To improve soil clod removal and reduce potato damage in potato combine harvesters, this study investigates the processes involved in soil clod removal and potato collisions within the bar-lift chain separation device of the harvester. It outlines the structure and working principles of the machine, theoretically analyzes the key dimensions of the digging device and potato–soil separation components, and derives specific structural parameters. A dynamic mathematical model of the bar-lift chain is established, from which the dynamic equations are formulated. The analysis identifies factors that influence the dynamic characteristics of the bar-lift chain. This study examines the working principles and separation performance of the potato–soil separation device, with a focus on the collision characteristics between potatoes and both the screen surface and the bars. Key factors such as the separation screen’s line speed, the harvester’s forward speed, and the tilt angle of the separation screen are considered. Simulations are performed using a coupling method based on the Discrete Element Method (DEM) and Multi-Body Dynamics (MBD). Through simulation experiments, the optimal parameter combinations for the potato–soil separation device are determined. The optimal working parameters are identified as a separation screen line speed of 1.25 m/s, a forward speed of 0.83 m/s, and a tilt angle of 25°. Field harvesting experiments indicate a potato loss rate of 1.8%, a damage rate of 1.2%, an impurity rate of 1.9%, a skin breakage rate of 2.1%, and a yield of 0.15–0.21 ha/h. All results meet national and industry standards. The findings of this research provide valuable theoretical references for simulating potato–soil separation in combine harvesters and optimizing the parameters of these devices. Future potential research will consider the automatic regulation of the excavation volume of the potato–soil mixture, aiming to achieve intelligent control of the potato–soil separation operation.

This paper presents the design of an integrated potato-planting machine capable of full-film covering, creating micro-ditches on ridges, and covering seed rows with soil. The machine addresses the challenges of traditional methods, allowing for mechanized planting with complete film coverage and individual seed row soil covering. The key components of the prototype were analyzed and designed. This includes the seeding system, the pointed wing-shaped trencher for creating micro-ditches, and the straddling film-mulching device. Additionally, the operating mechanism of these core components was analyzed. Field trials demonstrated an 85% success rate for seed depth placement under the film. The machine also achieved a 90% qualified index for seed potato spacing, with a 6% repetitive seeding rate and a 3% missed seeding rate. Furthermore, the qualified rate for covered soil width on seed rows was 94%, and the qualified rate for covered soil thickness was 93%. The adjacent row spacing achieved an 88% success rate. The degree of mechanical damage to the exposed surface of the mulch film was minimal, at only 30.2 mm²/m². These results meet all the national and industry standards. The successful field trials confirm the effectiveness of the machine in performing integrated fertilization, sowing, ridging, full-film covering, and seed row soil covering. Compared to traditional methods, this machine significantly reduces labor intensity for farmers and enhances the economic value of potato planting.

Rapid and non-destructive acquisition of soil nutrient information is crucial for precision fertilization and soil quality monitoring. This study aims to establish a Raman spectroscopy-based framework for predicting key soil fertility indicators, including alkali-hydrolyzable nitrogen (AN), total nitrogen (TN), total phosphorus (TP), and organic matter (OM). The framework systematically integrates three typical spectral preprocessing methods (Standard Normal Variate transformation (SNV), Savitzky–Golay first derivative (SG_D1), and wavelet transform (Wavelet)), three feature selection strategies (Recursive Feature Elimination, XGBoost importance, and Random Forest importance), and 14 mainstream regression models to construct a multi-combination modeling system. Model performance was evaluated using five-fold cross-validation, with 80% of samples used for training and 20% for validation in each fold. Preprocessed Raman spectral features served as input variables, while the corresponding nutrient contents were used as outputs. Results showed significant differences in prediction performance across various combinations of preprocessing methods and regression algorithms for the four soil nutrient indicators. For AN prediction, the combination of Raw_SNV preprocessing with ElasticNet and BayesianRidge models achieved the best performance, with Test R² values of 0.713 and 0.721, and corresponding Test NRMSE as low as 0.092. For OM prediction, the same Raw_SNV preprocessing with ElasticNet and BayesianRidge also performed well, yielding Test R² values of 0.825 and 0.832, and Test NRMSE of 0.100 and 0.098, respectively. In TN prediction, both ElasticNet and BayesianRidge under Raw_SNV preprocessing achieved consistent Test R² of 0.74 and Test NRMSE around 0.20, indicating stable reliability. For TP prediction, the BayesianRidge model with Raw_SNV preprocessing outperformed all others with a Test R² of 0.71 and Test NRMSE of just 0.089, followed closely by ElasticNet (Test R² = 0.70, Test NRMSE = 0.092). Overall, the Raw_SNV preprocessing method demonstrated superior performance compared to SG_D1_SNV and Wavelet_SNV. Both BayesianRidge and ElasticNet consistently achieved high R² and low NRMSE across multiple targets, showcasing strong generalization and robustness, making them optimal model choices for Raman spectroscopy-based soil nutrient prediction. This study demonstrates that Raman spectroscopy, when combined with appropriate preprocessing and modeling techniques, can effectively predict soil organic matter and nitrogen in specific soil types under laboratory conditions. These results provide initial methodological insights for future development of intelligent soil nutrient diagnostics.

