A Physics-Informed Neural Network for Unified Multi-Regime Pressure-Drop Representation of Inflow Control Devices in Reservoir–Wellbore Coupled Simulation

Accurate representation of the pressure drop–flow rate (Δp–q) relationship of nozzle-type inflow control devices (ICDs) is critical for reliable reservoir–wellbore coupled simulation. Conventional ICD models in reservoir simulators rely primarily on empirical correlations or tabulated data, but commonly used formulations cannot consistently capture the linear behavior in the low-flow regime or the transition between flow regimes, which may reduce physical fidelity and numerical robustness. To overcome this limitation, this study proposes a unified characteristic-curve representation that integrates linear, transitional, and quadratic flow regimes into a single continuous and differentiable function through a physically constrained least-squares formulation, and further develops a physics-informed neural network (PINN) to learn the ICD pressure–flow relationship while enforcing physical consistency. The trained PINN model is embedded into a multi-segment well model within a reservoir–wellbore coupled simulation framework and evaluated using a mechanistic reservoir model containing permeability streaks with varying permeabilities. The results show that the proposed method improves numerical convergence and accurately reproduces ICD pressure–flow behavior across multiple flow regimes, providing a more physically consistent and robust representation of ICD performance for inflow control analysis and reservoir simulation.