Dazi Li

Name

姓名

Dazi Li

李大字

Gender

性别

Female

女

College

学院

College of Information Science & Technology

信息科学与技术学院

Highest degree

最高学历

Ph.D,

工学博士

Professional Title

职称

Professor

教授

Discipline/Major

专业

Control Science and Engineering/Automation

控制科学与工程/自动化

Research Area/Direction

招生研究方向

Machine Learning and Artificial Intelligence, Advanced Process Control, Complex System Modeling And Optimization, Fractional Calculus System

机器学习与人工智能、先进控制、复杂系统建模与优化、分数阶系统

Email

邮箱

lidz@mail.buct.edu.cn

Research Topics（no more than 100 words）研究方向

 In modern process industries, the dynamic characteristics and complexity of processes are continuously increasing, posing challenges to model-based optimization control methods. In addressing the pressing issues within the field of process control, the applicant has developed a framework for reinforcement learning control that integrates both knowledge and data, leveraging the principles of dynamic programming theory.

1. A high-performance framework of inverse reinforcement learning with reward and policy optimization is proposed, addressing the challenging problem of reward design in reinforcement learning to provide theoretical and methodological support for engineering applications of reinforcement learning.

2. A complex process system graph deep reinforcement learning application framework is constructed based on a graph representation model of complex process systems and graph deep learning, achieving automated industrial knowledge extraction and reconstruction in the domain of complex process systems through collaborative driving of both prior knowledge and data.

3. A multi-objective decision & optimization method of deep reinforcement learning is proposed under safety constraint conditions, providing a novel solution for the intelligent management of complex process systems, with a focus on green, low-carbon, energy-efficient, and productivity-enhancing objectives.

Education Background 教育背景

1988.09-1992.07  Beijing University of Chemical Technology, Bachelor Degree

1992.09-1995.07  Beijing University of Chemical Technology, Master Degree

2000.10-2004.04  Kyushu University, Ph.D Degree

Work Experience 工作经历

1995.08-1997.08  Beijing University of Chemical Technology, Teaching Assistant

1997.09-2004.08  Beijing University of Chemical Technology, Lecture

2004.09-2011.11  Beijing University of Chemical Technology, Associate Professor

2011.12 -Present  Beijing University of Chemical Technology, Professor

2014.07 -Present  Beijing University of Chemical Technology, DoctoralSupervisor

Publications(no more than 10 representative publications) 发表文章

1. Tianheng Song, Dazi, Li*, and Xin Xu, Online Sparse Temporal Difference Learning based on Nested Optimization and Regularized Dual Averaging, IEEE Transactions on Systems, Man and Cybernetics: Systems, 2022, 52(4), 2042-2052.

2. Li Song, Dazi Li*, Xiao Wang, Xin Xu*, AdaBoost Maximum Entropy Deep Inverse Reinforcement Learning with Truncated Gradient, Information Science, 2022, 602, 328-350.

3. Li Song, Dazi Li*, Xin Xu*, Sparse Online Maximum Entropy Inverse Reinforcement Learning via Proximal Optimization and Truncated Gradient, Knowledge-Based Systems, 2022, 252, 109443.

4. Tianheng Song, Dazi Li*, Weiming Yang, Kotaro Hirasawa, Recursive Least-Squares Temporal Difference with Gradient Correction, IEEE Transactions on Cybernetics, 2021, 51(8), 4251-4264.

5. Luntong Li, Dazi Li*, Tianheng Song, Xin Xu, Actor-Critic Learning Control with Regularization and Feature Selection in Policy Gradient Estimation, IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(3), 1217-1226.

6. Dazi Li*, Wentao Gu, Tianheng Song, Multi-objective Reinforcement Learning in Process Control: A Goal-oriented Approach with Adaptive Thresholds, Journal of Process Control, 2023, 129: 103063.

7. Dazi Li*, JianxunLiu, XinMa, QibingJin, Stacked supervised auto-encoder with graph regularization for feature extraction and fault classification of chemical processes, Journal of Process Control, 2023, 127: 102999.

8. Jiahui Xu, Dazi Li*，Jinhui Zhang，Extended state observer based dynamic iterative learning for trajectory tracking control of a six-degrees-of-freedom manipulator，ISA Transactions，2023, 143:630-646.

9. Tianheng Song, Dazi Li*, Qibing Jin, Kotaro Hirasawa, Sparse Proximal Reinforcement Learning via Nested Optimization, IEEE Transactions on Systems, Man, and Cybernetics, 2020, 50(11), 4020-4032.

10.Luntong Li, Dazi Li*, Tianheng Song, Xin Xu, Actor-Critic Learning Control Based on l2-Regularized Temporal-Difference Prediction with Gradient Correction, IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(12), 5899-5909.