公开(公告)号：US12204304B2

公开(公告)日：2025-01-21

申请号：US17724473

申请日：2022-04-19

Applicant: Tsinghua University

Inventor： Wenchuan Wu ,  Boming Zhang ,  Zihao Li ,  Hongbin Sun ,  Bin Wang ,  Qinglai Guo

IPC: G05B19/042

Abstract: A planning method for a power distribution automation system based on a reliability constraint is provided. The method includes: defining installation states of components and principles of a fault isolation, a load transfer and a fault recovery after a branch fault occurs; establishing a reliability evaluation optimization model for a power distribution network based on a mixed integer linear programming, the reliability evaluation optimization model comprising a target function and constraint conditions; solving the reliability evaluation optimization model to obtain an optimum planning scheme; and planning the power distribution automation system based on the optimum planning scheme.

公开(公告)号：US20250021014A1

公开(公告)日：2025-01-16

申请号：US18885038

申请日：2024-09-13

Applicant: Tsinghua University

Inventor： Zhen ZHANG ,  Yijie LIU ,  Juntian QU

IPC: G03F7/00 ,  G03F7/20

Abstract: The present application discloses a scanning electron microscopic direct-write lithography system based on a compliant nano servo motion system, which includes an electron chamber, an ion chamber, a specimen chamber and a control system, wherein the electron chamber includes an electron chamber housing, an electron gun, an anode, an electron beam blanker, an electromagnetic lens and an electron beam deflection coil, the ion chamber includes an ion chamber housing, an ion source, an ion beam-scanning deflection electrode and the like, the specimen chamber includes a specimen chamber housing, a secondary electron detector, a nanoscale-precision compliant servo motion stage system and the like; control system includes a computer, an electron beam scanning controller, an ion beam scanning controller and the like.

公开(公告)号：US12194936B2

公开(公告)日：2025-01-14

申请号：US17705355

申请日：2022-03-27

Applicant: TSINGHUA UNIVERSITY

Inventor： Bing-Bing Nie ,  Wen-Tao Chen ,  Qing-Fan Wang ,  Jiajie Shen ,  Quan Li ,  Shengbo Li ,  Qing Zhou

IPC: B60N2/02 ,  B60N2/01 ,  B60R16/023 ,  B60R16/037 ,  B60R21/0132 ,  B60R21/015 ,  B60R21/16 ,  B60R22/48 ,  B60W30/085 ,  B60W30/095 ,  G06N20/00 ,  B60R21/013

Abstract: Disclosed is a method for predicting collision severity, including: establishing a first learning model, and inputting vehicle data and collision accident scene feature data into the first learning model; obtaining a predicted collision acceleration curve outputted by the first learning model, the predicted collision acceleration curve being established based on a plane rectangular coordinate system; establishing a second learning model, and inputting the predicted collision acceleration curve, the occupant feature data and the restraint system feature data into the second learning model; obtaining a plurality of predicted collision kinematics and dynamics curves of human body parts outputted by the second learning model; generating a collision severity parameter according to the plurality of predicted collision kinematics and dynamics curves of the human body parts, the collision severity parameter being configured to evaluate the collision severity.

公开(公告)号：US12189118B2

公开(公告)日：2025-01-07

申请号：US17350217

申请日：2021-06-17

Applicant: Tsinghua University ,  HON HAI PRECISION INDUSTRY CO., LTD.

Inventor： Yi-Lin Tan ,  Jun Zhu ,  Guo-Fan Jin ,  Shou-Shan Fan

IPC: G02B27/00

Abstract: The present application relates to a method for designing a nonsymmetric freeform surface optical system, and the method including the following steps establishing an initial plane system. The initial plane system is consistent with the expected system structure, but there is no focal power in the initial plane system. The image plane tilt angle of the initial plane system is defined as θ. The point-by-point method is used to calculate the coordinates and normal vectors of the data points used to construct the freeform surface. The iterative optical system is obtained by iteration; and the iterative optical system is optimized.

公开(公告)号：US12188882B2

公开(公告)日：2025-01-07

申请号：US18052671

申请日：2022-11-04

Applicant: Nuctech Company Limited ,  Tsinghua University

Inventor： Zhiqiang Chen ,  Li Zhang ,  Yunda Sun ,  Zhenhua Zhao ,  Xin Jin ,  Le Shen ,  Wuyang Liang

IPC: G01N23/046 ,  G01N23/083 ,  G06T11/00

Abstract: The method includes: receiving an encoder signal and a ray machine output beam signal, and initially synchronizing the encoder signal and the ray machine output beam signal; recording coded value M of the encoder at moment tm, and coded value N of the encoder at moment tm+1, where M, N, and m are integers; determining that duration from the moment tm to the moment tm+1 is an actual output beam time interval T of the ray machine, when it is determined that a difference value between the coded value M and the coded value N satisfies preset value a, a being an integer; determining gap time TG in the actual output beam time interval T based on a preset output beam time interval TJ of the imaging system and the actual output beam time interval T; and controlling the ray machine not to emit beam within the gap time TG.

