Most of the current crop row detection algorithms focus on extracting crop canopy rows as location information. However, for some high-pole crops, due to the transverse deviation of the position of the canopy and roots, the agricultural machinery can easily cause the wheel to crush the crop when it is automatically driven. In fact, it is more accurate to use the crop root row as the feature for its location calibration, so a method of crop root row detection is proposed in this paper. Firstly, the ROI (region of interest) of the crop canopy is extracted by a semantic segmentation algorithm, then crop canopy row detection lines are extracted by the horizontal strip division and the midpoint clustering method within the ROI. Next, the Crop Root Representation Learning Model learns the Representation of the crop canopy row and crop root row to obtain the Alignment Equation. Finally, the crop canopy row detection lines are modified according to the Alignment Equation parameters to obtain crop root row detection lines. The average processing time of a single frame image (960 × 540 pix) is 30.49 ms, and the accuracy is 97.1%. The research has important guiding significance for the intelligent navigation, tilling, and fertilization operation of agricultural machinery.

目 的 准双曲面齿轮副在实际装配过程中不可避免地存在安装误差。 本文旨在建立考虑多种安装误差的准双曲面齿轮啮合模型, 对齿轮副啮合印痕特征 (齿面分布位置、 大小和方向) 进行参数化建模, 精确评价印痕对安装误差的敏感性, 以及研究降低接触性能对安装误差的敏感度的方法, 为准双曲面齿轮副的加工和安装提供理论依据。

To control the meshing performance of hypoid gear drive, current local conjugate theory and local synthesis method establish a relationship between the relative motion and local geometrical properties of the mating surfaces at one reference point. Theoretically, both local conjugate theory and local synthesis method cannot ensure the contact performance on the entire tooth surface resulting in uncontrolled contact pattern and undesirable transmission error. A global synthesis approach consisting of a machine-tool settings calculation model, a tooth contact analysis model, a meshing quality assessment function, and a swarm intelligence algorithm are proposed. The direction, area, and shape of the contact pattern and the amplitude of the intersection of two adjacent transmission error curves are taken as the evaluation indexes. Three curvatures of the design pitch cone of the pinion are taken as the control variables. A global selection space is then established within the reasonable range of the curvatures. An improved multiple population genetic algorithm is employed to find the optimal set of the curvatures to achieve the target values of the evaluation indexes. To avoid the edge contact and corner contact condition, a feasible region is defined on tooth surface and the contact patterns on the gear and pinion surfaces are all confined within the area. The optimized contact patterns obtained by the loaded tooth contact analysis method are similar to those obtained by the proposed approach, thus demonstrating the effectiveness of this methodology. The main novelty of this approach is to translate the derivation of the mathematical relation between the curvatures of the mating surfaces and the contact properties to solving a multi-objective optimization problem of the meshing quality indexes by the intelligence algorithm.

The study of loaded meshing characteristics and dynamic behavior is significant for evaluating the stability of hypoid gear under actual working conditions. Loaded tooth contact analysis (LTCA) of a hypoid gear drive under different loads is carried out. The equivalent meshing force, loaded transmission error (LTE), comprehensive elastic deformation, and time-varying meshing stiffness (TVMS) are investigated. Results show that the LTE and TVMS are sensitive to load, and the LTE and TVMS curves show obvious asymmetric as the load increases. Under low load conditions, the actual contact ratio increases significantly with the increase of load, but tends to be flat when the load reaches a certain range. The obtained TVMS and LTE are fitted by higher Fourier series and introduced into an 8-DOF dynamic model. By comparing the time history diagram, phase diagram, Poincaré section, and spectrum, the dynamic characteristics of the system under different loads are contrasted. On low load condition, the system may exhibit chaotic motion in certain meshing frequency bands and damping ratio intervals. While the tooth backlash increases to a critical value, the system may change to chaotic motion from periodic motion. The results provided a basis for improving the meshing performance of hypoid gear.