Deep-sea mineral resource transportation predominantly utilizes hydraulic pipeline methodology.Environmental factors induce vibrations in flexible pipelines,thereby affecting the internal flow characteristics.Therefor...Deep-sea mineral resource transportation predominantly utilizes hydraulic pipeline methodology.Environmental factors induce vibrations in flexible pipelines,thereby affecting the internal flow characteristics.Therefore,real-time monitoring of solid–liquid two-phase flow in pipelines is crucial for system maintenance.This study develops an autoencoder-based deep learning framework to reconstruct three-dimensional solid–liquid two-phase flow within flexible vibrating pipelines utilizing sparse wall information from sensors.Within this framework,separate X-model and F-model with distinct hidden-layer structures are established to reconstruct the coordinates and flow field information on the computational domain grid of the pipeline under traveling wave vibration.Following hyperparameter optimization,the models achieved high reconstruction accuracy,demonstrating R^(2)values of 0.990 and 0.945,respectively.The models’robustness is evaluated across three aspects:vibration parameters,physical fields,and vibration modes,demonstrating good reconstruction performance.Results concerning sensors show that 20 sensors(0.06%of total grids)achieve a balance between accuracy and cost,with superior accuracy obtained when arranged along the full length of the pipe compared to a dense arrangement at the front end.The models exhibited a signal-to-noise ratio tolerance of approximately 27 dB,with reconstruction accuracy being more affected by sensor failures at both ends of the pipeline.展开更多
基金financial support by the National Natural Science Foundation of China (Nos.52471293 and 12372270)the National Youth Science Foundation of China (Nos.52101322 and 52108375)+3 种基金the Program for Intergovernmental International S&T Cooperation Projects of Shanghai Municipality, China (Nos.24510711100 and 22160710200)The Oceanic Interdisciplinary Program of Shanghai Jiao Tong University (No.SL2022PT101)funded by the Open Fund of the State Key Laboratory of Coastal and Offshore Engineering of Dalian University of Technology (No.LP2415)National Key R&D Program of China (No.2023YFC2811600)
文摘Deep-sea mineral resource transportation predominantly utilizes hydraulic pipeline methodology.Environmental factors induce vibrations in flexible pipelines,thereby affecting the internal flow characteristics.Therefore,real-time monitoring of solid–liquid two-phase flow in pipelines is crucial for system maintenance.This study develops an autoencoder-based deep learning framework to reconstruct three-dimensional solid–liquid two-phase flow within flexible vibrating pipelines utilizing sparse wall information from sensors.Within this framework,separate X-model and F-model with distinct hidden-layer structures are established to reconstruct the coordinates and flow field information on the computational domain grid of the pipeline under traveling wave vibration.Following hyperparameter optimization,the models achieved high reconstruction accuracy,demonstrating R^(2)values of 0.990 and 0.945,respectively.The models’robustness is evaluated across three aspects:vibration parameters,physical fields,and vibration modes,demonstrating good reconstruction performance.Results concerning sensors show that 20 sensors(0.06%of total grids)achieve a balance between accuracy and cost,with superior accuracy obtained when arranged along the full length of the pipe compared to a dense arrangement at the front end.The models exhibited a signal-to-noise ratio tolerance of approximately 27 dB,with reconstruction accuracy being more affected by sensor failures at both ends of the pipeline.
