The meat food manufacturing industry faces significant challenges in optimizing food processing efficiency, particularly during the drying stage, which is critical for preserving product quality, safety, and overall production efficiency. Drying time varies depending on factors such as meat type, environmental conditions, and desired product characteristics, making the process complex and difficult to predict using traditional methods. Conventional approaches, which often rely on empirical rules or manual observations, are time-consuming and prone to human error. This paper proposes an AI-driven solution by leveraging machine learning algorithms to predict the drying time of meat products. Specifically, the study applies Random Forest, Decision Tree, Stacking Regressor, and Voting Regressor to predict the 'Drying Hours' based on key input features, including moisture content, fat, temperature, humidity, exhaust fan speed, fan speed, and heating status. The paper further explores feature importance analysis and identifies correlations between various input factors and drying time. By developing an accurate predictive model, this research aims to optimize production planning, reduce resource waste, and enhance overall operational efficiency in meat food manufacturing.

Keywords: AI-driven, Meat Food Drying, Drying Time Prediction, Machine Learning, Random Forest, Decision Tree, Stacking Regressor, Voting Regressor, Food Processing Optimization, Feature Importance Analysis, Production Planning, Smart Manufacturing.