This study targets a core challenge in designing efficient drying equipment for Zanthoxylum schinifolium, the inability to establish a rigorous theoretical framework for optimization. This deficit primarily stems from a critical knowledge gap—the insufficiently characterized evolution of material porosity (ε) during drying—which consequently hampers predictive design and process control. The porosity (ε) evolution in the accumulation layer of Zanthoxylum schinifolium bulk was systematically examined by combining experimental analysis with numerical simulation. Zanthoxylum schinifolium is one of the spice plants, commonly known as Korean pepper. Dynamic evolution of the porosity during drying can lead to an insufficient basis for the process and structural optimization. This study aims to reveal the evolution of the porosity in the Zanthoxylum schinifolium bulk from a multi-scale perspective. Experimental analysis and numerical simulation were also combined during drying. The results show that the porosity varied in the range of 0.345-0.591. In the initial stage (0-120 min, Mc≥34.46%), the layer thickness (L) changed slightly (from 0.2 to 0.193 8 m, a decrease of only 3.1%), and the pressure difference (ΔP) fluctuated slightly (432.3-513.9 Pa). In the main drying stage (120-390 min, 10.45%≤Mc≤34.46%), the porosity decreased significantly, while the pressure difference (ΔP) dropped sharply, and the fruit body contracted outstandingly. In the final stage (t>390 min, Mc≤10.45%, the Zanthoxylum schinifolium bulk layer shared a local "cracking"; the layer thickness (L) abnormally expanded by 0.018 mm. Meanwhile, an ε-Mc mathematical model was established (R²=0.977 8) for the numerical simulation. This heat transfer in the bulk layer started from the bottom center and preferentially diffused upward and inward along the wall (steady-state temperature 70.1°C). This path of the heat diffusion coincided with the order of "cracking" in the Zanthoxylum schinifolium bulk layer in practice. The heat transfer of a single particle was divided into three stages: the shell-breaking (the heat broke through the shell to transfer the heat into the seed, and the Zanthoxylum schinifolium shell shared the slight contraction deformation); the internal heat-transfer dominant (the Zanthoxylum schinifolium seed gradually warmed up, and the contraction of the Zanthoxylum schinifolium shell increased gradually); and the heat balance approaching stage (the internal temperature of the Zanthoxylum schinifolium seed tended to stabilize, and the deformation of the Zanthoxylum schinifolium shell reached its peak value of 0.487 mm). This finding can also provide a theoretical basis to optimize the Zanthoxylum schinifolium drying on the heat and mass transfer.

In response to the challenge posed by low recognition accuracy in rugged terrains with diverse topography as well as feature recognition agricultural settings, this paper presents an optimized version of the YOLOv5 algorithm alongside the development of a specialized laser weeding experimental platform designed for precise identification of corn seedlings and weeds. The enhanced YOLOv5 algorithm integrates the effective channel attention (CBAM) mechanism while incorporating the DeepSort tracking algorithm to reduce parameter count for seamless mobile deployment. Ablation tests validated this model’s achievement of 96.2% accuracy along with superior mAP values compared to standard YOLOv5 by margins of 3.1% and 0.7%, respectively. Additionally, three distinct datasets captured different scenarios, and their amalgamation resulted in an impressive recognition rate reaching up to 96.13%. Through comparative assessments against YOLOv8, the model demonstrated lightweight performance improvements, including a notable enhancement of 2.1% in recognition rate coupled with a marginal increase of 0.2% in mAP value, thus ensuring heightened precision and robustness during dynamic object detection within intricate backgrounds.