Patents by Inventor Zitong XU

Zitong XU has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Preparation method of polymer-derived high-temperature ceramic film sensor
    Patent number: 12209057
    Abstract: A preparation method of a polymer-derived high-temperature ceramic thin film sensor is provided. Specifically, a sensitive layer precursor layer is prepared by spraying a sensitive layer precursor liquid on an alumina substrate, and the sensitive layer precursor liquid is obtained by mixing precursor liquid with conductive powder. A protective layer precursor liquid is prepared by spraying protective layer precursor liquid on the sensitive layer precursor layer, and the protective layer precursor liquid is obtained by mixing TiB2 nano-powder, insulating powder and the precursor liquid. The protective layer precursor layer, a solder and the sensitive layer precursor layer are simultaneously pyrolyzed by a one-time pyrolysis process, and thus a protective layer, the solder joints and the sensitive layer are obtained simultaneously. Thus, there is no need to pyrolyze the sensitive layer first, saving the time for pyrolyzing the sensitive layer.
    Type: Grant
    Filed: August 20, 2024
    Date of Patent: January 28, 2025
    Assignee: Lingnan Normal University
    Inventors: Zaifu Cui, Zhenguo Lu, Liwen Huang, Zhonghai Wang, Zitong Xu, Wenjin Duan, Bohuai Gou, Dingyun Mao, Xiaojun Chen, Xin Li, Guangzhou Sui
  • PREPARATION METHOD OF POLYMER-DERIVED HIGH-TEMPERATURE CERAMIC FILM SENSOR
    Publication number: 20250019310
    Abstract: A preparation method of a polymer-derived high-temperature ceramic thin film sensor is provided. Specifically, a sensitive layer precursor layer is prepared by spraying a sensitive layer precursor liquid on an alumina substrate, and the sensitive layer precursor liquid is obtained by mixing precursor liquid with conductive powder. A protective layer precursor liquid is prepared by spraying protective layer precursor liquid on the sensitive layer precursor layer, and the protective layer precursor liquid is obtained by mixing TiB2 nano-powder, insulating powder and the precursor liquid. The protective layer precursor layer, a solder and the sensitive layer precursor layer are simultaneously pyrolyzed by a one-time pyrolysis process, and thus a protective layer, the solder joints and the sensitive layer are obtained simultaneously. Thus, there is no need to pyrolyze the sensitive layer first, saving the time for pyrolyzing the sensitive layer.
    Type: Application
    Filed: August 20, 2024
    Publication date: January 16, 2025
    Inventors: Zaifu Cui, Zhenguo Lu, Liwen Huang, Zhonghai Wang, Zitong Xu, Wenjin Duan, Bohuai Gou, Dingyun Mao, Xiaojun Chen, Xin Li, Guangzhou Sui
  • Building a unified machine learning (ML)/ artificial intelligence (AI) acceleration framework across heterogeneous AI accelerators
    Patent number: 12175223
    Abstract: Disclosed is a system for converting a high-level runtime model to a low-level runtime model where the high-level runtime model runs on a client computer system, and the low-level runtime model runs on a server computer system. The server system has installed thereon a pool of hardware accelerators, and the low-level runtime model is targeted to the pool of accelerators. Outputs of the low-level runtime model are returned to the high-level runtime model as if the high-level runtime model computed the outputs.
    Type: Grant
    Filed: February 18, 2022
    Date of Patent: December 24, 2024
    Assignee: VMware LLC
    Inventors: Tiejun Chen, Gavin Lu, Yongtao Huang, Zitong Xu
  • BUILDING A UNIFIED MACHINE LEARNING (ML)/ ARTIFICIAL INTELLIGENCE (AI) ACCELERATION FRAMEWORK ACROSS HETEROGENEOUS AI ACCELERATORS
    Publication number: 20230221932
    Abstract: Disclosed is a system for converting a high-level runtime model to a low-level runtime model where the high-level runtime model runs on a client computer system, and the low-level runtime model runs on a server computer system. The server system has installed thereon a pool of hardware accelerators, and the low-level runtime model is targeted to the pool of accelerators. Outputs of the low-level runtime model are returned to the high-level runtime model as if the high-level runtime model computed the outputs.
    Type: Application
    Filed: February 18, 2022
    Publication date: July 13, 2023
    Inventors: Tiejun CHEN, Gavin LU, Yongtao HUANG, Zitong XU