The new technique of filming in autumn and planting directly through the plastic film in spring is an effective method for water-saving and drought-resistant commercial potato production. However, there are currently no supporting film-drilling seeders available. To address this, a new potato seeder machine has been specifically designed for planting potatoes in the dryland, hilly, and mountainous areas of northwest China. This machine can perform top mulching and hole planting in both the autumn and spring seasons. This innovative potato seeder accomplishes several tasks simultaneously: seeding, inoculation (if desired), hole punching through the mulch film, seed placement, and soil covering. The machine features an optimized spoon-chain seeder with an eccentric coupling mechanism that ensures the hole-punching device stays perpendicular to the ground throughout planting, minimizing damage to the mulch film. Additionally, a dedicated seeding valve opening and closing mechanism was designed to extend the opening time of the hole-forming device’s movable mouth beyond the potato’s falling time, guaranteeing successful seed placement. Furthermore, a soil-covering device specifically designed for use with mulch film ensures proper soil retention after seeding. Through computer-aided design (RecurDyn V9R5 software) analysis, the hole-punching device’s penetrating angle was optimized to minimize the tearing of the mulch film during entry into and exit from the soil. Rigorous field testing demonstrated the machine’s effectiveness. The seeder achieved a 92% success rate for proper planting depth, an 88% success rate for accurate seed potato spacing, a 98% success rate for avoiding overplanting, and a 99% success rate for eliminating missed planting spots. These field test results meet or exceed national and industry standards, validating the machine’s design goals. In essence, this innovative potato seeder, with its eccentric coupling mechanism, offers a one-pass solution for potato seeding, inoculation (optional), planting, and soil covering, significantly improving efficiency.

The efficacy of coated fertilizers in enhancing nutrient use efficiency and reducing environmental impacts depends on their coating properties. This study developed three biodegradable, waterborne polyacrylate latexes (A, B, and C) as eco-friendly coatings for controlled-release fertilizers (CRFs) using the Wurster fluidized bed process. The latexes were synthesized with varying hard-to-soft monomer ratios and cross-linked with 2 wt% aziridine to investigate how monomer composition affects coating properties and nutrient release. The results showed that coating B, which had an intermediate hard-to-soft monomer ratio, demonstrated optimal properties. It exhibited the lowest swelling capacity (2.54% at 60 °C), a suitable glass transition temperature (15.34 °C), and the slowest nutrient release, with cumulative nitrogen release remaining below 60% after 11 days in water at 40 °C. In field trials, the fertilizer coated with material B produced the highest rice yield among tested domestic CRF brands. It also achieved a significant 19.1% yield increase compared to a single basal application of conventional compound fertilizer. These findings confirm that this modified latex provides an effective and environmentally friendly solvent-free coating strategy for high-performance CRFs.

The fusion of Raman and visible–near-infrared (VIS–NIR) spectroscopy provides a promising pathway for rapid and non-destructive soil analysis. However, conventional fusion strategies often fail to properly balance modality discrepancies and complementary information. To address this limitation, this study develops an adaptive Gated Ridge Regression fusion model (Fusion_GatedRidge) for predicting soil organic matter (SOM). A total of 246 soil samples collected from a dryland agricultural region in Shanxi Province were analyzed using laboratory Raman and VIS–NIR spectroscopy. After standard preprocessing, three baseline fusion frameworks—EarlyFusion_Ridge, AE_LatentFusion, and WeightedLate_Fusion—were implemented for comparison with the proposed gated fusion method. Under fivefold cross-validation, Fusion_GatedRidge achieved the best performance, with an R² of 0.83, RMSE of 2.01 g·kg⁻¹, and RPD of 2.39. Compared with single-modality models, R² increased by up to 18.6% and RMSE decreased by up to 23.0%. The gating mechanism dynamically adjusted the contributions of Raman and VIS–NIR features, leading to more stable predictions with residuals largely within −2 to 2 g·kg⁻¹. Overall, the proposed model demonstrates that adaptive modality weighting enhances the exploitation of complementary spectral information and significantly improves SOM prediction accuracy. These findings offer a concise and effective multimodal fusion framework for laboratory-based soil nutrient assessment.