Mechanistic and Machine Learning Modeling of Microwave Heating Process in Domestic Ovens: A Review

Area of Science:

• Food science and technology
• Electromagnetics and microwave engineering
• Computational modeling and simulation

Background:

• Domestic microwave ovens offer rapid and efficient food heating.
• Non-uniform microwave heating is a significant drawback, impacting food safety and quality.
• Accurate modeling is crucial for understanding and mitigating uneven heating.

Purpose of the Study:

• To extensively review mechanistic models for simulating microwave heating processes in domestic ovens.
• To discuss model implementation, validation, and strategies for enhancing accuracy and efficiency.
• To explore the integration of machine learning with mechanistic models and the use of pure machine learning models.

Main Methods:

• Review of mechanistic models incorporating diverse geometric dimensions and physical/kinetic parameters.
• Discussion of model implementation and validation techniques.
• Analysis of hybrid models combining mechanistic approaches with machine learning, and pure machine learning models.

Main Results:

• Mechanistic models provide insights into microwave-food interactions for improved heating uniformity.
• Machine learning integration offers potential for enhanced microwave heating performance.
• Both hybrid and pure machine learning models show promise, depending on data availability and complexity.

Conclusions:

• Modeling plays a vital role in addressing non-uniform microwave heating issues.
• Hybrid and machine learning models represent a promising advancement in microwave heating technology.
• Further research is essential to improve model accuracy, efficiency, and user-friendliness for industrial applications.