AI-ENABLED OPTIMIZATION IN BEVERAGE FORMULATION AND QUALITY CONTROL: INSIGHTS FROM CHEMICAL ENGINEERING

Abstract

Background: The integration of Artificial Intelligence (AI) in food and beverage production has introduced new opportunities for enhancing formulation accuracy and maintaining consistent quality. Within the realm of chemical engineering, AI presents a data-driven approach to optimize ingredient composition, streamline processing parameters, and elevate product outcomes.

Objectives: This study aims to examine how AI techniques can be used to optimize beverage formulation and improve quality control. Specifically, it investigates the relationships between AI-driven variables—such as ingredient ratios, processing parameters, and algorithm type—and outcomes like beverage quality, product consistency, and consumer satisfaction.

Methods: A quantitative research design was adopted using a structured, Likert-scale questionnaire administered to 273 industry professionals. The study followed the Research Onion framework, employing a positivist philosophy, deductive approach, and cross-sectional survey strategy. Data were analyzed using descriptive statistics, Cronbach’s Alpha, correlation analysis, and multiple regression.

Results: The questionnaire demonstrated excellent reliability (Cronbach’s Alpha = 0.91). Normality tests indicated non-normal data distribution, typical of Likert-scale responses. Correlation analysis revealed weak to moderate relationships among the studied variables. Regression results showed that the independent variables accounted for only a small proportion of the variance in beverage quality (R² = 0.013, p > 0.05), indicating limited predictive power in the current model.