Sorghum is an important grain crop in many countries worldwide, yet it often suffers from high levels of fragmentation during harvest due to varying maturity. To this end, a study was conducted to investigate the crushing characteristics of sorghum grains subjected to compression and impact loading at different moisture contents. By configuring sorghum kernels with varying ranges of water and determining their physical parameters, such as length, width, etc., the geometric mean diameter of sorghum kernels was 3.105–3.550 mm, and the sphericity was above 75%. Compression tests were conducted on sorghum kernels in the triaxial direction. The compression energy was calculated to be 13.409–19.229 J on the X-axis, 16.313–21.409 J on the Y-axis, and 17.609–24.741 J on the Z-axis. In contrast, the apparent contact modulus of elasticity was calculated, with the maximum modulus of elasticity up to 72 MPa in the Z-axis direction, and the variations in the X-axis and Y-axis were approximate. Finally, mechanical impact tests were conducted to measure the critical angle of seed breakage, and a mathematical model was established to predict the impact of mechanical breakage force. The error between the predicted and experimental values was within 3%. This paper conducted compression and impact mechanics tests on sorghum seeds at different moisture contents to provide a design basis for sorghum harvesting and processing and other harvesting equipment.

In the foxtail millet field, due to the dense distribution of the foxtail millet ears, morphological differences among foxtail millet ears, severe shading of stems and leaves, and complex background, it is difficult to identify the foxtail millet ears. To solve these practical problems, this study proposes a lightweight foxtail millet ear detection method based on improved YOLOv5. The improved model proposes to use the GhostNet module to optimize the model structure of the original YOLOv5, which can reduce the model parameters and the amount of calculation. This study adopts an approach that incorporates the Coordinate Attention (CA) mechanism into the model structure and adjusts the loss function to the Efficient Intersection over Union (EIOU) loss function. Experimental results show that these methods can effectively improve the detection effect of occlusion and small-sized foxtail millet ears. The recall, precision, F₁ score, and mean Average Precision (mAP) of the improved model were 97.70%, 93.80%, 95.81%, and 96.60%, respectively, the average detection time per image was 0.0181 s, and the model size was 8.12 MB. Comparing the improved model in this study with three lightweight object detection algorithms: YOLOv3_tiny, YOLOv5-Mobilenetv3small, and YOLOv5-Shufflenetv2, the improved model in this study shows better detection performance. It provides technical support to achieve rapid and accurate identification of multiple foxtail millet ear targets in complex environments in the field, which is important for improving foxtail millet ear yield and thus achieving intelligent detection of foxtail millet.

To determine the patterns and influencing factors of the mechanical properties of millet stems from different varieties during the maturity period, this study employed a complete block experiment method and conducted shearing and bending tests on millet stems using the INSTRON5544 electronic universal material testing machine. The research investigated the variation in the shear strength, specific shear energy, bending strength, elastic modulus, and bending stiffness at different internode positions of the stems of Changza 466, Zhangza 16, and Jingu 21 during their maturity period. The results indicated that the variety had a significant impact on the mechanical properties of millet stems: from largest to smallest, the order of shear and bending forces was Jingu 21, Zhangza 16, and Changza 466. The shear strength and bending strength of Jingu 21 were the greatest among the three stem samples. The internode position significantly affected the shear mechanical properties of the millet stems, showing a general trend of decreasing shear strength with ascending internode position. The effect of the internode position on the bending stiffness was highly significant, whereas its impact on the bending strength and elastic modulus was not significant. The shear strength of the millet stems ranged from 3.866 ± 1.086 to 6.953 ± 2.208 MPa, significantly lower than the bending strength, which ranged from 18.934 ± 4.374 to 34.286 ± 6.875 MPa. The lowest shear strength and specific shearing energy, recorded at the fifth internode, were 4.028 ± 1.918 MPa and 15.097 ± 12.633 MJ/mm², respectively. Jingu 21 and Changza 466 exhibit better lodging resistance than Zhangza 16. It is recommended to use a cutting-type platform for harvesting millet stems, with the cutting height set at the fifth internode position. This study provides a theoretical basis for the design of millet harvesting machinery and the selection of harvest parameters.

