The paper shows that the drive axle housing of the electric farm management machine not only has the role of carrying and transmitting power, but also plays a supporting role for the main reducer, brake and other components, which needs to meet the requirements of stiffness and strength. Three-dimensional modeling and finite element analysis are used to design the joint, and a reasonable three-dimensional modeling of the drive axle housing is carried out. Aiming at the structural quality of the axle housing, the finite element analysis method is used to reduce the quality of the axle housing. Firstly, the force analysis is carried out according to the maximum vertical force condition of the drive axle housing. Secondly, the static and dynamic characteristics of the axle housing structure are analyzed. Then, with the parameters that have great influence on the quality as the design variables, the quality of the axle housing as the optimization objective, and the maximum static stress and maximum deformation as the constraint conditions, the Latin hypercube experimental design method and genetic optimization algorithm are used to carry out the lightweight design of the axle housing. Finally, through the optimization scheme, the total weight of the axle housing using structural steel is reduced from 169.4kg to 156.83kg, achieving a weight reduction effect of 7.42%, and realizing the lightweight of the axle housing.

With the increasing availability of multimodal remote sensing (RS) data, semantic segmentation that leverages complementary information from true orthophotos (TOP) and digital surface models (DSM) has become essential for urban analysis. Diffusion-based segmentation provides an effective iterative refinement mechanism for modeling complex multimodal distributions; however, conventional pixel-wise supervision emphasizes local accuracy while overlooking global distribution alignment, often leading to inconsistent predictions and blurred object boundaries. Although maximum mean discrepancy (MMD) measures global statistical differences between predicted and ground-truth distributions, its effectiveness in high-dimensional class-probability spaces is limited by directional cancellation effects that reduce sensitivity to complex distribution shifts. To address this issue, we propose a projection-kernel regularized diffusion-based multimodal RS segmentation framework that enforces global statistical alignment through distribution-level regularization rather than modifying the intrinsic diffusion process. The proposed regularization performs multi-directional projections of high-dimensional class-probability vectors onto one-dimensional subspaces and derives a closed-form kernel integration to avoid numerical sampling across projection directions, enabling efficient and stable global distribution matching. In addition, a Cross-Attention Dual-Encoder Fusion (CADEF) module is introduced to alleviate geometry–texture misalignment, and a Hierarchical EMA-Gated Recursive Denoising (HERD) mechanism is designed to stabilize multiscale feature refinement. Experiments on the ISPRS Vaihingen and Potsdam benchmarks demonstrate that the proposed regularization consistently improves segmentation accuracy over state-of-the-art CNN-, Transformer-, and diffusion-based baselines, yielding enhanced global consistency and sharper boundary delineation. Code is available at: https://github.com/tonyy127/PKDiff