Reconstruction of the solid–liquid two-phase flow field in the pipeline based on limited pipeline wall information

Pipeline hydraulic transportation is the primary method for transporting deep-sea mineral resources and fossil fuels. Pipeline blockage often causes excessive pressure in the pipeline, leading to pipeline breakage or even cargo leakage, which severely impacts transportation safety and can easily trigger secondary disasters. Therefore, clarifying the global flow field within pipelines, such as particle distribution, is crucial for monitoring and controlling pipeline systems. This study uses a limited number of easily measurable pipeline wall sensor pressure values as inputs of deep learning models for flow field reconstruction, with the global flow field of solid–liquid two-phase flow in the three-dimensional pipeline as the output. Three model frameworks from existing studies are summarized, and their reconstruction effects are compared. Based on this, a new framework is proposed. It expands the low-dimensional sensor pressure values to the same size as the global flow field using a pseudo-decoder and then processes them through an autoencoder. The results indicate that the new framework achieves further accuracy improvements compared to the previous three frameworks, with R2 and mean squared error reaching 0.933 and 5.13 ×10−4, respectively. Additionally, the effects of the skip connection configuration of the model, dataset size, and model learning rate, as well as the number and arrangement of pressure sensors on reconstruction accuracy, are investigated. Finally, the transferability of the model is demonstrated by reconstructing the pressure and fluid velocity fields of the pipeline two-phase flow.