University of Electronic Science and Technology of China

About: University of Electronic Science and Technology of China is a education organization based out in Chengdu, China. It is known for research contribution in the topics: Antenna (radio) & Dielectric. The organization has 50594 authors who have published 58502 publications receiving 711188 citations. The organization is also known as: UESTC.

Boundary Vibration Control of Variable Length Crane Systems in Two-Dimensional Space With Output Constraints

Abstract: A variable length crane system under the external disturbances and constraints is studied in the two-dimensional space. The dynamical analysis of the cable system considers the variable length, variable tension, variable speed, and the coupled vibrations of the cable in longitudinal-transverse directions. Considering output constraint problems, boundary control algorithms with output signal barriers are designed and acted on the boundary of the cable to reduce the coupled vibrations of the flexible crane cable, and to ensure the stability of the system in theory. Effectiveness and performance of the proposed control schemes are depicted via several simulation examples.

Semi-supervised Medical Image Segmentation through Dual-task Consistency

Abstract: Deep learning-based semi-supervised learning (SSL) algorithms have led to promising results in medical images segmentation and can alleviate doctors' expensive annotations by leveraging unlabeled data. However, most of the existing SSL algorithms in literature tend to regularize the model training by perturbing networks and/or data. Observing that multi/dual-task learning attends to various levels of information which have inherent prediction perturbation, we ask the question in this work: can we explicitly build task-level regularization rather than implicitly constructing networks- and/or data-level perturbation-and-transformation for SSL? To answer this question, we propose a novel dual-task-consistency semi-supervised framework for the first time. Concretely, we use a dual-task deep network that jointly predicts a pixel-wise segmentation map and a geometry-aware level set representation of the target. The level set representation is converted to an approximated segmentation map through a differentiable task transform layer. Simultaneously, we introduce a dual-task consistency regularization between the level set-derived segmentation maps and directly predicted segmentation maps for both labeled and unlabeled data. Extensive experiments on two public datasets show that our method can largely improve the performance by incorporating the unlabeled data. Meanwhile, our framework outperforms the state-of-the-art semi-supervised medical image segmentation methods. Code is available at: this https URL

Backstepping Control of Electro-Hydraulic System Based on Extended-State-Observer With Plant Dynamics Largely Unknown

Abstract: In this paper, an output position feedback control of the electro-hydraulic system (EHS) is proposed based on an extended-state-observer (ESO) with backstepping. On the basis of the augmented state model of the EHS, the ESO is designed to handle the unknown load disturbance and uncertain nonlinearity. Then, an observer bandwidth constraint is derived to compromise between the dynamic performance and the maximal load capability of EHS. The effectiveness of the proposed control for the suppression of largely unknown disturbances has been demonstrated by comparative experimental study, which indicates the proposed approach can achieve better dynamic performance on the motion control of two-degree-of-freedom robotic arm.