Research Group of Xinzheng Lu, Dept. Civil Engineering, Tsinghua University, Beijing (2026)

10/10/2026

Congratulations to Wenjun Zhuang and coauthors on the publication of “A Diffusion-Based Sequential Generative Workflow for AI-Assisted Architectural and Structural Design of Detached Houses” in _Engineering Structures_.

Most existing AI applications in building design focus on isolated tasks, such as floor plan generation or structural layout optimization. This paper takes a step toward integrated AI-assisted architectural and structural design, connecting the entire preliminary design workflow.

The proposed approach combines:

• Floor plan generation: Diffusion models enhanced by transfer learning to generate architectural layouts from design requirements.

• Architectural component generation: Conditional diffusion models to generate walls, doors, and windows based on floor plans.

• Structural design: Diffusion models and graph neural networks for column placement, beam layout, and member section sizing.

• Structural verification: Automated modeling and PKPM-based seismic code checks.

The models achieved:
• Floor plans: Micro IoU = 0.6165
• Architectural components: Micro IoU = 0.7479
• Column placement: IoU = 0.7885

In three practical residential case studies, the generated and refined designs satisfied the evaluated seismic code requirements. The AI-assisted workflow, including manual refinement and verification, reduced average preliminary design time from 437 minutes to 39 minutes (approximately 91%) compared with conventional manual design.

The key contribution is connecting architectural and structural generation into a continuous workflow, rather than developing AI models for isolated design tasks.

While manual refinement remains necessary, the study demonstrates the potential of integrating multiple generative AI models into practical building design.

Paper: https://doi.org/10.1016/j.engstruct.2026.123934

The accompanying graphical abstract was generated using AI based on figures and results from the paper.

29/09/2026

Congratulations to Jikang Xia on the publication of the paper, “Beam Layout Design in Shear Wall Structures Using a Diffusion Model Guided by Rule-Based Masks,” in Engineering Structures.

Beam layout design in shear wall structures needs to satisfy both architectural requirements and structural load-transfer principles. This paper explores how engineering knowledge can be incorporated directly into diffusion-based generative design to make AI-generated beam layouts more controllable and engineering-oriented.

The proposed method combines:
• Rule-based masks that encode engineering considerations such as vertical load transfer, shear-wall-end connectivity, horizontal load-path continuity, and architectural space segmentation
• A conditional diffusion model that generates detailed beam layouts within the admissible regions defined by these masks
• Automated structural modeling and analysis to evaluate the generated designs in practical engineering cases

More than 600 engineer-designed shear wall–beam structural plans were used for model development and evaluation. The rule-generated masks achieved a mean coverage ratio of 97.9% for engineer-designed beam locations. On the benchmark dataset, the diffusion model achieved an average IoU of 0.841, representing a 35.0% improvement over the GNN baseline reported in the study.

In a practical residential building case, the generated beam layout reached an IoU of 0.947 compared with the engineer’s design. The resulting structural model satisfied the evaluated mechanical performance requirements, while material usage differed by less than 1% from the manual design.

An important aspect of this work is the combination of explicit engineering rules with data-driven generation: the rules constrain where beams can reasonably be placed, while the diffusion model retains the flexibility to learn detailed beam topology from engineering design data.

Paper: https://doi.org/10.1016/j.engstruct.2026.123842

The graphical abstract accompanying this post was generated using AI based on figures and results from the paper.

25/09/2026

Congratulations to Yuan Tian on the publication of the paper, “Nonlinear Time-History Analysis of Degrading Structures under Spectrum-Compatible Shallow Moonquakes Synthesized from Apollo Records,” in Engineering Structures.

Shallow moonquakes can last much longer and attenuate more slowly than typical terrestrial earthquakes, making cumulative damage and structural degradation important considerations for future lunar infrastructure. In this study, Apollo shallow-moonquake records are used to investigate these effects through spectrum-compatible ground-motion synthesis and nonlinear structural analysis.

