1. Personal Information
LI Weiye: Doctor of Engineering, Tenure-Track Lecturer at Dongguan University of Technology, and a researcher in the field of Mechanical Engineering. He focuses on research directions including intelligent condition monitoring of equipment, tool wear prediction, process parameter optimization, deep learning, and reinforcement learning. Equipped with solid professional and technical capabilities, he has participated in 3 projects of various types such as the National Key R&D Program and Provincial Key R&D Program, published 8 high-level papers, and obtained 5 authorized invention patents. He possesses a strong sense of responsibility, excellent team collaboration skills, and the ability to implement engineering applications.
2.Education
September 2014 - June 2018, Hefei University of Technology, Major in Mechanical Design, Manufacturing and Automation, Bachelor's Degree
September 2018 - June 2020, Huazhong University of Science and Technology, Major in Mechanical Engineering, Master's Degree
September 2020 - October 2025, Huazhong University of Science and Technology, Major in Mechanical Engineering, Doctoral Degree
3.Work Experience
2025-10至今, 东莞理工学院, 准长聘讲师；
4. Research Interests
Intelligent condition monitoring of equipment, tool wear prediction, process parameter optimization, deep learning, and reinforcement learning
5.Research Projects
1.National Key R&D Program of China Sub-project: "Research on Intelligent Process Optimization Method Combining Data-Driven and Knowledge-Guided Approaches" (Nov 2022 – Oct 2025,), Key Participant (Under Review/Closure): Responsible for establishing a process parameter optimization model integrating mechanistic models and data-driven approaches, research on simulation data generation methods, and research on intelligent process optimization methods based on reinforcement learning.
2.Hubei Provincial Key R&D Program: "Research and Application of Dynamic Collaborative Operation Optimization Technology for Whole-Process Multi-Process Manufacturing" (Sep 2020 – Jul 2022), Key Participant (Completed): Responsible for machining condition monitoring and research on quality prediction models based on big data.
3.Ministry of Industry and Information Technology (MIIT) Deck Machinery Quality Brand Special Project: "Research on Reliability Design and Verification Technology - Special Topic IV: Reliability Database for Deck Machinery and Its Key Components" (Jan 2017 – Dec 2020), Key Participant (Completed): Responsible for vibration characteristic analysis of electric deep-well pumps, research on typical fault diagnosis methods, and vibration anomaly fault analysis of a 1200-ton crane.
6.Research Achievements
论文：
[1] Li W, Hao C, He S, et al. Multi-agent reinforcement learning method for cutting parameters optimization based on simulation and experiment dual drive environment[J]. Mechanical System and Signal Processing, 2024, 216(000):25. (SCI一区，IF= 8.9).
[2] Li W, He S, Mao X, et al. Multi-agent evolution reinforcement learning method for machining parameters optimization based on bootstrap aggregating graph attention network simulated environment[J]. Journal of Manufacturing Systems, 2023. (SCI一区，IF= 14.2).
[3] Li W, Li B, He S, et al. A novel milling parameter optimization method based on improved deep reinforcement learning considering machining cost[J]. Journal of Manufacturing Processes, 2022, 84: 1362-1375. (SCI一区，IF= 6.8).
[4] Qiu C, Liang Q, Yin L*, Li W*, et al. Graph-based meta learning to predict tool tip dynamics of multiple machine tools with few labeled data[J]. Mechanical Systems and Signal Processing, 2025, 237(000). (SCI一区，IF= 8.9).
[5] Hao C, Wang Z, Mao X, He S*, Li B, Liu H, Peng F, Li W*. A novel and scalable multimodal large language model architecture Tool-MMGPT for future tool wear prediction in titanium alloy high-speed milling processes[J].Computers in Industry, 2025, 169. (SCI一区，IF= 9.1).
[6] Hao C, Li W, Mao X, et al. An intelligent prediction paradigm for milling tool parameters design based on multi-task tabular data deep transfer learning integrating physical knowledge[J]. Journal of Manufacturing Processes, 2025, 134:998-1020. (SCI一区，IF= 6.8).
[7] Li W, Yu J, Hao C. Fault Diagnosis Method of Electric Deep Well Pump Based on CEEMDAN-CNN[C]. Proceedings of the 3rd International Conference on Information Technologies and Electrical Engineering, 2020. (EI).
[8] Guo Q, Hao C, Xie L, Li W. An Optimization Method of Deep Well Pump Sensor Configuration Based on Mutual Information of Transient Response Simulation Signals [C]. Proceedings of the 3rd International Conference on Information Technologies and Electrical Engineering, 2020. (EI).
专利：
1.Li Bin; Li Weiye; He Songping, et al. A Machining Parameter Optimization Method Based on Multi-Agent Evolutionary Reinforcement Learning. (Patent No.: ZL 2021 1 1218896.1)
2.He Songping; Zhao Zunyuan; Qiu Chaochao; Zhou Xinzhao; Li Bin; Li Weiye, et al. A Signal Labeling Method and System for Variable-Parameter Milling Process Based on Deep Learning. (Patent No.: ZL 2021 1 0285492.3)
3.Li Bin; Li Weiye; He Songping, et al. A Milling Parameter Optimization Method Based on Deep Reinforcement Learning. (Patent No.: ZL 2021 1 1131299.0)
4.Qiu Chaochao; Li Weiye; Zhou Xinzhao, et al. A Machine Tool Tool Tip Dynamic Characteristic Prediction Method Based on Improved Graph Convolutional Network. (Patent No.: ZL 2021 1 1396317.8)
5.Wang Daoming; Yin Yilin; Yang Xici; Zi Bin; Li Weiye, et al. A Magnetorheological Force Feedback Lower Limb Active-Passive Rehabilitation Training Device. (Patent No.: ZL 2018 1 0514239.9)
7.Contact Information
Office Address: International Innovation District, Dongguan University of Technology, Songshan Lake, Dongguan City, Guangdong Province, China.
Email:liweiye@dgut.edu.cn
