Abstract: To address the inefficiency and complexity of traditional chemical methods for measuring the acidity of Huangshui (HS), this study proposed a rapid and non-destructive detection approach using near-infrared (NIR) spectroscopy combined with partial least squares regression (PLSR). The raw spectra were preprocessed by Savitzky-Golay convolution smoothing to reduce noise interference. To simplify the model and enhance the predictive performance, a hybrid feature selection strategy integrating spectral band selection and wavelength optimization was developed. First, interval partial least squares (iPLS), synergy interval partial least squares (SiPLS), and backward interval partial least squares (BiPLS) were employed to preliminarily identify characteristic bands related to acidity. Subsequently, a multi-objective optimization framework was introduced, incorporating an improved non-dominated sorting genetic algorithm III (iNSGA-III) with chaotic initialization and adaptive mutation operators for secondary wavelength refinement. Results demonstrated that the PLSR model based on 70 optimal wavelengths selected by iPLS combined with iNSGA-III had the best predictive performance with higher coefficient of determination of prediction (R2p) and lower root mean square error of prediction (RMSEP) of 0.930 9 and 0.439 4 mmol/100 g compared to 0.757 6 and 0.825 0 mmol/100 g for the full spectral model, respectively. This study provides a theoretical foundation for rapid, non-destructive monitoring of HS acidity during baijiu fermentation.

Key words: Huangshui, acidity, near-infrared spectroscopy, feature selection, partial least squares regression, non-dominated sorting genetic algorithm