Non-destructive assessment of kiwifruit quality is critical for postharvest preservation and grading. This paper proposes a novel quantitative evaluation method for the kiwifruit comprehensive quality index (KCQI) during shelf life, based on hyperspectral imaging (HSI) combined with a one-dimensional convolutional neural network (1D-CNN). Hyperspectral images of two kiwifruit cultivars were acquired at four shelf-life stages using an HSI system, and six quality parameters were measured as reference standards. Based on correlation and factor analyses, five key parameters—soluble solids content, firmness, L*, b*, and chroma—were selected to construct the KCQI. Three spectral band selection methods and three modeling algorithms were compared, with the competitive adaptive reweighted sampling (CARS)–1D-CNN model yielding the highest prediction accuracy ($R_P^2$ = 0.82, RMSEP = 0.26, RPD_P = 2.39). Subsequently, a spatial distribution map was generated to visualize the KCQI. These results demonstrate the potential of the HSI–1D-CNN approach for accurate postharvest quality monitoring and intelligent grading.

To mitigate the entanglement, agglomeration, and unstable conveying of high-moisture rice residues during stubble crushing for field incorporation, a discrete element method (DEM)-based modeling and optimization framework was developed to enhance the performance of a stubble-crushing device under wet paddy-field conditions. The device structure and kinematics were first analyzed, and the physical and mechanical properties of the residues were obtained through field measurements. A hollow wet–flexible straw model was then proposed to account for both mechanical breakage and moisture-induced adhesive interactions. Key contact and material parameters were calibrated using DEM simulations coupled with laboratory shear and three-point bending tests, showing good agreement with experimental trends. The validated model was subsequently extended to the device scale to characterize the cyclic capture–acceleration–throwing behavior of residues inside the crushing chamber. The individual and interactive effects of rotor speed, forward speed, and throwing-chamber clearance on comminution efficiency and conveying stability were investigated. A multi-objective response surface optimization identified an optimal parameter combination of 2000 rpm rotor speed, 0.87 m s⁻¹ forward speed, and 10.5 cm clearance. Under these conditions, the comminution rate reached 96.94%, and the coefficient of variation in throwing uniformity was 8.71%. Field validation further confirmed the reliability of the simulation results, with relative errors below 6%. Overall, the proposed framework provides an effective tool for the design optimization and parameter selection of wet-residue comminution equipment.

To address the challenges of manual apple harvesting and the limitations of existing devices—such as constrained workspace, low efficiency, and limited flexibility—a two-stage, sub-region harvesting device was developed. The design, informed by the fruit distribution characteristics in densely planted dwarf apple orchards, integrates a positioning mechanism and a fruit-picking mechanism, enabling multiple pickings within a single positioning operation to enhance workspace coverage. A forward kinematics model was established using the Denavit–Hartenberg (D–H) parameter method. An improved Monte Carlo simulation based on a hybrid Beta distribution estimated the maximum reachable distances of the fruit-picking reference point in the X, Y, and Z directions as 2146 mm, 2169 mm, and 2165 mm, respectively—adequately covering the target harvesting domain. Incorporating a translational axis structure further expanded the harvesting volume by 1.165 m³, a 42.40% improvement over the conventional 3R configuration. To support adaptive control, a random point–geometry fusion method was proposed to solve for joint variables based on harvesting postures, and an automatic fruit-picking control system was implemented. Experimental validation, including reference point tracking and harvesting tests, demonstrated maximum positioning errors of 1.5 mm and 2.2 mm, a fruit-picking success rate of 76.53%, and an average picking time of 7.24 s per fruit—marking a 4.6% improvement compared to existing devices reported in previous studies. This study provides a comprehensive technical framework and practical reference for advancing mechanized apple harvesting.

