Rheological analysis in food processing: factors, applications, and future outlooks with machine learning integration

Abstract

Food rheology serves as a critical tool for characterizing the flow and deformation properties of food, which directly impact its texture, taste, stability, and overall quality. The complex production environments and rapidly evolving market demands necessitate the integration of rheology with machine learning (ML) to accurately and effectively characterize and optimize the rheological properties of food. This review, with a focus on machine learning, examines texture analysis, including both large deformation rheology measurements, and small deformation rheology. It summarizes the factors influencing food rheology, emphasizing the interactions between key food components that affect rheological properties and the rheological characteristics of complex food systems. Furthermore, this review explores the detailed applications of combining rheology and machine learning in the food industry, as well as the associated challenges and future outlooks. ML has demonstrated significant efficacy in predicting and analyzing food rheology, despite the challenges posed by large datasets and intricate production conditions. The integration of ML with food rheology facilitates the analysis of food flow and deformation, optimization of product formulations, monitoring of production processes, and execution of sensory analysis. While ML-based approaches to rheology have advanced considerably in the context of food processing and quality assurance, substantial potential for further development remains.