Zhenzhong Hu

    He received both his BE and PhD degree in the Department of Civil Engineering at Tsinghua University, China. He was a visiting researcher in Carnegie Mellon University.
    He is now the associate professor in Shenzhen International Graduate School, Tsinghua University, and also the secretary general of the BIM Specialty Committee of the China Graphics Society.
    His research interests include information technologies in civil and marine engineering, building information modeling (BIM) and digital disaster prevention and mitigation.
  • 2026-05-06

    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

    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

    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.

  • 2026-04-16

    2026-04-16

    The paper "ST-SRNet: A deep learning framework for seismic response prediction of subsea tunnels" has been published in Tunnelling and Underground Space Technology.

    As key infrastructure in nearshore and offshore areas, subsea tunnels face extremely high risks from earthquake disasters. Conventional numerical methods are computationally intensive, making them inadequate for real-time prediction demands under complex marine environments. To address this, this study proposes a rapid prediction method integrating high-fidelity finite element (FE) simulation and deep learning technology. A two-dimensional FE model incorporating bidirectional (horizontal and vertical) ground motions and hydrodynamic pressure effects is established to construct a comprehensive seismic response database. On this basis, the Subsea Tunnel Seismic Response Network (ST-SRNet) is developed, combining one-dimensional convolution, attention mechanisms, long short-term memory (LSTM), and a Feature-wise Linear Modulation (FiLM) module to achieve efficient and accurate prediction of seismic responses at multiple monitoring points. Results show that the model achieves high prediction accuracy, with the coefficient of determination values exceeding 0.95 and peak relative errors controlled below 10%, while also exhibiting strong generalization. An engineering case study further validates the robustness and applicability of the proposed method, providing effective technical support for disaster assessment, structural monitoring, and real-time early warning of subsea tunnels.

    Note: Tunnelling and Underground Space Technology is a Q1 top journal in the field of engineering and technology, with an impact factor of 7.4 in 2025. The first author of the paper is Master’s student Yimu Chen, and Prof. Yutao Guo is the corresponding author. This research was supported by the Shenzhen Science and Technology Program.

  • 2026-03-26

    2026-03-26

    The paper "Typhoon-Induced Risk Evolution in Wind Farms: From Disaster-Inducing Factors Identification to Domino Effect Assessment" has been published in the journal Reliability Engineering & System Safety. 

    In response to the technical accidents caused by typhoons in the complex waters of the South China Sea, this study proposes a Disaster-Inducing and Risk Evaluation (DIRE) framework. This framework integrates two modules: the Disaster Inducing Factor Extraction Model (DIFEM), which identifies the key environmental driving factors that cause damage to wind turbines through a hybrid physical-data fusion analysis; and the Hierarchical Analytical Domino Evaluation System (HADES), which realizes systematic hazard classification, hierarchical structuring, probability assessment, and consequence assessment. Through the analysis of five typhoon-induced disaster events in the South China Sea, this study not only identified the common and specific disaster-causing factors that cause damage to wind turbines, but also quantified the cascading disaster risks. The findings of this study provide reliable data and decision-making support for disaster prevention and mitigation on wind farms.

    Note: "Reliability Engineering & System Safety" is a top journal in the field of engineering technology in the Q1 zone, with an impact factor of 11.0 in 2025. The first author of the paper is doctoral student Li Yilin and postdoctoral researcher Li Yihong, and I am the corresponding author. The research results were supported by the National Key R&D Program of China, the Guangdong Basic and Applied Basic Research Foundation, the Shenzhen Science and Technology Program, and the Shuimu Tsinghua Scholar Program.