As an important technology to enhance nutrient use efficiency and reduce agricultural non-point source pollution, controlled-release fertilizers (CRFs) have been widely applied in modern agriculture. However, during packaging, transportation, and field application, CRF particles are prone to mechanical impacts, which can lead to particle fragmentation and damage to the controlled-release coating. This compromises the release kinetics, increases nutrient loss risk, and ultimately exacerbates environmental issues such as eutrophication. Currently, studies on the impact-induced fragmentation behavior of CRF particles remain limited, and there is an urgent need to investigate their fragmentation susceptibility mechanisms from the perspective of internal stress evolution. In this study, the mechanical properties of CRF particles were first experimentally determined to obtain essential parameters. A two-layer finite element model representing the coating and core structure of the particles was then constructed, and a fragmentation susceptibility index was proposed as the key evaluation criterion. The index, defined as the ratio of fractured volume to peak impact energy, reflects the efficiency of energy conversion at the critical moment of particle rupture (1–5). An explicit dynamic simulation framework incorporating multiple influencing factors—equivalent diameter, sphericity, impact material, velocity, and angle—was developed to analyze fragmentation behavior from the perspective of energy transformation. Based on the observed effects of these variables on fragmentation susceptibility, three regression models were developed using response surface methodology to quantitatively predict fragmentation susceptibility. Comparative analysis between the simulation and experimental results showed a fragmentation rate error range of 0–11.47%. The findings reveal the relationships between particle fragmentation modes and energy responses under various impact conditions. This research provides theoretical insights and technical guidance for optimizing the mechanical stability of CRFs and developing environmentally friendly fertilization strategies.

This study proposed a method to predict the crushing force of controlled-release fertilizer granules based on their phenotypic characteristics to prevent coating damage during production, transport, and fertilization, which could affect nutrient diffusion rates. The phenotypic features, including sphericity, particle size, and texture, of three commonly used controlled-release fertilizers were obtained using machine vision, while the crushing force was measured using a universal testing machine. A principal component analysis was applied for data reduction, and the optimal parameters for the support vector machine (SVM) were selected using particle swarm optimization (PSO) combined with k-fold cross-validation. A particle swarm optimization–support vector machine (PSO-SVM) model was then developed to predict the crushing force based on fertilizer shape features. Compared with the traditional method, the innovation of this paper is that a non-destructive prediction method is proposed, which enables high-precision predictions of the crushing force by integrating multi-dimensional phenotypic features and an intelligent optimization algorithm. Comparative tests with a random forest regression, the K-nearest neighbor, a back propagation (BP) neural network, and a long short-term memory (LSTM) neural network have demonstrated that the PSO-SVM model outperforms these methods in terms of mean absolute error, root mean square error, and correlation coefficient, underscoring its effectiveness. The proportion of predictions within the −10% to +10% error range reached 0.82, 0.82, and 0.86 for the three fertilizers, confirming the high reliability and accuracy of the PSO-SVM method for non-destructive testing.

To address the challenge of apple picking-point localization under severe occlusion and complex backgrounds in dwarf rootstock high-density orchards, this paper proposes a target-region-segmentation-based 3D localization method in which the fruit sphere center is defined as the picking point. A lightweight occlusion-aware semantic segmentation network, OA-LiteSegNet, is developed to generate accurate foreground masks for partially visible apples. Guided by the segmentation result, a local target-region point cloud is reconstructed from the depth map and further processed by robust sphere fitting to estimate the apple sphere center and fruit diameter. Experimental results show that OA-LiteSegNet achieves 90.35% mIoU and 76.27% BF1 with only 5.92 M parameters and 11.30 GFLOPs, while reaching an inference speed of 128.40 FPS, achieving a favorable accuracy–efficiency trade-off among the compared mainstream models. The proposed 3D localization method achieves an average sphere-center error of 2.88 mm, which is 68.4% lower than that of the conventional bounding-box-center back-projection method (9.11 mm), and maintains stable performance across different occlusion types. These results demonstrate the potential of the proposed method for real-time and accurate apple localization under controlled laboratory occlusion scenarios, while further field validation in real orchards remains necessary.