Comparative Kinetic Modeling of Ayran Fermentation with Functional Additives

The present study aimed to develop and evaluate a predictive approach for modeling pH dynamics during ayran fermentation using kinetic analysis, multivariate statistics, and IoT-based monitoring. Ayran is a low-viscosity fermented dairy beverage characterized by rapid acidification and high sensitivity to formulation and processing parameters, which limits the effectiveness of conventional endpoint pH control. The effects of two types of functional additives were investigated at empirically selected concentration ranges: a multifunctional dry fortifier (1–3%, w/w) and a vitamin–mineral syrup (2–4%, w/w). The data were analyed within a grouped comparative exploratory framework; the primary objective was comparative kinetic modeling of the fermentation process and prediction of the technological pH endpoint rather than evaluation of strict dose–response relationships. Fermentation was conducted at 41.0 ± 0.5 °C until the target pH range of 4.30 ± 0.05 was reached. An IoT monitoring architecture was used to generate a structured time-series dataset consisting of 909 sequential time-series measurements obtained during nine fermentation experiments. The formulation-associated kinetic behavior was evaluated using ANOVA, Tukey’s test, correlation analysis, and principal component analysis (PCA). The additives significantly affected the final pH and fermentation duration (p < 0.05; η2 > 0.90). The application of additives reduced fermentation time by 1.6–1.8 h compared with the control. The first principal component explained 96.4% of the total variance, confirming that pH can serve as a sufficient proxy indicator for monitoring the overall fermentation system. A comparative analysis of four kinetic models (Gompertz, logistic, logarithmic, and linear) was performed over the full fermentation range (t = 0–10 h). The Gompertz model demonstrated the highest predictive accuracy (R2 = 0.994–0.996; MAE = 0.027–0.033 pH units), whereas the logarithmic model was inadequate for describing the sigmoidal acidification profile of ayran (R2 = 0.685–0.703). Numerical solution of the inverse problem enabled prediction of the time required to reach pH ≤ 4.35 in experimental groups with an accuracy of 0.90–1.93 h, providing a preliminary early warning signal suitable for operator decision support. For the control group, the asymptotic behavior of the Gompertz model during the stabilization stage limited the applicability of numerical prediction, indicating the necessity of direct pH sensor monitoring for this formulation. The proposed approach may serve as an exploratory basis for further development of predictive monitoring frameworks for fermented dairy production.