Tianming Xie is a Lecturer at the School of Artificial Intelligence, Shenzhen University of Information Technology (SUIT). He entered Hefei University of Technology (HFUT) in 2015 and was admitted in 2019, through recommendation without entrance examination, to the master's program in Management Science and Engineering at the School of Management, HFUT — a national "Double First-Class" (Class A) discipline. The following year, he transferred to the direct doctoral track under the supervision of Prof. Qifa Xu.
His research focuses on intelligent fault detection and diagnosis of rotating machinery. His doctoral dissertation is entitled "Research on Health Assessment Methods for Critical Equipment Based on Information-Correlated Deep Reconstruction Networks". From November 2023 to December 2024, he was a CSC-funded visiting scholar at the Department of Mathematics, Physics and Electrical Engineering, Northumbria University (UK), working with Prof. Zhiwei Gao (IEEE Fellow, AAIA Fellow, AIIA Fellow) on AI-driven equipment fault diagnosis integrating expert diagnostic experience.
To date, he has published more than 15 papers in leading journals and international conferences, including 4 first-author journal papers, 1 first-author EI conference paper, 1 corresponding-author paper, and 9 co-authored papers. His work has been positively cited by renowned scholars including Academician Shanlin Yang, Zidong Wang, Qiang Zhang, Zhiqiang Zuo, Ruqiang Yan, Yan-Fu Li, Kai-Uwe Schröder, and Malka N. Halgamuge. He was selected for the 2024 Young Elite Scientists Sponsorship Program (Ph.D. Candidate Special Program) of the China Association for Science and Technology (CAST), and received the Excellent Doctoral Dissertation Award of the 2025 Provincial Quality Project for Education in the New Era.
For critical rotating equipment such as pumps, fans, and offshore wind turbines: fault detection, diagnosis, and prognosis based on time-frequency vibration signals and deep learning (VAEs, recurrent networks, attention mechanisms), integrating fault-frequency priors and expert diagnostic experience.
Fault detection over multivariate sensor time series: unsupervised and adaptive anomaly detection with spectral residual, contrastive learning, and multi-scale convolutional recurrent networks in strong mechanistic contexts.
Centered on the doctoral dissertation topic: information-correlated deep reconstruction, remaining useful life (RUL) prediction, and the development of equipment health management (PHM) systems.
For industrial IoT scenarios: distributed fault diagnosis under federated learning and event-triggered mechanisms, and the application of knowledge graphs and cloud-edge collaboration to predictive maintenance of industrial equipment.
Multimodal perception (fusion of vision, force, and vibration signals) for fault identification and abnormal motion detection of humanoid robots; based at the Multimodal Intelligent Flexible Assembly Joint R&D Center, research on condition monitoring, fault diagnosis, and human-robot collaborative assembly optimization for industrial robots in flexible assembly scenarios.
15+ papers published in leading journals and international conferences: 4 first-author journal papers, 1 first-author EI conference paper, 1 corresponding-author paper, and 9 co-authored papers. The work has been positively cited by many renowned scholars.
Principal Investigator (Grant No. QNXMC20250701091306009).
University–enterprise joint R&D center of Shenzhen University of Information Technology; Director.
Grant No. 72171070. Participated in the design and preparation of research content and assisted in the implementation of model code.
Grant No. 202004a05020020. Built an integrated monitoring, diagnosis, and life-prediction system for rotating machinery combining cloud platforms, deep learning, and expert knowledge, forming a closed-loop equipment lifecycle management system.
Developed a labeling tool for the intelligent algorithm platform (MATLAB GUI, integrated into the expert fault-labeling toolbox); conducted pilot research on an industrial O&M knowledge graph based on Neo4j; developed start-stop state recognition algorithms for pumps, blowers, induced-draft fans, and rolling mills, deployed on the Ronds O&M platform; led pilot research on fault identification algorithms for rotating equipment in the petrochemical industry.
China Association for Science and Technology (CAST), 2024
Provincial Quality Project for Education in the New Era, 2025
China Scholarship Council (CSC), 2023 — Northumbria University, UK
Hefei University of Technology, 2019 / 2020
2026
Supervised student teams in recent two years
Supervised student teams in recent two years
Supervised student teams to the National Second Prize (2026) and Provincial Second Prize, guiding them through the full pipeline of modeling, programming, and paper writing.
Supervised student teams to Honorable Mention, developing students' skills in international academic communication and English scientific writing.
Undergraduate students interested in robotics, artificial intelligence, programming, or data analysis are welcome to get in touch. You can start with foundational tasks and gradually take on deeper practice based on your interests, background, and project progress. I design different training plans for each student according to their development goals (pursuing a postgraduate degree or entering the workforce directly).
Students planning to work after graduation will aim to develop a real product within three years (based at the Multimodal Intelligent Flexible Assembly Joint R&D Center, in areas such as robotics), participating throughout the whole process — requirements analysis, solution design, algorithm development, software-hardware integration, and product delivery — to build the complete engineering project experience that employers value most.
Students intending to pursue a postgraduate degree will join the research group according to their interests and abilities, participate in real research projects (intelligent fault diagnosis, time series analysis, robot perception, etc.), receive systematic training in research methodology, and get guidance on research and academic paper writing — building a solid track record for postgraduate recommendation, entrance exams, or applications abroad.
Academic exchanges, research collaboration, and enrollment inquiries are welcome.