公开(公告)号：US12184530B2

公开(公告)日：2024-12-31

申请号：US17543726

申请日：2021-12-06

Applicant: Tsinghua University

Inventor： Ke Xu ,  Yangfei Guo ,  Xiaoliang Wang ,  Mingxing Liu

IPC: H04L45/02 ,  H04L41/12 ,  H04L41/14 ,  H04L45/00 ,  G06F17/18

Abstract: A method for selecting a recommended node in a behavior deviation model includes: determining a candidate path starting from a delegation node to a target node based on a preset network topology; determining candidate recommended nodes passing through each candidate path, and acquiring a first behavior deviation corresponding to the target node at each candidate node; reading a second behavior deviation of each candidate recommended node from a central node in the network topology; calculating an average deviation value for the target node based on second behavior deviations and first behavior deviations; determining a candidate path with the smallest average deviation value as a target candidate path; and in response to the average deviation value of the target candidate path being less than or equal to a preset warning value, determining the candidate recommended node on the target candidate path as a recommended node.

公开(公告)号：US12182272B2

公开(公告)日：2024-12-31

申请号：US17523474

申请日：2021-11-10

Applicant: Tsinghua University

Inventor： Ke Xu ,  Yi Zhao ,  Su Yao ,  Ziwei Li

IPC: G06F21/57 ,  G06F21/54 ,  G06N3/12

Abstract: A method and an apparatus for actively defending against backdoor attacks under an edge computing scenario. The method includes: generating an initial optional operation set based on optional operations configured to enhance a model generalization ability, and constructing a configuration parameter set for each operation in the set; selecting a first subset with a curve between configuration parameters and model accuracies of the operation presenting a monotonically decreasing concave function characteristic; selecting a second subset with a curve of the operation between configuration parameters and probabilities that a model is successfully attacked by the backdoor attack presenting a monotonically decreasing convex function characteristic; constructing a mutation characteristic set for each operation in an intersection of the first and second subsets; and for each operation in the intersection, determining a final parameter setting value of the operation based on the mutation characteristic set, to actively defend against possible backdoor attacks.

公开(公告)号：US20240428064A1

公开(公告)日：2024-12-26

申请号：US18749238

申请日：2024-06-20

Applicant: TSINGHUA UNIVERSITY

Inventor： Lu FANG ,  Yuan CHENG

IPC: G06N3/067 ,  G06N3/0464 ,  G06N3/084

Abstract: The present disclosure relates to a system and an apparatus for an intelligent photonic computing lifelong learning architecture. The system includes: a multi-spectrum representation layer configured to transfer originally input electronic signals including multiple tasks into coherent light with different wavelengths by multi-spectrum representations; a lifelong learning optical neural network layer including cascaded sparse optical convolutional layers in a Fourier plane of an optical system, in which final spatial optical signals are output through the lifelong learning optical neural network layer by performing multi-task step-by-step training of the lifelong learning optical neural network layer on the coherent light with different wavelengths input into the cascaded sparse optical convolutional layers; and an electronic network read-out layer configured to recognize final optical output data obtained by detecting the final spatial optical signals, to obtain multi-task recognition results.

公开(公告)号：US12174083B2

公开(公告)日：2024-12-24

申请号：US17812169

申请日：2022-07-12

Applicant: Tsinghua University

Inventor： Fei Guo ,  Yijie Huang ,  Chong Xiang ,  Ganlin Cheng ,  Shengshan Chen ,  Xiaohong Jia ,  Yuming Wang

IPC: G01M13/005 ,  G01M3/04

Abstract: An equipment for sealing-performance test includes a housing, a fixed mechanism and a detection part; the housing is configured to accommodate the fixed mechanism, and an abutting part is formed in the housing and is configured to abut against an outer side of a sealing ring; the fixed mechanism includes a central rod, a plurality of fixed blocks and a driving assembly, the central rod extends along a direction parallel to the axial direction of the central rod, the plurality of fixed blocks are evenly disposed along a circumferential direction of the central rod, and the driving assembly is configured to drive the plurality of fixed blocks to move along a radial direction of the central rod; a test cavity and a detection cavity are formed in the housing, the test cavity is filled with a test fluid, and is separated from the detection cavity by the sealing ring.

公开(公告)号：US20240422445A1

公开(公告)日：2024-12-19

申请号：US18460997

申请日：2023-09-05

Applicant: Tsinghua University

Inventor： Lu FANG ,  Tao YU

IPC: H04N23/957 ,  H04N23/661 ,  H04N23/90

Abstract: A system for intelligent sensing and computing of an immersive light field includes a mobile platform, a support, an acquisition array, a control system and a computing system. The control system and the acquisition array are fixed on the support that is in form of hemisphere. The support changes a pose through the mobile platform. The acquisition array includes acquisition cameras of multiple views that are uniformly distributed and fixed on the support, and lenses of the acquisition cameras point to outside from a sphere center and are configured to acquire video images at a plurality of pitch angles. The control system is connected to the acquisition array and configured to transmit the video images to a control device for data storage, and the computing system is configured to acquire the video images in the control device and generate an immersive light field video based on the video images.