Liao Zhengjingxuan is a 2023-level master's student in Mechanical Engineering at the Intelligent Maintenance and Additive Manufacturing Technology Research Team (IMAM Team), College of Engineering. Under the meticulous supervision of Professor Wang Fengtao, he has published/accepted 5 academic papers, including 1 Chinese Academy of Sciences Category 2 Top paper, 1 Chinese Academy of Sciences Category 1 Top paper, and 1 Peking University Core/EI paper. He has filed 1 national invention patent application and participated in 3 National Natural Science Foundation projects and 3 provincial research projects. Liao Zhengjingxuan has been awarded a scholarship from the China Scholarship Council (CSC) for the High-Level University Graduate Program and will pursue his Ph.D. at the University of Sydney.
In terms of academic performance and comprehensive development, Liao Zhengjingxuan has maintained consistently outstanding results. His master's GPA is 4.08/5.0, ranking 2nd out of 88 students in his major. He has twice received the Shantou University First-Class Graduate Academic Scholarship. He has won the Second Prize and Third Prize of the Guangdong Provincial China Robot and Artificial Intelligence Competition and is a member of the Chinese Society for Vibration Engineering. In addition to his own research, he has served as a peer reviewer for SCI journals including Mechanical Systems and Signal Processing, Journal of Materials Processing Technology, Journal of Manufacturing Processes, Measurement, and Optics and Laser Technology, continuously enhancing his literature evaluation skills, academic integrity awareness, and international academic communication capabilities through rigorous research training.
As a member of the IMAM Team, Liao Zhengjingxuan has long been deeply engaged in experimental work, undertaking substantial foundational and critical research tasks. From experimental design, specimen preparation, multimodal in-situ monitoring, data acquisition, image processing, model construction, and paper writing, he has mastered laser wire/powder directed energy deposition (DED) additive manufacturing, modeling, slicing, and path planning. He is capable of comprehensively utilizing monitoring methods including infrared thermography, high-speed cameras, acoustic emission, coaxial CMOS, and pyrometers for additive manufacturing process condition analysis. He independently completed the fabrication and in-situ monitoring of over 600 deposited specimens including single tracks, thin walls, and bulk samples, establishing an experimental dataset covering material systems such as In718 wire, 316L wire, 316L powder, TC4 powder, and TB6 powder, laying a solid foundation for subsequent quality prediction and mechanism analysis.
As the person in charge of the laboratory's laser scanning confocal microscope (LSCM), he has completed over 70 testing tasks and more than 350 sample measurements since April 2025, serving the research group as well as teams within and outside the university. The testing content covers three-dimensional surface morphology, geometric dimensions, flatness, roughness, microstructure, and wear behavior. His long-term LSCM testing experience has cultivated in him a more rigorous scientific mindset: reliable conclusions come not only from model calculations but also from repeated calibration among sample preparation, testing parameters, data screening, and mechanistic judgment. It is through this process that he has gradually developed the ability to analyze problems by establishing connections from manufacturing processes to in-situ monitoring to microstructure and performance.
Meanwhile, Liao Zhengjingxuan not only conducts DED research but has also mastered the operation of the EP-M150 laser powder bed fusion (LPBF) equipment, capable of performing EP-Hatch preprocessing, in-chamber oxygen concentration monitoring, and equipment calibration. He has successfully fabricated complex metal components including porous structures and semi-open impellers. He also possesses experimental capabilities in metallographic sample preparation, SEM microstructure analysis, and EDS elemental characterization, enabling him to conduct a relatively complete research loop around "process — data — structure — performance."
Reflecting on his master's research experience, Liao Zhengjingxuan believes that the greatest gain is not any single achievement but the gradual establishment of a research methodology for addressing complex engineering problems: identifying issues from experimental phenomena, extracting patterns from monitoring data, verifying mechanisms through microstructural characterization, and synthesizing discrete experimental results into interpretable, reproducible, and generalizable academic contributions. Experimental failures, anomalies in data, and repeated refinements during paper revisions have all become crucial components of his research competency development.
Looking ahead, Liao Zhengjingxuan expresses his commitment to maintaining reverence for experimental details, persistent inquiry into scientific questions, and close attention to engineering applications. He will carry the rigorous work ethic, research resilience, and problem-awareness cultivated at Shantou University to his new platform, continuing his journey on a broader academic stage.
Intelligent Maintenance and Additive Manufacturing Technology Research Team (IMAM Team), Shantou University
The IMAM Team focuses on the national strategy of "AI + Manufacturing," deeply integrating cutting-edge technologies including multimodal large models, generative AI, digital twins, and physics-informed neural networks. The team conducts systematic research across four major directions: intelligent maintenance and health management of high-end equipment, intelligent monitoring and quality control of additive manufacturing processes, laser additive remanufacturing processes and performance evaluation, and multi-scale forming mechanisms and defect control. The team focuses on breakthroughs in key technologies including multimodal large model-driven equipment fault diagnosis and remaining useful life prediction, retrieval-augmented generation and multimodal perception fusion for real-time defect identification in additive manufacturing, AI-enabled synergistic evaluation of remanufacturing process-microstructure-performance, and graph neural networks with physics-constrained deep learning for multi-physics coupled defect suppression. The team further explores industrial multimodal intelligent agent systems for equipment-process synergy, building a full-chain intelligent technology system from manufacturing process monitoring to service health management, providing core support for the green, highly reliable, and intelligent development of high-end equipment in China.
The team is led by Professor Wang Fengtao and currently comprises 10 core researchers, including 2 professors, 3 associate professors, and 5 lecturers, with over 50 master's and doctoral students. In recent years, the team has undertaken dozens of research projects including the National Natural Science Foundation, Guangdong Provincial Natural Science Foundation, and industry collaborative research projects. The team has published over 100 high-level academic papers in authoritative domestic and international journals including Mechanical Systems and Signal Processing, Reliability Engineering & System Safety, Journal of Manufacturing Processes, and Journal of Mechanical Engineering, and has been granted more than 50 invention patents.
The team is committed to establishing itself as an important research base addressing major national strategic needs and the industrial development requirements of the eastern Guangdong region. Focusing on key common technological issues and frontier scientific problems in modern industries, strategic emerging industries, and the fields of health and medical devices, the team provides foundational, strategic, and forward-looking knowledge reserves, technical support, and talent development for the transformation, upgrading, and long-term development of local high-end equipment, new energy (offshore wind power), new materials, high-performance medical devices, and traditional characteristic industries (textile and apparel, creative toys).
