Feiyan Zhou 周菲嫣

Northeastern University

MS in Khoury College of Computer Science

Email: zhoufeiyn AT gmail DOT com

    

Biography

I am a MSCS student at Northeastern University(2025.1-now). Previously, I was a senior research engineer (2020-2024) in China Electric Power Research Institute(CEPRI).

I obtained my bachelor and master degree from Electrical Engineering Department, Xi'an Jiaotong University.

Projects

  • Learning to Play: Game Generation Model with Action and Memory
  • Design a generative framework combining a VAE encoder–decoder with a Diffusion Forcing DiT architecture enhanced by recurrent-style hidden states, achieving temporally and interactively consistent game play video frame generation.
  • Interactive SQL Training and Assessment System based on Large Language Models
  • Developed a full-stack web platform for interactive SQL learning using Django and MySQL, enabling real-time data retrieval and AI-generated SQL exercises through LLM API integration and prompt engineering, and deployed the system on GCP for remote access.
  • Dynamic Simulation Systems for Urban Intelligent Distribution Power Network
  • Constructed a small smart power distribution substation dynamic simulation system,combining an authentic physical frame with simulated digital network by employing topology recognition and plug-and-play self-registration methods. The entire system can be monitored and maintained automatically by one single diagram from a cloud-based platform.
  • Automatic Detection Technology for Power Distribution Terminal Unit
  • Based on transient high-power sources and integrated RLC devices, this platform constructed nearly a hundred standardized testing cases, including test scenarios such as communication failure and data acquisition,realizing the dynamic simulation of real power distribution main stations, transmission lines, electrical loads, interference factors, and measuring devices.
    3 industry-level awards (Top-2 level award in China)
  • Fast distributed Feeder Automation fault handling strategies in power distribution network
  • As a core component of the distribution automation system, feeder automation(FA) plays a crucial role in quickly isolating faults and restoring power supply to non-faulty areas, thereby enhancing the reliability of power supply.
  • Overheating Defect Identification in Power Transmission Lines based on Deep Learning
  • This project proposes a three-stage cascaded DL detection method: cropping component image patch from whole image, segmenting component region in component image patch and locating overheating defect in component region, which removes the interference background step by step and finally realizes the heating diagnosis of insulator and drainage plate in the transmission line.
    3rd Price in 6th China State Grid Corporation’s Youth Innovation and Creativity Competition
  • Lightweight Cooling Tower Water Recovery Device Based on Air Corona Ion Wind
  • Designed an ultra-light plasma water collection electrode by combining the advantage of air plasma ion wind generation and conductive properties of the adhered water film, which can reduce the comprehensive water consumption rate of thermal power plants by more than 10%.
    1st Price in National University Student Social Practice and Science Contest on Energy Saving & Emission Reduction in 2016 (National level award, top 0.05% of 2839 projects from 300 universities in China)

    Publications (show selected / show all)

    Honors

    Academic Service


    © Feiyan Zhou | Last update: April 2024