Abstract This study employs an artificial intelligence symbolic regression method to analyze the sucrose hydrolysis experimental data,reproducing a kinetics equation consistent with chemical principles and optimizing the rate constant evaluation.For the symbolic regression analysis of sucrose hydrolysis polarimetry data,this study proposes:when the accurate value of α∞ is known,the transformed data ln(αt-α∞) should be used;when α∞ is unknown or difficult to measure,exponential regression should be performed on the polarimetry data αt.Through comparative validation with traditional fitting methods,this study confirms the effectiveness of this AI-driven data processing approach and analyzes its advantages and limitations in practical applications.