To address the issue of header loss in millet combine harvesters, a double-chain millet harvester header was designed based on the principles of contact mechanics and tribology. Key component parameters of the header were determined, with the divider length and width measuring 0.56 m and 0.30 m, respectively. The divider angle was 40°, and the spiral angle was also 40°. A prototype was manufactured, and field performance tests were conducted. The results showed that the total header loss rate of the double-chain header was lower than that of the single-chain header under various combinations of header height and harvesting speed. The lowest total header loss rate, 3.12%, occurred when the header height was 0.2 m and the harvesting speed was 1.667 m/s, with a grain loss rate of 0.55% and a spike loss rate of 2.57%. This research provides a theoretical foundation for the development of low-loss, high-efficiency millet combine harvesters.

In order to solve the problems of high planting density, similar color, and serious occlusion between spikes in sorghum fields, such as difficult identification and detection of sorghum spikes, low accuracy and high false detection, and missed detection rates, this study proposes an improved sorghum spike detection method based on YOLOv8s. The method involves augmenting the information fusion capability of the YOLOv8 model’s neck module by integrating the Gold feature pyramid module. Additionally, the SPPF module is refined with the LSKA attention mechanism to heighten focus on critical features. To tackle class imbalance in sorghum detection and expedite model convergence, a loss function incorporating Focal-EIOU is employed. Consequently, the YOLOv8s-Gold-LSKA model, based on the Gold module and LSKA attention mechanism, is developed. Experimental results demonstrate that this improved method significantly enhances sorghum spike detection accuracy in natural field settings. The improved model achieved a precision of 90.72%, recall of 76.81%, mean average precision (mAP) of 85.86%, and an F1-score of 81.19%. Comparing the improved model of this study with the three target detection models of YOLOv5s, SSD, and YOLOv8, respectively, the improved model of this study has better detection performance. This advancement provides technical support for the rapid and accurate recognition of multiple sorghum spike targets in natural field backgrounds, thereby improving sorghum yield estimation accuracy. It also contributes to increased sorghum production and harvest, as well as the enhancement of intelligent harvesting equipment for agricultural machinery.

As the millet ears are dense, small in size, and serious occlusion in the complex grain field scene, the target detection model suitable for this environment requires high computing power, and it is difficult to deploy the real-time detection of millet ears on mobile devices. A lightweight real-time detection method for millet ears is based on YOLOv5. First, the YOLOv5s model is improved by replacing the YOLOv5s backbone feature extraction network with the MobilenetV3 lightweight model to reduce model size. Then, using the multi-feature fusion detection structure, the micro-scale detection layer is augmented to reduce high-level feature maps and low-level feature maps. The Merge-NMS technique is used in post-processing for target information loss to reduce the influence of boundary blur on the detection effect and increase the detection accuracy of small and obstructed targets. Finally, the models reconstructed by different improved methods are trained and tested on the self-built millet ear data set. The AP value of the improved model in this study reaches 97.78%, F₁-score is 94.20%, and the model size is only 7.56 MB, which is 53.28% of the standard YoloV5s model size, and has a better detection speed. Compared with other classical target detection models, it shows strong robustness and generalization ability. The lightweight model performs better in the detection of pictures and videos in the Jetson Nano. The results show that the improved lightweight YOLOv5 millet detection model in this study can overcome the influence of complex environments, and significantly improve the detection effect of millet under dense distribution and occlusion conditions. The millet detection model is deployed on the Jetson Nano, and the millet detection system is implemented based on the PyQt5 framework. The detection accuracy and detection speed of the millet detection system can meet the actual needs of intelligent agricultural machinery equipment and has a good application prospect.