Search

Roll forming is a plastic processing technology that gradually bends metal strips and sheets laterally using sequentially arranged forming dies. Due to its low cost, high efficiency, and flexibility, it has become one of the important technologies for light weighting, energy saving, emission reduction, and safety improvement in various fields such as new energy, aerospace, and rail transportation in China. However, the complexity and discreteness of the process, uneven material thickness properties, and low level of equipment informatization and flexibility automation have made it similar to a “black box”, making it difficult to predict product quality, highly dependent on manual experience for production debugging, limited in formable cross sections, and unstable in yield. Therefore, this paper proposes a data-driven intelligent roll forming equipment (system) and introduces in detail its technical architecture and characteristics. By building a data architecture based on artificial intelligence, this system collects, screens, integrates, stores, and analyzes discrete data in traditional roll forming. Meanwhile, it integrates digital twins, artificial intelligence, contour detection technology, and multi-agent collaborative control to construct a self-correcting production mode that can replace manual experience. For the new energy vehicle industry, this paper provides a case study of using this system to solve springback control of structural components of roll-formed battery packs. Finally, suggestions and prospects for the development of this system are given. [ABSTRACT FROM AUTHOR]

By using the self-developed unmanned aerial vehicle (UAV) borne mini synthetic aperture radar (MiniSAR) system, all-directional echoes for multiple types of representative ground targets are collected and used for image processing by the Radar Detection and Imaging Techniques Research Group of Nanjing University of Aeronautics & Astronantics (NUAA). A proprietary SAR database for complex targets is constructed, based on which artificial-intelligence-inspired target recognition approaches are studied. To solve the challenging issue of SAR image defocus caused by unstable movement of the UAV platform and the limited accuracy provided by the accessory sensors, novel movement compensation and auto-focus processing methods are proposed. The impact of the image defocus on the classification accuracies provided by the neural networks is revealed, and the limited generalizability of the existing neural networks is demonstrated. Simulation results show that although the classic neural networks, such as AlexNet, ResNet-18, AConvNet, and VGG offer a near-100% accuracy for the MSTAR 10-target classification problem, the 9-class target classification accuracies provided by these networks for the MiniSAR dataset are all much lower than 90%. Since the experiment method employed in this paper closely resembles the practical application scenario, the proposed database will be of great reference value to the development of SAR target recognition algorithms for engineering applications. [ABSTRACT FROM AUTHOR]

A network system is composed of a couple of subsystems connected with mechanisms or communication. Such a system has a high probability of faults because of its complex structure and changeable coupling mechanisms. With the rapid development of artificial intelligence technology in recent years, network systems are threatened by physical faults and malicious decisions. This paper summarizes current research results on fault-tolerant control and fault-tolerant optimization. Then, following the development of the fault-tolerant game, the relevant research results are summarized from the game control to the fault-tolerant game for physical faults and malicious agents. Further, the applications of the game theory on unmanned aerial vehicle (UAV) swarms are summarized. Finally, several research directions that are worth investigating in the future are presented. This review could promote the development of fault-tolerant game in the field of aerospace. [ABSTRACT FROM AUTHOR]

Due to the irregular features of the airport pavement cracks with variable shapes，narrow widths， different lengths，and free⁃form spatial trends，the existing algorithms perform not well. To solve this problem，this paper constructs a neural network model based on deformable convolution and feature fusion （DFNet）. Firstly， the deformable convolution module is used to enhance the learning of fracture morphological characteristics by feature extraction network. Secondly，the multi⁃scale convolution module captures the global information of the fracture under different receptive fields. Finally，the feature fusion module is used to extract the characteristics of different levels of the fracture，through combining low⁃level and high⁃level features of cracks to achieve accurate segmentation of cracks on airport pavements. On the collected actual airport pavement crack data set，comparative experiments are carried out with other six existing algorithms. The proposed algorithm reaches 90.95% on the F1⁃Score of pixel⁃level segmentation， which is better than those of all other compared algorithms. The DFNet algorithm improves the ability of detecting cracks in airport pavements. Experimental results show that the proposed algorithm better meets the actual engineering requirements. [ABSTRACT FROM AUTHOR]