It is easy to cause increases in temperature and the gasification of water in materials, facilitated via supercharging and the generation of instantaneous strong pressure under the collaborative action of a microwave and a vacuum, thus facilitating the internal cell swelling of materials, changes in fibre structures, and the formation of loose and uniform microstructures. In this experiment, mulberries were dehydrated using microwave–vacuum drying technology. The drying characteristics were disclosed by using crispness as the evaluation index and multiple drying parameters (e.g., products’ surface temperature, microwave power, chamber vacuum level and drying height) as the control variables. The optimised Two-term model can predict the dehydration process of mulberries under multiple drying variables, as determined through the experimental data. The optimal drying variables were determined according to the crispness of the dried mulberries. The optimal puffing quality of mulberries could be gained under a product surface temperature = 50 °C, microwave power = 5.45 W/g, a chamber vacuum level = 0.08 MPa and a drying height = 0 cm. The diffusion coefficient of the available water of the mulberries during the microwave–vacuum drying process ranges from 4.98 × 10⁻⁸ to 3.81 × 10⁻⁷, and the activation energy for drying is 183.923 KJ/mol.

Walnut shell–kernel separation is an essential step in the deep processing of walnut. It is a crucial factor that prevents the increase in the added value and industrial development of walnuts. This study proposes a walnut shell–kernel detection method based on YOLOX deep learning using machine vision and deep-learning technology to address common issues, such as incomplete shell–kernel separation in the current airflow screening, high costs and the low efficiency of manually assisted screening. A dataset was produced using Labelme by acquiring walnut shell and kernel images following shellshock. This dataset was transformed into the COCO dataset format. Next, 110 epochs of training were performed on the network. When the intersection over the union threshold was 0.5, the average precision (AP), the average recall rate (AR), the model size, and floating point operations per second were 96.3%, 84.7%, 99 MB, and 351.9, respectively. Compared with YOLOv3, Faster Region-based Convolutional Neural Network (Faster R-CNN), and Single Shot MultiBox Detector algorithms (SSD), the AP value of the proposed algorithm was increased by 2.1%, 1.3%, and 3.4%, respectively. Similarly, the AR was increased by 10%, 2.3%, and 9%, respectively. Meanwhile, walnut shell–kernel detection was performed under different situations, such as distinct species, supplementary lighting, or shielding conditions. This model exhibits high recognition and positioning precision under different walnut species, supplementary lighting, and shielding conditions. It has high robustness. Moreover, the small size of this model is beneficial for migration applications. This study’s results can provide some technological references to develop faster walnut shell–kernel separation methods.

The separation of walnut kernels and shells has long been regarded as a bottleneck, limiting processing efficiency, product quality, and industry advancement. In response to the challenges of improving separation accuracy and the inadequacy of existing equipment for meeting industry demands, this paper proposes an innovative walnut shell–kernel separation device based on machine vision technology. An experimental system was constructed, and key parameters were optimized to enhance its performance. The device comprises five main modules: material conveyance, image acquisition, control module, sorting module, and frame. Differential separation technology is used to convert the walnut material group into a stable particle flow, addressing the issue of missed selections due to material blockages. An enhanced YOLOv8n algorithm improves small object detection and interference resistance, enabling accurate identification of walnut kernels. The Box–Behnken Design and Artificial Neural Network prediction model was used to determine the optimal operating parameters for the device. Experimental results showed that effective differential separation was achieved when the dual-stage conveyor system operated at speeds of 0.2 m/s and 1 m/s. The improved I-YOLOv8n algorithm reached an accuracy of 98.8%. Using the neural network model, the optimal operational parameters were determined: an air pressure of 0.72 MPa, a jetting component angle of 10.16°, and a sorting height of 105.12 cm. Under these conditions, the device achieved an actual cleaning rate of 93.56%, demonstrating outstanding separation performance. Compared to traditional separation methods, this device offers significant advantages in terms of efficiency, quality, and ease of operation, providing new technological pathways and support for the automation and intelligent transformation of the walnut processing industry. In the future, the device is expected to undergo further improvements to meet broader market demand and serve as a reference for the separation of other agricultural products.

