Evaluating the performance of machine learning CFD-based and hybrid analytical models for transient flow prediction in temperature-compensated digital flow units

This investigation utilized binary-coded, parallel-connected on-off valves that can achieve high flow rates with fewer valves while addressing flow peak challenges. By considering temperature and refining modeling techniques, the study rectifies certain limitations observed in previous research, such as neglecting temperature, imprecise valve orifice flow coefficients, and absent flow pattern visualization, thereby enhancing flow prediction accuracy. The results for the ML_CFD-based model suggest that although extrapolation challenges exist in rarely data-driven systems, the proposed approach exhibits errors under 5 % across diverse metrics, attributable to the effectiveness of well-constrained overparameterized models and the segmented structure of digital flow control units. On the other hand, while the simplified Hybrid Analytical model shows minor deviations and offers easier implementation, it encounters constraints when processing data beyond its pre-tuned coefficient of discharge values.