expert Systems with Applications, 231 Bibliographical note Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. Part of collection Institutional Repository Document type journal article Rights © 2023 Xinqi Zhang, Jihao Shi, Xinyan Huang, Fu Xiao, M. Yang, Jiawei Huang, Xiaokang Yin, Asif Sohail Usmani, Guoming Chen Files PDF 1_s2.0_S0957417423010448_main.pdf 4.37 MB Close viewer /islandora/object/uuid:88161c48-f59a-481c-ba61-4ab5ef2d9474/datastream/OBJ/view