This study focuses on mitigating the decrease in the quality of mulberry after harvest and increasing the value of mulberry products through microwave vacuum drying. The effects of mulberry moisture content on texture properties were investigated, and the test method was optimized through the membership function model and the central composite technique. The influences of the material surface temperature, vacuum degree, and microwave power on the quality of instant mulberry were analyzed comprehensively. A regression model was established to analyze the relationship between each test factor and quality index. The results show that, with increases in the moisture content, both the hardness and chewiness of mulberry present a decreasing trend; when elasticity increases gradually, adhesivity is presented in an inverted V-shaped variation trend, and the cohesiveness remains basically constant. Moreover, the moisture content of mulberry had significant correlations with elasticity, glueyness, chewiness, and hardness (R² > 0.9). When the moisture content of the samples reached ≤44.07%, the total plate count reached a minimum and changed gradually; thus, the moisture content (44.07%) of mulberry was determined for the technological optimization test. The combination of optimal technological parameters was as follows: material surface temperature = 51.0 °C, vacuum degree = 0.07 MPa, and microwave power = 370 W. Under these optimal technological parameters, the soluble solid content was 42.37%, chewiness was 9.08, and the Vc content was 0.725 mg·(100 g)⁻¹. The average error between the test results and software optimization parameters was 5.88%. The optimized microwave vacuum drying technological parameters improved the drying quality of mulberry significantly. The results can provide theoretical support for the microwave vacuum drying of berries.

The separation of walnut kernels from shells is a crucial step in walnut processing. Pneumatic sorting is the mainstream method. However, due to the overlapping suspension speeds of half-shells and eighth-shells, complete separation was not achieved. This paper proposes using a toothed vibrating screen to separate the two. Using EDEM to simulate and analyze the motion forms, collision processes, and stress conditions of walnut shells and kernels on the vibrating screen, the effectiveness of this method was demonstrated, and the mechanisms of shell–kernel retention and loss during the separation process were revealed. Results indicate that 1/8 kernels, being smaller, easily fall into tooth grooves and move upward step by step under the excitation force during reciprocating vibration. The 1/2 shells, being larger, are difficult to fall into the teeth grooves, and their smooth surfaces cause them to slide easily, moving downward continuously under the action of reciprocating vibration and gravity. Using the cleaning rate and loss rate as evaluation indicators, it was found that as the inclination angle of the vibrating screen increased step by step, the cleaning rate consistently increased monotonously. The loss rate initially rose slowly, then surged sharply after reaching 22°, at which point the loss rate was at its lowest, around 10%, and the cleaning rate was at its maximum, at 95%. The shortest retention time of walnut shells on the screen is 2.85 s, and the longest is 10.6 s, with the number of collisions being 458 and 2619, respectively; the collisions between the shells and the kernels account for 51.8%. The failure to thoroughly separate is due to the shell and kernel entangling within the separation area, making it impossible to segregate them. They enter the opposite region, collide, and cause loss and retention phenomena.

The low level of mechanization in the production process of cumin seeds is one of the primary factors limiting their yield and economic efficiency. To enhance the mechanization of cumin seed production, this study focused on cumin seeds as the research subject. Physical parameters of cumin seeds were determined through physical experiments; based on these parameters, a discrete element model of cumin seeds was established, and the shear modulus was calibrated using angle of repose tests. The established model was used to simulate the seeding process of a seed drill, the model’s accuracy was verified by analyzing the seed trajectory, movement velocity, seeding quality, and the dynamic angle of repose of seeds inside the drill. Results indicated that the collision recovery coefficient, static friction coefficient, and rolling friction coefficient between cumin seeds and ABS plastic, stainless steel plates, and other cumin seeds were 0.3, 0.35, and 0.21; 0.49, 0.39, 0.24; and 0.24, 0.38, 0.18, respectively. Calibration via simulated cylinder accumulation tests yielded a deviation of 0.28% between the simulated accumulation angle and the physical accumulation angle at a shear modulus of 100 MPa; the simulated seed trajectory during dispensing closely matched physical dispensing tests. The average deviation in particle drop velocity within the bridge channel region was 4.23%, with a maximum deviation of 6.07%; the average deviation in dynamic packing angle from start to finish for the particle group was 2.84%, with a maximum deviation of 4.18%; and the average mass discharged from the 14 simulated seed nozzles was 0.0446 g, compared to 0.043 g in physical tests, with a deviation of 3.72%. These results demonstrate the high accuracy and reliability of the established cumin discrete element model and its parameters, providing technical support for the design and optimization of full-process mechanical cumin production systems.