The hopper is commonly utilized for storing and transporting agricultural materials. Predicting the discharge mass flow rate of the hopper accurately is crucial for achieving precise handling of these materials. To reveal the segregation law of material and the effect of segregation behavior on the mass flow rate during material discharging from a hopper, crushed corn was selected for the study. A segregation discharging test bench and a flow rate determination test bench were constructed to analyze the changes in particle size distribution, bulk density, segregation index, and mass flow rate of crushed corn during the hopper discharging process. Additionally, 14 models of crushed corn particles were constructed based on the three-dimensional dimensions of the crushed corn particles, and the discharge process of the crushed corn from the hopper was simulated using the discrete element method. The results indicate that during the discharging process, crushed corn in the hopper exhibits a noticeable segregation phenomenon. Specifically, the mass proportion of particles larger than 4 mm in the discharged material initially decreases and then increases. In contrast, the proportion of particles smaller than 2.5 mm increases and subsequently decreases. Smaller particles demonstrate interparticle percolation throughout the discharging process. The bulk density of the discharged material exhibited an initial increase followed by a decrease. It rose from 668.01 kg/m³ to a peak of 706.74 kg/m³ before falling to 597.66 kg/m³. Throughout the discharging process, the overall segregation index showed similar fluctuations, first increasing and then decreasing. This indicates that the average particle size of the material at the hopper outlet was dynamically changing, with a trend of decreasing and then increasing. When the overall segregation index reaches a peak value of 1.16, the mass proportion of particles with a particle size less than 2.5 mm in the discharged material is about 34%, and that of particles with a size greater than 4 mm is about 27%. Due to the influence of segregation, the overall mass flow rate of discharging also shows a trend of first increasing and then decreasing. Results from the discrete element simulation indicate that particles smaller than 1.25 mm exhibit significant activity in the upper section of the hopper, suggesting that these small particles experience percolation. As a result of percolation, small particles form a mass flow pattern, while larger particles form a funnel flow pattern. This percolation process causes the small particles to discharge from the hopper before the larger ones. Based on the law of segregation of crushed corn during discharging from the hopper, assuming that the discharging process consists of 3 segregation stages, as the beginning stage, the segregation stage, and the reverse segregation stage, a function of the overall segregation index as a function of discharging time was constructed. The function was utilized to adjust the particle size term in the Brown and Richards flow rate model. Subsequently, a flow rate model for hopper discharging was developed, taking into account the behavior of material segregation. Verification tests demonstrated that the modified flow rate model exhibits minimal error and effectively reflects changes in the mass flow rate during the discharging process. In practical engineering applications, the three assumed stages of segregation flow can serve as a foundation for predicting the real-time mass flow rate of segregation flow in a hopper. By using a calibration method, a mass flow rate model tailored to the specific scenario can be developed. The findings of this study will provide a theoretical basis for predicting the discharge process of agricultural granular materials that consist of irregular particles with significant size variations. Additionally, this research may offer valuable insights for the development of precision handling equipment for agricultural materials.

