Predicting gas flow rates of wellhead chokes based on a cascade forwards neural network with a historically limited penetrable visibility graph

This study presents a novel hybrid model that combines the cascade forward neural network (CFNN) with a historical limited penetrable visibility graph (HLPVG) for accurate prediction of gas flow rates through wellhead chokes in shale gas production. The model addresses the challenges of complex, nonlinear relationships between multiple variables affecting gas flow, including liquid-gas ratio (LGR), upstream pressure, temperature, and choke bean size. Using 11,572 field production samples from shale gas fields in the southern Sichuan Basin, the CFNN-HLPVG model demonstrates superior predictive performance compared to the conventional methods. The HLPVG algorithm transforms time series data into a graph structure, enabling the extraction of rich temporal and topological features, whereas the CFNN captures the complex interactions between variables. The model achieves a mean absolute relative error (MARE) of 0.014, significantly outperforming traditional approaches, including the Gilbert-type correlation, support vector machine, and other neural network architectures. Sobol sensitivity analysis revealed that choke bean size has the greatest impact on gas flow prediction (37.7% first-order sensitivity), followed by upstream pressure (19.3%) and temperature (11.6%), whereas LGR has a minimal influence (0.6%). The model performs particularly well under normal operating conditions but shows decreased accuracy in extreme environments with high temperature and pressure. This research provides a novel approach to gas flow prediction in wellhead chokes, offering valuable insights for optimizing shale gas production operations while highlighting areas for future improvement in handling extreme conditions and multisource data integration.