Intelligent Monitoring of Polymer Drag Reduction in Turbulent Flow Using Fiber Bragg Grating Sensing and Deep Learning

Turbulent drag reduction (DR) using polymers is a critical technique for energy conserva-tion in fluid transport systems. Traditional monitoring methods relying on pressure transducers are intrusive and lack real-time turbulence characterization. This study pro-poses a novel non-intrusive intelligent monitoring system based on Fiber Bragg Grating (FBG) sensing and Artificial Intelligence (AI). An experimental setup was constructed to investigate the DR performance of polymer solutions. FBG sensors were utilized to capture the optical spectrum shift induced by turbulent flow fluctuations. A deep learning model was trained to correlate the optical signal features with the drag reduction rate. Results demonstrated that the AI model achieved high prediction accuracy (R² > 0.95), effectively replacing complex fluid dynamic calculations with optical signal analysis. This work provides a promising approach for real-time, non-intrusive monitoring of fluid flow characteristics in industrial applications.