Thermal Imaging for Defect Detection, Drying Dynamics, and Machine Learning-Based Mass Loading Estimation in Silicon Thin coating Production

Abstract

This study demonstrates thermal imaging as a non-destructive, real-time quality control method for detecting coating defects, analyzing mass loading, and understanding drying dynamics in silicon-based thin coatings. Thermal imaging identifies critical defects such as streaks, pinholes, and chatter marks through distinct thermal signatures, with streaks reducing surface temperature by up to 15 °C. It establishes strong correlations between surface temperature, mass loading, and coating thickness; for instance, a 100 μm wet film thickness shows a surface temperature of ~50 °C, corresponding to a mass loading of 2.4 mg cm⁻². Drying dynamics reveal that thicker coatings retain more solvent, prolong drying, and shrink significantly, with 100 μm wet-gap coatings shrinking by up to 60%. A Random Forest machine learning model predicts mass loading with high accuracy (±0.3 mg cm⁻²) using surface temperature data, highlighting the feasibility of thermal imaging-based quality estimation. While validated in a batch process, this approach is well-suited for integration into roll-to-roll production across diverse thin coating applications, such as batteries, solar cells, and functional films. Thermal imaging provides a robust pathway for real-time defect detection, drying optimization, and quality control, improving coating performance and production reliability.