Roll forming has been widely used to manufacture constant cross-section products because of high quality, efficiency and low cost. It is quite epidemic in producing automobile parts made of advanced high strength steels (AHSS) nowadays. However, with the development of the vehicle industry and diversity of the products, variable cross-section profiles have attracted more and more attention. The traditional roll forming technique is difficult to meet the requirements. Chain-die forming which was introduced in recent years makes it possible. Chain-die forming is an extension of roll forming and its key characteristic is enlarging the rotation radii of the moulds, by which the deformation zone is extended. The study focused on the finite element simulations of Chain-die forming U profiles with variable cross-section, including variable width and height. The feasibility of Chain-die forming producing variable cross-section products was verified by the perfect simulation results. The advantage of Chain-die forming was that there was no need to design the intermediate moulds except the finished-profile ones, which reduced the mould quantity immensely. Then the cost was lower.
Efficient drivable region segmentation is a critical for greenhouse robot navigation. State-of-the-art deep learning based road segmentation methods rely largely on labeled datasets to deal with the complexity of unstructured facility agriculture environment. However, the scarcity of annotated datasets limits the model performance. To break the bottleneck, this paper proposes a semi-supervised domain adaptive learning method for unstructured road semantic segmentation. Firstly, we establish a training framework for segmentation models through the transfer learning approach from a synthetic road dataset to an unstructured road dataset. Secondly, we determine the optimal pre-training strategy for solving the greenhouse road segmentation problem. Finally, for the long-tailed distribution of image data in the process of drivable area segmentation, we optimize the loss function to obtain an effective segmentation model for greenhouse robot navigation. For unstructured facility farming scenarios, we created an unstructured road dataset with annotation. Experiments show that, with a small number of labeled data, the road mIoU reaches 98.6%, which is about 10% greater than the existing unstructured road segmentation models to deal with ambiguous boundaries, complex obstacles, and shadow interference. It shows that the proposed method is feasible to leverage the successful existing city self-driving models and datasets to enrich and improve the road segmentation under agricultural scenarios.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.