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 BIM/GIS, Internet, digital twin, artificial intelligence, etc. Candidates with research or practical experiences in algorithms, and the development of large-scale software systems or Web/App 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.

2026-07-10

Recently, the editorial department of the engineering technology journal "Engineering Structures" announced the winning papers of the Editor's Featured Paper for the first issue of 2026. Among them, the paper "Real-time multiload response prediction and inverse analysis of offshore bridges based on deep learning" published in Volume 353-C of this journal in 2026 won the award. The authors include Master's student Zhuyu Sun, Associate Professor Yu-Tao Guo, Doctoral student Kang Ge, and Associate Professor Chao Hou from the Southern University of Science and Technology, alongside Professor Zhen-Zhong Hu.

Offshore bridges operate in complex ocean environments, making structural time history analysis and nonlinear model updating based on finite-element methods computationally intensive and time consuming, which limits their usage in scenarios requiring real-time analysis. To address the challenge of balancing computational efficiency with prediction accuracy inherent in existing methods, the research team proposed a deep learning-based offshore bridge predictor that integrates structural characteristics and coupled dynamic loads in ocean environments, enabling millisecond-level, high-precision nonlinear dynamic response predictions. Building upon this, a differentiable structural inverse framework was further developed, coupling the surrogate model with gradient-based optimization to enable rapid damage identification and model calibration for structural health monitoring. This research delivers an intelligent technical approach for efficient structural analysis and real-time monitoring of offshore bridges, advancing the application of deep learning in marine structural engineering.

Note: Engineering Structures, an authoritative journal in structural engineering published by Elsevier, was founded in 1978 and is ranked as a CAS Zone 1 TOP journal, with a 2026 impact factor of 7.6. The Editor's Featured Paper Award is conferred by the journal's Editor-in-Chief and Associate Editors based on a comprehensive evaluation of content innovation, research applicability, and writing quality. The selection covered Volumes 350 through 353-C, published between March and April 2026, across the Asia-Pacific, European, and Americas & Africa regions.

2026-07-02

The research article "Intelligent failure mode diagnosis of tubular joints using multimodal visual question answering" has been published online in the Journal of Building Structures.

Addressing the challenge of diagnosing failure modes of tubular joints in marine environments under coupled multi-loading conditions, this paper proposes a diagnostic method based on multimodal visual question answering (VQA). A multimodal database was constructed, comprising 409 failure images and 6,510 question-answer pairs, covering semantic information such as failure modes, components, locations, and quantities, and expanded to 1,227 images using image augmentation techniques. ResNet152 and LSTM were adopted to extract visual and semantic features, respectively, and the model was optimized by combining visual Feature-wise Linear Modulation, attention mechanisms, and multimodal fusion strategies. Results demonstrate that the improved model achieves an overall accuracy of 77.6%, with a 14.4% improvement in accuracy for failure location-related questions. Attention visualization confirms that the model effectively focuses on key failure regions, exhibiting strong interpretability.

Note: The first author is Zhang Wenhao, a PhD student in the Department of Ocean Science and Engineering at Southern University of Science and Technology, and the corresponding author is Associate Professor Hou Chao from Southern University of Science and Technology. This research was supported by the National Natural Science Foundation of China and the Shenzhen Science and Technology Program.

2026-06-24

On June 24, the research group's faculty and students went to Dabao Bay for a graduation season team-building activity to bid farewell to the Class of 2026. 

On the event day, team members participated in various activities in groups. During the sea voyage session, teachers and students immersed themselves in nature across the vast ocean, enjoying the thrill of fishing as they rode the waves. The beach exploration group relaxed and unwound amid the scenic coastal views, savoring peace and openness. In the afternoon, water-based activities emphasized participation and teamwork; under the guidance of instructors, members took turns engaging in challenges, strengthening their coordination through speed and cooperation. Later, during the beach afternoon tea break, everyone relaxed with casual games. At dinner, the research group extended heartfelt congratulations to the graduates, who in turn shared unforgettable experiences from their time in the team and expressed sincere gratitude. 

This team-building event provided the research group with a platform for communication beyond scientific work, further strengthening team cohesion. With the belief of "sailing forward united," team members will continue exploring the path of marine research. Wishing the graduates a future as vast and promising as the ocean.

2026-06-15

Recently, our research group's paper titled "BIM-based integrated delivery technologies for intelligent MEP management in the operation and maintenance phase," published in the journal Advances in Engineering Software, has reached 300 citations on Google Scholar.

The sustained attention this work has received from both domestic and international peers can be attributed to its effective response to critical challenges in the operation and maintenance (O&M) phase of building lifecycle. In response to the common difficulties caused by inconvenient access to traditional completion documents and incomplete information delivery, which hinder intelligent management, our research focused on the urgent task of "information digitalization." We explored ways to enable the as-built model to truly embed the key information required for intelligent O&M management, striving to establish a complete research loop from "data integration" to "system implementation."

Validation through real-world engineering cases demonstrated that the proposed solutions effectively support intelligent MEP management and ensure the operational safety of the systems. The cumulative citation count, to some extent, reflects the practical value of this research in advancing the digital transformation of the construction industry. Looking ahead, we will continue to deepen our research and further explore the integration and application of BIM technology across the full building lifecycle, providing more solid technical support for the intelligent and digital development of China's construction industry.