Patents by Inventor Xiaokang Lin

Xiaokang Lin 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).

  • Publication number: 20240036080
    Abstract: Disclosed are an analog quantity acquisition method and apparatus. An acquisition circuit with a zero flux current transformer is first used to acquire a current signal, where the acquisition circuit with the zero flux current transformer includes the zero flux current transformer, a compensating winding, and a dynamic detection unit, and the compensating winding generates a reverse excitation potential to counteract an excitation current and eliminate impacts of a ratio error and a phase angle error on accuracy. A multi-segment amplification circuit is used to perform segmented amplification on different ranges of the current signal, and full-range current acquisition is achieved by using different amplification circuits. An analog-to-digital converter chip is used to convert an amplified current signal into a digital signal. The acquisition circuit with the zero flux current transformer is used to eliminate the impacts of the ratio error and the phase angle error on the measurement accuracy.
    Type: Application
    Filed: September 4, 2023
    Publication date: February 1, 2024
    Inventors: Zhu Liu, Wenjing Li, Yunpeng Li, Yonggui Wang, Chuanjian Cui, Lvchao Huang, Xueyu Han, Jinguo Fang, Xiao Feng, Xiaokang Lin, Yuan Gao, Shunhui Luo, Shuying Cheng, Tengfei Dong, Chao Zhan, Afeng Tan
  • Publication number: 20240030705
    Abstract: The present invention provides an interpretable power load prediction method, system and terminal machine, relating to the field of power load prediction. The method comprises: initializing three factors—seasonal factor, trend factor, and smoothing factor, denoted as S1, T1, and I1 respectively; calculating states of the three factors for time t+1 in a current DeepES unit; outputting the three factors St+1, Tt+1, and It+1 to a next DeepES unit; repeating until a n-th DeepES unit completes its operation; calculating a predicted value Y based on the three factors that are outputted from a final DeepES unit. In power load prediction, constructing an interpretable prediction model enables users to understand the inference process of the model, therefore helps enhance the credibility of the model.
    Type: Application
    Filed: September 28, 2023
    Publication date: January 25, 2024
    Inventors: Qiang Li, Zhu Liu, Wenjing Li, Liyuan Gao, Yumin Liu, Feihu Huang, Xuxin Yang, Shilei Dong, Tianyang Li, Honglei Zhao, Meng Ming, Zhongyu Shang, Chunyang Li, Mingtao Cui, Peiyao Zhang, Hongyue Ma, Bin Dai, Dashuai Tan, Xiao Feng, Xiaokang Lin