Chili flower target detection can serve as one of the most important steps during mechanical pollination in modern agriculture. It is of great significance to accurately detect chili flowers in natural environments. This study aims to propose a lightweight and efficient detection model (named YOLOv8n-Chili Flower) using the YOLOv8n architecture. Multiple modifications were also carried out to enhance the detection accuracy, sensitivity, and computational efficiency suitable for resource-constrained scenarios, such as mobile pollination robots. Firstly, an Efficient Multi-scale Lightweight Attention Mechanism Module (EMA) was introduced into the neck layer, in order to capture and recognize the multi-scale features of chili flowers. Specifically, the targets were also detected in complex natural environments, such as occlusion, varying lighting conditions, and dense foliage. The EMA module significantly improved the detection sensitivity and accuracy. The robust performance was obtained to focus the critical features under the demanding scenarios. Secondly, the conventional C2f module in the backbone layer was replaced with a Group Separable Convolution (GSConv) module. The information redundancy was effectively reduced during extraction while preserving the key features. The GSConv module was utilized to enhance the effectiveness of the attention mechanism. The model architecture was simplified to reduce the computational complexity. Real-time detection was also realized on low-computing-power devices, like embedded systems. Finally, the Weighted Intersection over Union (WIoU) loss function was used to replace the traditional Complete Intersection over Union (CIoU) loss, in order to optimize the regression loss. Additionally, a smoothing term was introduced to improve the precision of the overlap area computation between predicted and ground-truth bounding boxes. Experimental results show that the YOLOv8n-Chili Flower model achieved a recall rate of 94.6% and a mean average precision (mAP) of 95.9%, which were improved by 0.9 and 0.6 percentage points over the original one. In terms of computational efficiency, the modified model reduced FLOPs to 7.2 G, the parameters to 2.39 M, and the model size to 5.0 MB, which were reduced by 12.20%, 20.60%, and 20.63%, respectively. Compared with the state-of-the-art models, like YOLOv5s, YOLOv7tiny, YOLOv8s, and YOLOv9, there was a superior balance between detection accuracy and lightweight. The improved model was then deployed on an NVIDIA Jetson AGX Orin computing platform for the real-world test. An 83.25% correct detection rate and 99.02 frame per second processing speed were achieved to outperform the existing solutions. This finding can also provide technical support for real-time chili flower detection and lightweight deployment during mechanical pollination.

Chili pepper is one of the most widely planted vegetables in China. The current production of fresh chili peppers, such as field management and harvesting, faces the challenges of high labor intensity and low efficiency. The chili pepper industry is ever transitioning towards mechanization and intelligent production. The rapid and accurate detection of chili fruits in the natural environment is of great significance for the automatic picking of chili peppers. However, it is still lacking in the adaptive ability and detection accuracy of the model under different light and occlusion conditions. In this study, an improved detection model, called YOLOX_Pepper, was proposed for chili fruit using YOLOX. Firstly, a fusion-efficient channel CA (coordinate attention) attention mechanism was added to the YOLOX feature fusion network, in order to capture the key features of chili fruits. Secondly, the convolution module in the feature fusion module of the backbone network was replaced with Deformable Convolutional DCNv2 (Deformable ConvNets v2), in order to improve the perceptual ability of the model in the case of the complex geometric features of chili pepper length, width, and aspect ratio, due to branch and fruit occlusion. The experimental results showed that the improved YOLOX_Pepper model had mAP (mean average precision) of 93.30%, which was 3.99, 1.58, 3.19, and 2.84 percentage points higher than that of Faster R-CNN, YOLOv5, YOLOv7, and YOLOX, respectively, with an F1 score of 96%. Under strong light conditions, the mAP of green and red chili fruits of the YOLOX_Pepper model was 69.16% and 89.67%, respectively, and the number of correctly detected green and red peppers was 83 and 304, respectively. Under shadow conditions, the mAP of green and red peppers of the YOLOX_Pepper model was 77.21% and 90.42%, respectively, and the number of green and red peppers was 119 and 255 correctly detected. Under the lack of light conditions, the mAP of the YOLOX_Pepper model for green peppers and red peppers were 77.38% and 75.47%, respectively, and the number of correctly detected green and red peppers were 86 and 311, respectively. The YOLOX_Pepper model performed better in various light conditions, especially in the number and accuracy of detections, compared with the YOLOV5, YOLOV7, and YOLOX models. Under fruit occlusion conditions, the mAP of YOLOX_Pepper was 71.15% and 94.87% for green and red peppers, respectively, and the number of correct detections was 79 and 650 for green and red peppers, respectively. Under branch and foliage occlusion conditions, the mAP of YOLOX_Pepper was 83.98% and 87.10% for green and red peppers, respectively, and the number of correctly detected green and red peppers was 88 and 394, respectively. The improved YOLOX_Pepper model performed better in the chili fruit detection under different occlusions, compared with the YOLOv5, YOLOv7, and YOLOX models. The YOLOX_Pepper model showed excellent performance of detection in complex environments. The effectiveness of the improved module can also provide the intelligent production of chili peppers with reliable technical support.