A field-based apple detection and grading device was developed and used to detect and grade apples in the field using a deep learning framework. Four features were selected for apple grading, namely, size, color, shape, and surface defects, and detection algorithms were designed to discriminate between the four features using machine vision and other methods. Then, the four apple features were fused, and a support vector machine (SVM) was used for infield apple grading into three grades: first-grade fruit, second-grade fruit, and other-grade fruit. The results showed that for a single index, the accuracy of detecting the apple size, the fruit shape, the color, and the surface defects, were 99.04%, 97.71%, 98%, and 95.85%. The grading accuracies for the first-grade fruit, second-grade fruit, other-grade fruit, and the average grading accuracy based on multiple features were 94.55%, 95.71%, 100%, and 95.49%, respectively. The field experiment showed that the average grading accuracy was 94.12% when the feeding interval of the apples was less than 1.5 s and the walking speed did not exceed 0.5 m/s, meeting the accuracy requirements of field-based apple grading.

The most common harvesting method of Lycium barbarum L. (L. barbarum) is manual harvesting, resulting in low efficiency and high cost. Meanwhile, the efficiency of vibration harvesting, which is considered an efficient mechanical harvesting method, can be significantly improved if the optimized resonance frequency of the shrub can be obtained. To vibration harvest fruit efficiently, a 3D model of the shrub was established based on measurements of the shape parameters, and material mechanics models of the branches were established based on physical tests. The modal analysis of the shrub based on finite element method (FEM) simulation was performed to obtain the range of resonance frequency, and the modal experiment of the shrub using acceleration sensors and an impact hammer was conducted to obtain the accurate resonance frequency. Based on the results of the modal analysis and experiment, the optimized resonance frequency was determined to be 2 Hz. The field experiment showed that the fruit fell off when the branches were vibrated at this frequency. The results provide the design basis for the efficient vibration harvesting of L. barbarum.

When harvesting Lycium barbarum L., excess amounts of detachments of the half-ripe fruit, unripe fruit, flowers, and leaves significantly affect the yield and adversely affect the subsequent processing, such as drying and grading. Finite element method (FEM) simulations and experiments of detachments were performed to harvest more ripe fruit and less half-ripe fruit, unripe fruit, flowers, and leaves. Three-dimensional (3D) models of the ripe fruit, half-ripe fruit, unripe fruit, flowers, leaves, fruit calyxes (flower calyx), fruit stems (flower stem), and branches were constructed using a 3D scanner, and material mechanics models of the above parts were established based on physical tests with universal testing machines. Detachment simulations and experiments of the ripe fruit, half-ripe fruit, unripe fruit, flowers, and leaves were performed to determine the detachment mechanisms and sequences. The detachment forces of each set of two parts were obtained. The field experiments showed that the detachment force between the fruit and calyx of ripe fruit was the lowest value of these forces, and only the ripe fruit was the first to detach from the calyx when harvesting. The results provided data support on the mechanics properties of wood and the optimization basis for the harvesting method of L. barbarum.

The accurate quantitative maturity detection of fresh Lycium barbarum L. (L. barbarum) fruit is the key to determine whether fruit are suitable for harvesting or not and can also be helpful to improve the quality of post-harvest processing. To achieve this goal, abnormal samples were eliminated by the Mahalanobis Distance (MD), and nine components (i.e., R, G, B, H, S, V, L, a, and b) of the ripe fruit, half-ripe fruit, and unripe fruit were extracted, firstly. Then, significant component combinations of the three fruits beneficial to the extraction of their areas were determined. Through binary processing, morphology processing, and other image processing methods, a quantitative maturity detection model of fruit was established based on the support vector machine (SVM) model. On this basis, field experiments were conducted to verify and compare the relationship between the prediction results of the model and the picking forces of fruit. Field experiments showed that the accuracies of both the training set and prediction set were 100% and the prediction results of the model were consistent with the picking forces of fruit. Findings provided a theoretical basis for the accurate quantitative maturity detection of fresh L. barbarum fruit.

A pneumatic oscillating Chinese wolfberry harvester was designed to improve the efficiency of manual harvesting and minimize fruit damage by mechanical harvesting. The shedding model of Chinese wolfberry under pneumatic forces was established based on kinetic analysis, and the flow field characteristics were investigated using computational fluid dynamics (CFD). The position and shape of the fan outlet were determined by comparing the effects of a linear reduction outlet and a Laval reduction outlet on the outlet airflow rate. The size of the oscillating mechanism was optimized with nonlinear constraints to achieve uniform oscillation of the airflow. A three-factor, three-level orthogonal test was conducted on the NingQi 7 wolfberry variety. The flow rate at the outlet, the oscillation frequency, and the outlet distance were the test factors, and the net harvesting rate of ripe fruits, the harvesting rate of green fruits, and the damage rate of ripe fruits were the test indices. The results showed that the net harvesting rate of ripe fruits was 85.21% at an outlet distance of 10 cm, an outlet flow rate of 70 m·s⁻¹, and an oscillation frequency of 2 Hz. This study provides references for the design of pneumatic harvesters for Chinese wolfberry.