The rapid and nondestructive detection of tea leaf moisture content (MC) is of great significance to processing tea with an automatic assembly line. This study proposes an MC detection method based on microwave scattering parameters (SPs). Through the established free-space electromagnetic measurement device, 901 different frequency points are taken between 2.45 and 6 GHz using a vector network analyzer (VNA). The SPs of tea leaves with different moisture contents (5.72–55.26%) at different bulk density and different sample thicknesses were measured. The relationship between frequency, S₂₁ amplitude and moisture content, thickness, and bulk density of tea was analyzed using correlation coefficients, significance analysis, and model construction. Back propagation (BP) neural network, decision tree (DT), and random forest (RF) MC prediction models were established with the frequency, amplitude, and phase of the SPs, thickness, and bulk density of the samples as inputs. The results showed that the RF-based model had the best performance, with determination coefficient (R²) = 0.998, mean absolute error (MAE) = 0.242, and root mean square error (RMSE) = 0.614. Compared to other nondestructive testing processes for tea, this method is simpler and more accurate. This study provides a new method for the detection of tea MC, which may have potential applications in tea processing.

The detection of the moisture content of wheat is an important index used to measure the quality and preservation of wheat. In order to rapidly and non-destructively detect the moisture content of wheat, in this study, we designed a stripline detection device that measures 151 frequency points in the 50–200 MHz frequency range with a vector network analyzer. Random forest (RF), extreme learning machine (ELM), and BP neural network prediction models were established, using the frequency, temperature, volume density and dielectric constant as input and the water content as output. It was shown that, in the frequency range 50–200 MHz, the permittivity of wheat decreases as the frequency increases, and that this is negatively correlated. The dielectric constant of wheat increases as the moisture content, temperature, and bulk density increase, and these are positively correlated. The random forest (RF) prediction model, which uses the frequency, temperature, effective dielectric constant ${\epsilon }_{eff}$. and volume density as inputs and the wheat moisture content as the output, demonstrates the best performance. The determination coefficient (R²) = 0.99977, the mean absolute error (MAE) = 0.044368, the mean square error (MAE) = 0.0053011, and the root mean square error (RMSE) = 0.072809. This study provides a new device and method for the detection of the moisture content of wheat. The device is small and is not easily disturbed by the external environment. It can be measured in a variety of conditions and is important for the development of low-cost, high-precision, and portable devices for the detection of the moisture content of wheat.

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 °C to 20 °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.

The growth status of winter wheat seedlings during the greening period is called the seedling situation. Timely and accurate determinations of the seedling situation type are important for subsequent field management measures and yield estimation. To solve the problems of low-efficiency artificial classification, subjective doping, inaccurate classification, and overfitting in transfer learning in classifying the seedling condition of winter wheat seedlings during the greening period, we propose an improved ConvNeXt winter wheat seedling status classification and identification network based on the pre-training–fine-tuning model addressing over-fitting in transfer learning. Based on ConvNeXt, a SETFL-ConvNeXt network (Squeeze and Excitation attention-tanh ConvNeXt using focal loss), a winter wheat seedling identification and grading network was designed by adding an improved SET attention module (Squeeze and Excitation attention-tanh) and replacing the Focal Loss function. The accuracy of the SETFL-ConvNeXt reached 96.68%. Compared with the classic ConvNeXt model, the accuracy of the Strong class, First class, and Third class increased by 1.188%, 2.199%, and 0.132%, respectively. With the model, we also compared the effects of different optimization strategies, five pre-training-fine-tuning models, and the degree of change in the pre-trained model. The accuracy of the fine-tuning models trained in the remaining layers increased by 0.19–6.19% using the last three frozen blocks, and the accuracy of the pre-trained model increased by 3.1–8.56% with the least degree of change method compared with the other methods. The SETFL-ConvNeXt network proposed in this study has high accuracy and can effectively address overfitting, providing theoretical and technical support for classifying winter wheat seedlings during the greening period. It also provides solutions and ideas for researchers who encounter overfitting.

Residues in the grain tank of seed-production wheat harvesters often cause varietal admixture, challenging seed purity maintenance above 99%. To address this, an intelligent cleaning system was developed for automatic residue recognition and removal. The system utilizes an RGB-D camera and an embedded AI unit paired with an improved lightweight object detection model. This model, enhanced for feature extraction and compressed via LAMP, was successfully deployed on a Jetson Nano, achieving 92.5% detection accuracy and 13.37 FPS for real-time 3D localization of impurities. A D–H kinematic model was established for the 4-DOF cleaning manipulator. By integrating the PSO and FWA models, the motion trajectory was optimized for time-optimality, reducing movement time from 9 s to 5.96 s. Furthermore, a gas–solid coupled simulation verified the separation capability of the cyclone-type dust extraction unit, which prevents motor damage and centralizes residue collection. Field tests confirmed the system’s comprehensive functionality, achieving an average cleaning rate of 92.6%. The proposed system successfully enables autonomous residue cleanup, effectively minimizing the risk of variety mixing and significantly improving the harvest purity and operational reliability of seed-production wheat. It presents a novel technological path for efficient seed production under the paradigm of smart agriculture.

To address the issues of corn harvester field operations relying on driver visual guidance for row alignment, high labor intensity, and unstable operation accuracy, this study innovatively proposes a “vision-dominant, gateway-enhanced” dual-mode collaborative row-alignment assistance architecture, and independently develops the R²DC-Mask R-CNN instance segmentation network and MCC-KF robust filtering algorithm to form a deeply coupled hardware–software-assisted driving system. The R²DC-Mask R-CNN network is autonomously designed for corn row-detection scenarios, achieving accurate perception in complex field environments; the MCC-KF algorithm innovatively solves the state estimation divergence problem during transient vision failures through a multi-criteria constraint mechanism, ensuring continuous navigation capability; the intelligent gateway and vision system form a confidence-driven master–slave switching mechanism that adaptively enhances system robustness when vision is restricted. Field experiments demonstrate that within the speed range of 0.5–5.0 km/h, the average lateral deviation in the row alignment assisted by the system is 3.82–5.30 cm, the proportion of deviations less than 10 cm exceeds 96%, and all sample deviations remain within 20 cm; at a speed of 3.5 km/h, the system reduces the average grain loss rate from 3.76% under manual operation to 2.65%, a decrease of 29.5%. This system effectively improves row alignment accuracy and harvest quality, providing a practical human–machine collaborative solution for intelligent harvester operations.