Establishing a Low-Temperature Maize Kernel Moisture Content Prediction Model Based on Dielectric Constant Measurement

Detecting the moisture content of stored maize kernels is critical for minimizing post-harvest losses. To measure the moisture content of maize kernels under low-temperature conditions, a small-strip transmission line device was employed to construct a non-destructive measurement platform. The dielectric constant of maize kernels with varying moisture content was measured at temperatures ranging from -15 degrees C to 20 degrees C and frequencies between 1 and 200 MHz. By using the dielectric constant, frequency, and temperature as input variables, along with volume density and scattering parameter characteristics, three moisture content prediction models-SPO-SVM, XGBoost, and GA-BP-were established. The results show that temperature significantly affects the dielectric constant of maize kernels, especially when the moisture levels exceed 22.4%. The prediction model significantly improves the prediction accuracy under low-temperature conditions after introducing the volume density feature. Furthermore, incorporating the multi-phase and amplitude characteristics of scattering parameters further improves the model's performance. This study verifies the mechanism and behavior of dielectric constant variations in maize kernels under low-temperature conditions. The proposed model effectively mitigates measurement errors caused by the icing of free water and is well suited for measuring maize moisture content under low-temperature conditions.