Graduated from Zhejiang University of Technology with a bachelor's degree in Industrial Engineering, with formal training in system modeling and simulation, operations research, optimization algorithms, machine learning, lean production, mechanical design, and supply chain management. A solid methodological foundation has been developed through paper collaboration, competition projects, logistics planning, and industrial practice.
Current representative work focuses on multistage stochastic blending optimization for recycled copper alloys. The main research line centers on integrating numerical solution methods with heuristic algorithms to address practical optimization problems in manufacturing and process industries, with effectiveness assessed through system simulation, experimental analysis, and engineering constraints. The combination of algorithm design and simulation has supported a relatively complete workflow spanning problem formulation, solution validation, and result interpretation.
In addition, systematic familiarity has been established with the application of deep reinforcement learning, machine learning, and deep learning methods, together with sustained experience in factory investigations, layout planning, and production-system analysis.
Graduated from Zhejiang University of Technology with a bachelor's degree in Industrial Engineering and currently pursuing a master's degree in Industrial Engineering and Management. Research is oriented toward practical optimization problems in manufacturing and process industries, with emphasis on integrating numerical solution methods, heuristic algorithms, and deep reinforcement learning.
Representative work focuses on multistage stochastic blending optimization for recycled copper alloys, with validation supported by system simulation, experimental analysis, and engineering constraints. Sustained experience has also been developed in factory investigation, layout planning, production-system analysis, and research-oriented tool development.
Research Summary
The current research profile is positioned along the chain of algorithm design, industrial problem modeling, and simulation-based validation. The primary objective is to address optimization problems with real process constraints, multistage decision structures, and complex search spaces. Methodologically, emphasis is placed on combining numerical solution techniques, heuristic algorithms, and learning-based methods to improve solution quality, computational efficiency, and engineering applicability.
Existing work covers production scheduling, recycled-alloy blending optimization, environmental control in industrial sericulture, and optimization of assembly and suspension-chain systems, forming a comparatively complete workflow from problem abstraction and mathematical modeling to algorithm implementation, simulation experiments, and result interpretation.
The current target directions are as follows:
Industrial optimization methods that integrate numerical solution techniques with heuristic algorithms.
Applications of deep reinforcement learning to multistage decision, scheduling, and control problems.
Simulation-based validation, parameter analysis, and comparative evaluation of algorithmic solutions.
Optimization Algorithms
Particular emphasis is placed on numerical optimization, heuristic search, swarm intelligence, and hybrid optimization frameworks for complex industrial problems requiring feasible, stable, and efficient solution strategies.
Deep RL and MLDL
Systematic familiarity has been developed with machine learning, deep learning, and deep reinforcement learning, especially for discrete decision-making, hybrid action spaces, and engineering problems with explicit operational constraints.
Simulation-based Validation
Proficient in FlexSim, Simio, Anylogic, Matlab, and SPSS for system modeling, simulation experiments, comparative analysis, and the validation of algorithmic performance in engineering contexts.
The current research profile follows the chain of algorithm design, industrial problem modeling, and simulation-based validation, with particular attention to multistage decision problems, engineering constraints, and the practical applicability of optimization methods in real production settings.
Publications
Multistage Stochastic Blending of Recycled Copper Alloys with Endogenous
Stopping: A Hybrid DAH-DDPG and Chance-Constrained Programming Approach
Transfer-learning-based Strategy for Enhancing Prediction Accuracy and
Computational Efficiency of Nonlinear Mechanical Properties in Composite Materials
Cyber-Physical Scheduling System for Multiobjective Scheduling Optimization
of a Suspension Chain Workshop Using the Improved Non-Dominated Sorting
Genetic Algorithm II
Under submission to JCLP. Multistage Stochastic Blending of Recycled Copper Alloys with Endogenous Stopping: A Hybrid DAH-DDPG and Chance-Constrained Programming Approach. Hu JunHan, Wang Cheng. [Paper]
Under submission to CEA. Priority-guided Search Strategy and Cyber-Physical Energy System Design for Industrial Sericulture. Wen-Bin Zhao, Hu JunHan, Gao-An Zheng. [Paper]
Published. Transfer-learning-based Strategy for Enhancing Prediction Accuracy and Computational Efficiency of Nonlinear Mechanical Properties in Composite Materials. Composites Science and Technology, 2024, 246: 110388. Fourth author. [Paper]
Published. Virtual Simulation-Based Optimization for Assembly Flow Shop Scheduling Using Migratory Bird Algorithm. Biomimetics, 2024, 9(9): 571. [Paper]
Published. Cyber-Physical Scheduling System for Multiobjective Scheduling Optimization of a Suspension Chain Workshop Using the Improved Non-Dominated Sorting Genetic Algorithm II. Machines, 2024, 12(9): 666. [Paper]
Software Copyrights
Experimental Analysis System for Genetic Algorithms Based on Multiple Encoding Schemes V1.0
Zhejiang University of Technology · Industrial Engineering and Management (Master's Student)
Currently pursuing a degree in Industrial Engineering and Management. Current research focuses on practical optimization problems in manufacturing and process industries, with particular emphasis on integrating numerical solution methods with heuristic algorithms, applying deep reinforcement learning to multistage decision problems, and evaluating algorithms and alternative plans through system simulation.
