TOP

The research group will recruit several PHD and master students and 2 postdocs.

There are three requirements for doctoral and master students  enrollment: (1) Applicants should have an engineering background and have a strong interest in information technology. Applicants should have obtained a relevant bachelor's or master's degree; (2) Strong technical background, including but not limited to research experiences in offshore engineering structural analysis, marine environment numerical simulation and prediction, marine digital twin, etc. Candidates with research or practical experiences in numerical algorithms, industrial software development, or high-performance computing will be preferred; (3) Highly self-motivated, good written and oral English communication skills, and independent working ability.

Postdoctoral recruitments should also meet the following two points: (1) The applicant should be under the age of 35 and have obtained a doctoral degree no more 3 years; (2) The research directions are civil engineering information technology, Marine environmental information modeling and application, data-driven knowledge discovery and application, etc. (Note: postdoctoral candidates are required to present a half-hour academic presentation, including the main research works during PHD period and future postdoctoral work plans).

If you are interested, please send your resume, transcripts and work plan to the email: hu.zhenzhong@sz.tsinghua.edu.cn. For details, please see: PHD Master Recruitment and Postdoctoral Recruitment.

2026-10-26

The paper "Knowledge Extraction and Discovery Based on BIM: A Critical Review and Future Directions," published by the research group, has surpassed 100 citations on Google Scholar.

This study has attracted wide attention from the academic community, as it addresses the core pain point of knowledge management in the Architecture, Engineering, and Construction (AEC) industry. For a long time, industry knowledge has mainly relied on personal experience and been scattered across hard-copy documents and isolated databases, making systematic retrieval and reuse difficult. By deeply integrating knowledge science with BIM technology, this research systematically reviews the latest research progress from five aspects: knowledge description, knowledge discovery, knowledge storage and management, knowledge inference, and knowledge application. It points out that BIM, through semantic networks, knowledge graphs, and other related methods, can serve as a high-quality information carrier for knowledge extraction and discovery. The study also notes that such knowledge is valuable in the design, construction, operation, and maintenance periods of the AEC industry.

In addition to this work, the research group has published several other papers focusing on BIM-based knowledge engineering. Among them, the paper "BIM-based integrated delivery technologies for intelligent MEP management in the operation and maintenance phase" has been cited 301 times (with the author as first and corresponding author). This study focuses on digitalization of operational and maintenance information, establishing a complete closed-loop from "data integration" to "system implementation," effectively supporting intelligent management of mechanical, electrical, and plumbing systems. Another paper, "A natural-language-based approach to intelligent data retrieval and representation for cloud BIM," has received 243 citations (with the author as corresponding author). Addressing the industry's challenges of integrating multi-source information and managing increasingly large volumes of BIM data throughout the entire lifecycle of AEC projects, this study proposes a method for intelligent data retrieval and representation in cloud BIM based on natural language processing, which was validated for feasibility in the Kunming Airport Terminal project.

2026-10-17

Recently, China Graphics Society announced the results of its 2026 Incentive Program evaluation, and I was honored to be selected for the “Distinguished Graphics Teaching Award (Young Scholar Category) Incentive Program” of the China Graphics Society.

The Distinguished Graphics Teaching Award Incentive Program of the China Graphics Society is established to honor graphics educators who have long been engaged in graphics education and teaching, emphasized teaching reform and practice, and demonstrated outstanding teaching competence and remarkable teaching effectiveness. It represents the highest teaching honor for graphics teachers in higher education institutions nationwide. The Program was first launched in 2024 and is conducted annually, with no more than 10 recipients selected each time—no more than 5 for the Distinguished Graphics Teaching Award and no more than 5 for the Distinguished Graphics Teaching Award (Young Scholar Category). This year’s evaluation went through multiple stages, including nomination (self-recommendation), qualification review, on-site defense by candidates, on-site expert evaluation, and final committee review. A total of 5 educators were ultimately selected, with the Distinguished Graphics Teaching Award left vacant this year and 5 recipients selected for the Distinguished Graphics Teaching Award (Young Scholar Category).

This recognition is both an affirmation of my teaching and talent cultivation work, and a source of motivation for further improvement. Going forward, I will continue to move forward steadily.

2026-10-09

The invention titled "Method and System for Structural Damage Identification of Floating Offshore Wind Turbines" has been granted a patent certificate (Patent No.: ZL202611188223.4).

This invention discloses a method and system for identifying structural damage in floating offshore wind turbines. The method includes: establishing a joint state space incorporating discrete damage states and continuous operational conditions; acquiring multi-source dynamic response data and performing window-based feature extraction; using a temporal neural network to generate proposals for discrete damage states, and employing a neural posterior estimation model combined with a uniform distribution to generate proposals for continuous parameters; calculating observation likelihood based on a structural response prediction model; correcting particle weights via sequential Monte Carlo by integrating constraints on irreversible damage evolution, transition relationships among continuous parameters, and statistical patterns of activation rates; and recursively updating and applying backward smoothing to obtain posterior distributions of damage states, continuous parameters, damage activation rates, and the first activation time, which are then outputted. By unifying external operational variations and damage evolution within a sequential inference framework, this approach avoids misinterpreting environmental-induced modal drift as structural damage, delivering probabilistic identification results that support online safety assessment and maintenance decision-making for floating offshore wind turbines.

Note: The inventors of this patent also include doctoral student Jiang Chunhao and postdoctoral researcher Liu Yi.

2026-09-24

According to the latest data released by Clarivate’s Essential Science Indicators (ESI) database in September this year, the paper entitled "Digital disaster prevention for ocean engineering: Current progress and future directions", published in *Ocean Engineering* (a Q1 Top journal, IF = 6.3), has been selected as an ESI Highly Cited Paper.

This study addresses the risks of natural hazard-triggered technological accidents (Natech) intensified by the increasing frequency of typhoons and other extreme climate events, and systematically synthesizes recent progress in digital disaster prevention for ocean engineering under climate extremes. Focusing on three core areas—disaster-inducing factor identification, disaster mechanism modeling, and structural safety assessment—the paper summarizes the integration of physics-based numerical modeling, data-driven simulation, and system dynamics, and reviews the applications of digital twins, machine learning, and deep learning in scenario-based risk analysis, safety evaluation, and early-warning systems, with particular emphasis on offshore wind farms. Building upon this framework, the study proposes a forward-looking digital technology system that integrates environmental sensing, interpretable modeling, intelligent prediction and warning, and resilience-oriented decision support, paving the way toward more adaptive, predictive, and resilient safety management in ocean engineering.

Note: ESI Highly Cited Papers refer to papers published within the last ten years that rank in the top 1% globally by citation frequency within their respective subject fields. ESI Highly Cited Papers have now become one of the important indicators for measuring the academic influence of a university.