公开(公告)号：US12166346B1

公开(公告)日：2024-12-10

申请号：US18650125

申请日：2024-04-30

Applicant: Zhejiang University ,  Hainan Research Institute of Zhejiang University

Inventor： Donglian Qi ,  Xueqi Wang ,  Yunfeng Yan ,  Guangxin Zhi ,  Dawang Fu

IPC: H02J3/00 ,  G01R23/04 ,  G01R31/08 ,  H02J3/38

Abstract: A fully distributed island micro-grid attack elasticity control system and method are provided. The method includes following specific steps: collecting basic information of a local AC micro-grid bus of a distributed power generation unit and basic information of a neighbor distributed power generation unit connected through a directed communication topology; predicting, based on a dynamic equation of the distributed power generation unit, a sequence of states thereof within a set period of time, namely, the predicted sequence of states; judging whether a system is under attack according to a comparison result of the predicted sequence of states and a real-time state sampling value of a micro-grid, to obtain a sequence of optimal auxiliary control inputs ui*; and calculating an optimal angular frequency reference value ωi* at the next time point according to the sequence of optimal auxiliary control inputs ui*.

公开(公告)号：US12189766B1

公开(公告)日：2025-01-07

申请号：US18800166

申请日：2024-08-12

Applicant: Hainan Research Institute of Zhejiang University ,  Zhejiang University

Inventor： Yulin Chen ,  Donglian Qi ,  Xing Huang ,  Yunfeng Yan ,  Shenjun Weng ,  Xianbo Wang

IPC: H04L29/06 ,  G06F21/55 ,  H02J3/00

Abstract: A microgrid self-triggering control method and system for resisting FDI attacks is provided. The method includes the following steps: S1: adopting primary control based on droop control for a microgrid; S2: designing a secondary control strategy of the microgrid, where the secondary control strategy includes frequency recovery and fair distribution of active power; and S3: designing a microgrid distributed self-triggering control method of a hash encryption method after considering the condition that the FDI attacks are injected into a secondary control communication link, so as to resist false malicious data in the microgrid and achieve secondary control. According to the microgrid self-triggering control method and system, a distributed secondary control target of the microgrid is achieved even under the FDI attacks, the injected malicious data can be quickly detected and eliminated, and the distributed secondary control communication network of the microgrid can be protected.

公开(公告)号：US12125214B2

公开(公告)日：2024-10-22

申请号：US17749179

申请日：2022-05-20

Applicant: Zhejiang University

Inventor： Yunfeng Yan ,  Donglian Qi ,  Meilin Chen

IPC: G06T7/194 ,  G06T5/77

CPC classification number: G06T7/194 ,  G06T5/77 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20221

Abstract: A method for segmenting a power line image in real time based on self-supervised learning includes: inputting an input power line sample image and power line sample image mask set for the same batch of images into a region growing algorithm to obtain a single power line sub-image and single power line mask set; randomly extracting at least one single power line image pair for combination, and combining the single power line image pair with a random background picture to generate a power line random background fusion image and power line random background mask set; and carrying out random non-repetitive region growing to obtain image inpainting regions, forming a segmentation mask with the image inpainting regions, obtaining power line segmentation images through an image inpainting algorithm, inputting the power line segmentation images into a power line real-time segmentation network for training, and carrying out predicted segmentation.

公开(公告)号：US12131484B1

公开(公告)日：2024-10-29

申请号：US18732676

申请日：2024-06-04

Applicant: Zhejiang University

Inventor： Yunfeng Yan ,  Haoyuan Jin ,  Donglian Qi ,  Qi Li ,  Rui Han ,  Bingxiao Mei ,  Zezhou Wang ,  Gang Chen

IPC: G06T7/20 ,  G06T5/20 ,  G06T7/11 ,  G06V10/44 ,  G06V10/80

CPC classification number: G06T7/20 ,  G06T5/20 ,  G06T7/11 ,  G06V10/44 ,  G06V10/806 ,  G06V2201/07

Abstract: A multi-object tracking method based on authenticity hierarchizing and occlusion recovery relates to the technical field of multi-object tracking for security management and control of complex scenes. The method includes the following steps: image acquisition, object detection, authenticity hierarchizing, hierarchical association and outputting tracks. The multi-object tracking method is helpful to solve the long-term puzzling occlusion problem in the field of multi-object tracking, the constructed new algorithm framework can achieve an advanced tracking performance, improve the adaptability of the method to complex environments, and adapt to more difficult video surveillance security control tasks.