Representative work centers on multistage stochastic blending optimization for recycled copper alloys, involving chance-constrained programming, a hybrid DAH-DDPG strategy, endogenous stopping, and solution as well as validation issues under complex engineering constraints.
In addition, current work is advancing a stochastic lead-time constrained planning model for tree-structured multi-level assembly systems. Starting from a simplified two-level assembly model, the framework is being extended to a K-stage tree-structured assembly setting, where raw-material lead-time uncertainty, interstage assembly timing constraints, holding costs for semi-finished and purchased components, and time-loss penalties are unified in the objective. The goal is to develop a solution approach from a multistage stochastic programming perspective.
2020.09 - 2024.07
Zhejiang University of Technology · Industrial Engineering (B.Eng.)
Major coursework included system modeling and simulation, operations research, optimization algorithms, machine learning, lean production, mechanical design, enterprise resource planning, automated warehousing design, Six Sigma management, quality management, and supply chain management.
2024.09 - Present Zhejiang University of Technology, Industrial Engineering and Management, Master's Student.
2020.09 - 2024.07 Zhejiang University of Technology, Industrial Engineering, B.Eng.
Project and Practice Experience
Mechanical Design and Embedded Development
Mechanical Design Competitions and Robotics Projects
Participated in four mechanical design competitions and robotics projects, with responsibilities covering structural design, model development, technical drawing, kinematic and mechanical verification, as well as selected work in embedded development, gait design, path-planning algorithms, and machine vision recognition.
Programming
GUI Development and Research-oriented Utility Tools
Participated in graduate and undergraduate development teams, with responsibility for GUI development and the integration of intelligent algorithm modules. In addition, utility programs such as algorithm-optimization visualization tools were developed for course and project needs. With the support of AI-assisted development, scripts and process-oriented utilities can be produced rapidly to facilitate research workflows. Most graduate course projects were presented in the form of software tools or HTML-based pages.
System Modeling and Simulation
Logistics Planning, Factory Investigation, Layout Planning, and Scheduling Optimization
Long-term involvement has been maintained in factory investigations, production-process analysis, and layout planning. FlexSim-based modeling and simulation, data analysis, and optimization algorithms were applied to logistics planning, course-design projects, and production-line scheduling studies. During industrial internship work, scheduling schemes based on simulation and algorithmic optimization were also proposed and evaluated.
Organization and Coordination
Competition Organization and Student Affairs
Served multiple times as team leader in competitions and previously held positions including deputy director of the student financial-aid association and department head in the student union of the School of Mechanical Engineering, with responsibilities covering the organization and coordination of student-aid and work-study activities involving approximately 200 participants.
Project and practice experience covers mechanical design competitions, GUI development and research-oriented utility tools, factory investigation, logistics and layout planning, production scheduling studies, and student-team organization, with long-term engagement in simulation-based analysis and optimization-oriented problem solving.
Selected Honors and Awards
[2025-09] National Scholarship.
[2023-09] National Second Prize, College Students' Mechanical Engineering Innovation and Creativity Competition, Industrial Engineering Track.
[2023-07] Outstanding Award, Excellent Course Design in Industrial Engineering.
[2023-04] Provincial Second Prize, College Students' Mechanical Innovation Design Competition.
[2022-06] University Third Prize, College Students' Mechanical Innovation Design Competition.
[2021-12] National Third Prize, College Students' Industrial Engineering and Lean Management Innovation Competition.
[2020-2024] National Encouragement Scholarship, awarded four times during undergraduate study.
Skills
Simulation and Analysis: Anylogic, Simio, FlexSim, Matlab, SPSS
A PDF version of this page can be generated directly from the browser print dialog.
For a clean result, use portrait orientation and disable browser headers and footers in the print settings before saving.
