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.

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.