The study:
• Constructs 69 spectrum-compatible shallow-moonquake records for return periods of 475, 2,500, and 5,000 years using a continuous-wavelet-transform-based procedure.
• Performs 1,656 nonlinear time-history analyses on SDOF structural models with different periods, strength levels, and stiffness/strength degradation characteristics.
• Examines not only peak displacement, but also the progressive shift of the oscillating center and residual deformation caused by long-duration excitation.
• Shows that explicitly considering structural degradation can substantially increase displacement demand. For some models, the median peak displacement increases by more than 20%, while several degrading models experience collapse under the stronger moonquake scenarios.

One important message is that the long duration of moonquakes matters. Even when the later-stage acceleration is relatively small, repeated cyclic loading can continue to accumulate damage and residual deformation. For lunar structural design, strength and stiffness degradation therefore need to be considered together with conventional measures of seismic intensity.

The generated spectrum-compatible moonquake records are also made available for further research, which we hope can support continued development of seismic analysis and design methods for future lunar structures.

Paper: https://doi.org/10.1016/j.engstruct.2026.123835

Congratulations again to Yuan Tian and the team.
The graphical abstract accompanying this post was generated using AI.

19/08/2026

Our new paper “QuakeF2G: A region-specific transformer-based ground motion prediction model considering fault segments modeling” has been published in Computer-Aided Civil and Infrastructure Engineering

Accurately capturing near-fault ground motions and rupture directivity remains challenging. Empirical ground-motion models often simplify complex rupture geometry, while physics-based simulations can be computationally demanding.

In this work, we developed QuakeF2G, a Transformer-based probabilistic ground-motion prediction framework that represents earthquake ruptures as a sequence of fault-segment tokens. A dedicated fault encoder and geometry-aware cross-attention mechanism integrate rupture geometry, source–site configuration, and site information to predict PGV.

Some results from the study:

• Trained on approximately 626,000 CyberShake earthquake scenarios in Southern California
• Explicit finite-fault representation reduced RMSE by 36% compared with the point-source baseline
• The same framework supports both ground-motion prediction and conditional spatial interpolation
• In our spatial interpolation experiments, QuakeF2G outperformed Ordinary Kriging across the evaluated sampling densities

Code: https://github.com/YitianF/QuakeF2G
Paper: https://doi.org/10.1016/j.cacaie.2026.100183

Many thanks to Yitian Feng and Weiqiang Zhu for the collaboration.

The graphical abstract accompanying this post was generated using AI.

14/08/2026

Congratulations to Yongjun Kang on the publication of the review paper, “Advances and Applications of Computational Design Methods in Structural Design,” in the ASCE Journal of Computing in Civil Engineering.

Computational design is reshaping structural engineering, but a clear framework is still needed to connect digital representation, performance analysis, and design generation. This paper organizes the field into three complementary categories:

• Drawing-oriented methods, including CAD and BIM
• Analysis-oriented methods, including formula-based calculations and finite-element analysis
• Design-oriented methods, including form-finding, structural optimization, and generative structural design

The paper reviews their historical development, engineering applications, current limitations, and future directions. A key message is that these three paradigms are not successive replacements for one another; rather, they need to work together across the structural design workflow.

Future progress will depend on stronger semantic interaction, more robust engineering reasoning and modeling, higher-quality data, and more accurate and interpretable AI-generated designs.

Paper: https://doi.org/10.1061/JCCEE5.CPENG-7548

The graphical abstract accompanying this post was generated using AI.

12/08/2026

Our new paper, “Graph-based data-physics hybrid surrogate modeling for seismic response estimation of steel moment frame building portfolios,” is now online in Bulletin of Earthquake Engineering.

Regional-scale seismic assessment requires models that are both accurate and computationally efficient. In this study, we represent steel moment-frame buildings as graphs and integrate graph neural networks with physics-based multi-degree-of-freedom models.

The proposed framework:

• preserves building topology and member-level structural information;
• accommodates buildings with different heights and configurations without building-specific retraining;
• reduces mean absolute error by up to 57.5% compared with conventional parameterized MDOF models; and
• enables response estimation in less than one second—or about 0.007 seconds using the end-to-end model.

The hybrid approach also better preserves physical response trends at high drift levels and under critical seismic demands, providing a promising pathway for scalable seismic assessment based on urban building databases and digital twins.

