TOP-1

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.

TOP-2

26 November 2021, Discharge of treated Fukushima nuclear accident contaminated water: macroscopic and microscopic simulations has been published on National Science Review, which is a full affirmation of the students and teachers of the subject group who are generous and rigorous in their learning! NSR officer micro-push high-quality and efficient, reflecting China's outstanding leading journals of the super-class level! Thanks to the director of singhua University's Institute for Ocean Engineering (IOE), Zhang Jianmin's guidance and support, thanks to the editorial department and reviewers for their high evaluation!

The results of this study are of great significance for the prediction of long-term spread of pollutants, the rational response of nuclear wastewater discharge plans and the monitoring of subsequent radioactive material concentrations. In the future, we will continue to deepen our research, Further explore the long-term impact of the discharge of nuclear waste water on the whole ocean and mankind, and provide important decision support for the country and the world to deal with the nuclear wastewater crisis!

Note: National Science Review , whose impact factor in 2021 is 17.275, is the top journal in the multi-discipline domain. For more information, please see the introduction video.

2026-05-06

The paper "A Differentiable Optimization Framework for Automated Design of Offshore Jacket Structures under Varied Scenarios" has been published in Computer-Aided Civil and Infrastructure Engineering.

To address the long-standing issue that conventional offshore jacket platform design relies heavily on engineers’ experience and often leads to overly conservative solutions, this study proposes a beam element-based topology optimization method for offshore jacket structures. By integrating multidisciplinary knowledge, the proposed method simultaneously optimizes nodal coordinates and cross-sectional sizes, with the objective of minimizing the weighted sum of structural volume and compliance. Considering that marine loads are dependent on structural configuration, a differentiable formulation of Morison’s equation is developed, while pile-soil interaction is incorporated through a hybrid sensitivity scheme. Displacement constraints, diameter-to-thickness ratio constraints, and symmetry constraints are also considered. In addition, a Gumbel-Softmax-based strategy is employed to enable differentiable optimization of discrete standard sections, thereby improving manufacturability. A member removal strategy is further proposed to generate diversified design alternatives. The method is applicable to various multi-leg spatial frame configurations, can complete the design of a four-leg jacket within 3–5 minutes, and has been validated through a real engineering case.

Note: Computer-Aided Civil and Infrastructure Engineering is a top-tier journal in the field of engineering and technology, with a 2025 Impact Factor of 9.1. The first author of the paper is doctoral student Kang Ge, and Prof. Yutao Guo is the corresponding author. This research was supported by the Shenzhen Science and Technology Program.

2026-05-01

The paper "Real-time virtual sensing for offshore wind turbines with arbitrary sensor configurations using subspace-based spectral graph networks" has been published in Ocean Engineering.

To address the challenges faced by offshore wind turbines under harsh marine environments, including unstandardized sensor layouts and the limitations of sparse, single-sided measurements, this study proposes a subspace-based spectral graph network for virtual sensing. The proposed method overcomes the dependence of conventional structural health monitoring techniques on fixed sensor configurations. Specifically, sparse and single-sided strain measurements from arbitrary sensor layouts are first reconstructed in a proper orthogonal decomposition subspace. The reconstructed features are then combined with Fourier-enhanced spatial coordinates and mapped to full-field structural responses through a Chebyshev spectral graph network. Experimental results demonstrate that the model maintains robust reconstruction accuracy even under highly non-uniform sensor distributions, significantly outperforms baseline models, and achieves real-time inference within 0.01 s. In addition, theoretical guarantees on sensor count and error bounds are derived and numerically validated. This work effectively overcomes practical sensing constraints in engineering applications and enables continuous, autonomous integrity management to support the long-term resilience of critical offshore energy infrastructure.

Note: Ocean Engineering is a Q1 Top journal in the field of engineering and technology, with a 2025 impact factor of 5.5. The first authors of the paper are PhD student Chunhao Jiang and postdoctoral researcher Yihong Li, and I serve as the corresponding author. This research was supported by the Guangdong Basic and Applied Basic Research Foundation.

2026-04-28

"The method and system for monitoring the structural health of offshore wind turbines" has been granted an invention patent certificate (Patent Number: ZL202610248475.5). 

The present invention discloses a method and system for structural health monitoring of offshore wind turbines. The method comprises: in the offline stage, constructing a strain snapshot matrix through finite element simulation, extracting a low-dimensional feature subspace basis matrix by using proper orthogonal decomposition, and mapping the structural grid to a graph; Simultaneously, the Fourier feature mapping of node coordinates is carried out, and after concatenating with the reconstructed strain features, a spectral graph neural network based on Chebyshev graph convolution is trained. In the online monitoring stage, based on the real-time collected sparse strain data on one side, the modal coefficients are quickly solved through the mask matrix and the pre-stored basis matrix, and the full-field strain is preliminarily reconstructed. Then, it is input into the trained network model to real-time infer the high-fidelity full-field displacement and stress fields. This invention can effectively adapt to any changes in sensor layout and achieve real-time and accurate reconstruction of the full-field physical response of complex structures under the harsh condition of sparse measurement on one side, solving the problem of traditional techniques' dependence on fixed measurement points and bilateral measurement.

Note: The inventors of this patent also include doctoral student Jiang Chunhao and postdoctoral fellow Li Yihong.