Existing corn harvester cutting blades have problems associated with large cutting resistance, high energy consumption, and poor cut quality. Using bionics principles, a bionic blade was designed by extracting the cutting tooth profile curve of the B. horsfieldi palate. Using a double-blade cutting device testing system, a single stalk cutting performance contrast test for corn stalks obtained at harvest time was carried out. Results show that bionic blades have superior performance, demonstrated by strong cutting ability and good cut quality. Using statistical analysis of two groups of cutting test data, the average cutting force and cutting energy of bionic blades and ordinary blades were obtained as 480.24 N and 551.31 N and 3.91 J and 4.38 J, respectively. Average maximum cutting force and cutting energy consumption for the bionic blade were reduced by 12.89% and 10.73%, respectively. Variance analysis showed that both blade types had a significant effect on maximum cutting energy and cutting energy required to cut a corn stalk. This demonstrates that bionic blades have better cutting force and energy consumption reduction performance than ordinary blades.

With the application of elastic parameter test method of composite material mechanics, UTM6503 PC-controlled universal testing machine was adopted to study the characteristics of axial compressive mechanics on the xylem and the whole stalk in the paper. The test result showed that the average axial compressive elastic modulus of the ramie xylem of first crop of "Zhongzhu No.1" was 374.70 MPa and the average maximum compressive strength was 13.71 MPa, while the average axial compressive elastic modulus of whole stalk was 336.40 MPa, and its average maximum compressive strength was 13.19 MPa; there was no significant difference between the elastic modulus and the compressive strength of the ramie xylem and the whole stalk. In the stalk composition, xylem and phloem bond on the surface depending on their own adhesion strength which was not able to prevent the phloem slipping away along the surface of xylem. In the compressive test, it showed the load-bearing function of xylem more.

Environment perception is a basic and necessary technology for autonomous vehicles to ensure safety and reliable driving. A lot of studies have focused on the ideal environment, while much less work has been done on the perception of low-observable targets, features of which may not be obvious in a complex environment. However, it is inevitable for autonomous vehicles to drive in environmental conditions such as rain, snow and night-time, during which the features of the targets are not obvious and detection models trained by images with significant features fail to detect low-observable target. This article mainly studies the efficient and intelligent recognition algorithm of low-observable targets in complex environments, focuses on the development of engineering method to dual-modal image (color–infrared images) low-observable target recognition and explores the applications of infrared imaging and color imaging for an intelligent perception system in autonomous vehicles. A dual-modal deep neural network is established to fuse the color and infrared images and detect low-observable targets in dual-modal images. A manually labeled color–infrared image dataset of low-observable targets is built. The deep learning neural network is trained to optimize internal parameters to make the system capable for both pedestrians and vehicle recognition in complex environments. The experimental results indicate that the dual-modal deep neural network has a better performance on the low-observable target detection and recognition in complex environments than traditional methods.

No abstract

No abstract