Hefei University

The identification of soybean variety is of great importance for crop quality, stabilizing yield, and regulating agricultural markets. This study presents a novel, high performance approach for soybean variety identification by innovatively fusing hyperspectral data with RGB images and introducing an optimized deep learning framework. YOLO (You Only Look Once), a widely-used real-time object detection algorithm, was adapted and improved in this work. Different spectral preprocessing strategies were evaluated to enhance data quality, then a novelty linear interpolation method was proposed to integrate spectral and visual information to enrich feature inputs. YOLOv11 architecture was improved by optimizing parameter efficiency and strengthening the spatial attention mechanism, boosting model representational capacity. Results demonstrate that the combined preprocessing method of moving average and multiple scattering correction achieved optimal performance. The proposed enhanced YOLOv11 model with multi-modal data fusion at trained a test set accuracy of 98.8%, significantly outperforming conventional single modal approaches. These findings validate that multi-modal fusion of spectral and imaging data is a highly effective strategy for crop variety identification, with promising translational potential for broader applications in agricultural product classification and quality control.

Size sieving and Donnan exclusion are generally recognized as the two primary mechanisms governing membrane separation in aqueous systems; however, their respective roles in covalent organic framework (COF) membranes remain insufficiently elucidated. In this work, bilayer COF composite membranes were fabricated by a two-step interfacial polymerization of cationic and anionic COFs. By combining pore-shielding effects with the intrinsic charge of ionic COFs, two types of bilayer membranes were constructed, featuring either smaller effective pore size with weakened surface charge or larger pore size with stronger surface charge. Separation performance was evaluated using dyes and salts with different molecular sizes and charge states. For both membranes, solute rejection decreased with decreasing molecular or ionic size, indicating that size sieving dominates the separation process, whereas Donnan exclusion becomes significant only when solute dimensions approach the membrane pore size. Importantly, in dye/salt mixed solutions, salt-induced surface-charge neutralization markedly reduced dye rejection for the strongly charged COF membrane, while the small-pore, weakly charged COF membrane maintained high dye rejection and salt permeability. The latter membrane exhibited a stable permeance of 115 L·m⁻²·h⁻¹·bar⁻¹ and a dye/salt selectivity of 109 during 300 h of cross-flow filtration. These results demonstrate the dominant role of size sieving and the inherent limitations of Donnan exclusion in COF membrane separations, and suggest that precise pore-size regulation coupled with surface-charge attenuation provides an effective strategy for designing stable, high-performance COF membranes in molecular/ionic separations.

To address uncertainty and inequality constraints in dual-arm collaborative robot systems, this paper proposes an adaptive robust control strategy based on the diffeomorphism technique. Specifically, system uncertainties are characterized using fuzzy set theory, while inequality constraints are systematically incorporated into the constraint-following control framework via diffeomorphism. Moreover, an adaptive robust control scheme is developed to ensure practical stability in the presence of uncertainties. In addition, the control parameters are optimized based on the fuzzy description of uncertainty, striking a balance between system performance and control cost. Finally, numerical simulations are conducted to validate the effectiveness of the proposed scheme.