About me

I am a control system researcher at Shanghai Nuclear Engineering Research and Design Institute (SNERDI). I received the Ph.D degress in Control Science and Engineering from Shanghai Jiao Tong University. I was a visiting scholar in University of Oxford when Pursuing Ph.D. I received the B.Eng. and M.S. Eng. degrees in Automation from North China Electric Power University in 2016 and 2019, respectively.

I am focusing on modeling, safety-critical and optimal control of the nuclear power engineering. Moreover, I dedicate to applying these techniques to Digital-Twin Systems for industry and industrial robotics in my free time.

What i'm doing

Working Partners

Resume

Education

  1. North China Electric Power University

    2012 — 2016

    Received a B.Eng degree in Measurement & Control Technology and Instrumentation.

  2. North China Electric Power University

    2016 — 2019

    Received an M.S.Eng degree in Pattern Recognition & Intelligent Systems.

  3. Shanghai Jiao Tong University

    2019 — 2024

    Received a Ph.D. degree in Control Science and Engineering.

Experience

  1. Control Systems Researcher (Shanghai Nuclear Engineering Research and Design Institute)

    2024.07 — Present

    1) Developing SimScape simulation models for micro-pipe reactor systems.
    2) Researching control theory for safe and stable reactivity in Boiling Water Reactors.

  2. Data Scientist Intern (Bosch, China)

    2023.03 — 2024.05

    1) Developed and deployed a virtual force sensor for the excavator based on a dynamic model.
    2) Developed a data-driven fault detection model for the CNC machining process.
    3) Achieved first place in Bosch’s internal ESP data-driven control competition.

  3. Safety-critical Control in Motion Planning (Oxford)

    2022.10 — 2023.02

    Designing a safety-critical control method is fundamental for robotic manipulators. By exploring the control invariance, we designed a CBF-based QP control method to guarantee the dynamics' safety intrinsically. We mainly focus on the following: 1) Controller construction method based on environment and dynamics; 2) Feasibility of the controller in a cluttered environment. 3) High computing time of the controller; Together, the online optimal control for safety-critical robotics is efficient.

  4. Intelligent Control System with Virtual-Physical Interaction for Robots (Tencent)

    2022.06 — 2022.09

    I worked with Robotics X to develop a digital-twin system for robotics, including wheeled and quadruped walking robots. The system aims to verify strategies and present a virtual-reality environment. I focused on 1) developing a cross-platform communication framework with low latency; 2) constructing robot models and control in Unreal Engine.

  5. Research and Application of Distributed Multi-Robot Digital Twin Platform

    2021.01 — 2023.01

    Led the design of the multi-robot testbed Robopheus, integrating virtual-physical modeling in a digital twin system. Robopheus bridges physical hardware and virtual simulations, offering scalable, interactive tests. It dynamically learns models from the physical environment and enhances real-time robot dynamics online.

    Omni-Directional Mobile Manipulator: Designed and implemented the robot with a stable structure, advanced control, and SLAM integration.
    Multi-Target Vision Positioning: Developed an autonomous camera system for real-time multi-target recognition using edge computing.
    Virtual Robot Platform: Built a virtual platform in Unreal Engine for synchronized robot modeling and control algorithm testing.
    Control Center Development: Developed multi-source perception fusion and cross-platform control algorithms.
    2D Motion Capture System: Created a low-cost 2D motion capture system with 100Hz tracking, 10ms delay, and 0.5mm accuracy.

  6. Low Cost Autopilot Field Vehicle

    2021.12 — 2022.02

    I designed an autopilot field vehicle with low-cost hardware which can autopilot to the desired position with obstacle avoidance. There are two visions of the system. 1) 8-bit MCU with GPS, IMU, and ultrasound detectors. The positional accuracy is improved by fusing information from GPS and IMU. The fusion algorithm is modified to adapt to the 8-bit MCU. The positional error is 2m, and the frequency is 20Hz. 2) 32-bit ARM Cortex-M3 with Dual-GPS, IMU, magnetic sensor, encoders, and ultrasound detectors. The positional error is 0.8m, and the frequency is 20Hz.

  7. Sintering Digital Twin System (Liugang)

    2019.12 — 2020.12

    Designed and developed the architecture of the sintered digital twin platform, aimed at providing process variable prediction, strategy optimization, and system verification. The platform utilizes microservices as the core foundation, with Docker technology for cross-platform model packaging and Harbor storage with Kubernetes (K8s) for efficient multi-model management.

    Sintering Quality Prediction Model: Developed around 80 lightweight, data-driven prediction models, each tailored for different functions. Over 200 microservices were created to work in conjunction with these models, enabling reliable prediction of various process variables and ensuring the platform's stable operation.
    Platform Deployment and Visualization: Successfully deployed the prediction models onto the digital twin platform and developed a front-end interface for real-time data visualization, enhancing the platform's usability and performance in industrial settings.
    Reinforcement Learning Control: Designed advanced reinforcement learning-based control methods to optimize blast furnace operations. These methods enabled state-of-the-art control performance by leveraging predictive models and data-driven insights for real-time decision-making and control.

  8. NOx prediction in coal-fired power plant(NCEPU)

    2017.01 — 2018.12

    The proposed data-driven NOx prediction method includes on-site data SCADA acquisition and processing, information entropy, and HITS algorithm for practical information data mining, designing LSSVM update mechanism, and prediction of NOx content. Control logic building and on-site DCS configuration and debugging, using data analysis results, design control logic, setting up system parameters, and completing the control system upgrade on the spot.

My skills

  • Optimal Control
    80%
  • Motion Plan
    80%
  • Stastical Learning
    70%
  • MATLAB
    80%
  • C++
    70%
  • Python
    60%

Publication

Videos

Safe Control For Manipulators

Optimal Motion Plan

Camera Sensing Model