Deeppipe: a customized generative model for estimations of liquid pipeline leakage parameters. (June 2021)

• Record Type: Journal Article
• Authors: Zheng, Jianqin; Liang, Yongtu; Xu, Ning; Wang, Bohong; Zheng, Taicheng; Li, Zhengbing; Liao, Qi; Zhang, Haoran
• Is Part Of: Computers & chemical engineering. Volume 149(2021)
• Publication Date: 2021-06
• Subjects: GANs framework -- Pipeline leakage parameters -- Estimations -- neural network -- Sensitivity analysis; Chemical engineering -- Data processing -- Periodicals; 660.0285
• DOI: 10.1016/j.compchemeng.2021.107290
• Languages: English
• ISSNs: 0098-1354

Abstract

Highlights: A GANs framework is proposed for estimations of pipeline leakage parameters. The architecture of this proposed GANs framework is analyzed in detail. The sensitivity analysis for the proposed GANs framework is evaluated. Two pipeline leakages are studied to show the effectiveness of this work. Abstract: Considering the tremendous economic losses and human injury caused by pipeline leaks, it is critical to detect and locate the pipeline leakage in time. This work proposes a generative adversarial networks (GANs) framework for leak detection and localization from the perspective of data science instead of physical meaning. The GANs are designed by two powerful neural networks: generative (G) network and discriminative (D) network. Real experiments are performed to verify the effectiveness of the proposed GANs framework, confirming that it can be applied to pipeline leakages for the estimations of the location, coefficient, and the starting time. To qualify the performance of the approach, sensitivity analysis for the structure of the GANs framework is evaluated. Finally, the proposed generative model is validated by two pipeline leakages. The errors of these two examples are 3.9% and 3.5%, respectively, indicating that the proposed method is better than the improved PSO and ANN.