The datasets and GNN algorithms are available at:
Dataset: https://doi.org/10.57760/sciencedb.33049
Code: https://doi.org/10.57760/sciencedb.33051

Read the paper: https://doi.org/10.1007/s10518-026-02629-z

The graphical abstract was created with the assistance of generative AI.

10/08/2026

Young Scholars Workshop on Intelligent Engineering Design

Today we held the Young Scholars Workshop on Intelligent Engineering Design at Tsinghua University. The workshop featured 27 young speakers from 16 universities across mainland China, Hong Kong, and overseas—with 23 presenting onsite and four online—and attracted an audience of more than 60 participants.

The presentations covered a wide range of topics, including data–physics-driven surrogate models, graph neural networks, topology and differentiable optimization, generative AI for architectural and structural design, BIM automation, and LLM-based design agents.

Two impressions stood out.
First, AI-enabled engineering design is advancing at remarkable speed, moving rapidly from individual algorithms toward integrated workflows for design, analysis, checking, and optimization.
Second, the creativity of these young researchers was equally striking. The presentations were technically rigorous, highly original, and genuinely exciting, with many ideas closely connected to real engineering challenges.

Many thanks to all the speakers and participants for the excellent presentations and open discussions. I look forward to seeing these ideas develop into further research and collaboration.

30/07/2026

Our latest paper, “An intelligent sizing design method for frame-shear wall components in industrial parks via heterogeneous graph neural networks,” has been published in Advanced Engineering Informatics.

Our group has been continuously advancing AI-assisted structural design. While previous studies have achieved significant progress in structural layout generation, layout alone does not constitute a complete structural design—component sizing is the essential bridge from layout generation to structural analysis and engineering implementation. Existing intelligent sizing methods often focus on pure frame or shear-wall systems, cover only selected component types, and rely mainly on geometry and global design conditions without explicitly representing component-level load transfer.

In this study, we developed a unified heterogeneous graph representation that simultaneously covers the principal load-bearing components of frame–shear wall structures: shear walls, beams, columns, and shear-wall end columns.

More importantly, the method explicitly incorporates component-level load paths, tracing dead and live loads from slabs through secondary members and shear walls to primary beams, frame columns, and wall-end columns. The model therefore learns not only structural topology, but also how loads are transferred among components and influence their required dimensions.

Using data from 101 real industrial-park projects, the proposed method reduced the average sizing RMSE by approximately 21% compared with the baseline HGNN, with reductions approaching 30% for column dimensions. In three independent engineering cases, more than 70% of the predicted dimensions agreed with engineers’ designs within a ±15% tolerance, over 95% of the components satisfied code requirements without modification, and the overall preliminary design workflow was approximately five times faster.

This work extends our research on intelligent structural design toward a more complete engineering workflow—jointly considering walls, beams, columns, their interactions, and the load paths connecting them.

📄 https://doi.org/10.1016/j.aei.2026.105100

The graphic abstract is generated by Gemini based on the paper.

27/07/2026

🏆 Honored at WAIC 2026: Advancing AI-Driven Building Design with High-Quality Data

We are delighted to share that the Image–Text Topology Dataset for Building Engineering Design was recognized as an Outstanding High-Quality Industry Dataset Achievement at the World Artificial Intelligence Conference (WAIC) 2026 in Shanghai.

Jointly developed by the China Southwest Architectural Design and Research Institute, Tsinghua University, Southwest Jiaotong University, and Hemu AI-Structure, the dataset connects engineering drawings, textual information, and spatial-topological relationships to support AI applications in building design.

The dataset has already contributed to:
- AI-assisted structural design, fire safety design, and building equipment layout
- The development of more than 20 domain-specific AI models
- The continuous improvement of AI-structure Copilot (ai-structure.com), which has supported over 5,200 real-world engineering projects

This recognition at WAIC highlights a fundamental principle: reliable engineering AI depends not only on advanced models, but also on high-quality, domain-grounded data.

We look forward to working with researchers, engineering firms, and technology partners worldwide to accelerate the transition from experience-driven design to data-driven and AI-assisted engineering.

20/07/2026

I just came across this newly published review paper, “Automatic structural design of RC building layout based on deep learning,” and found it very interesting.

Abstract: Driven by rapid urbanization, the demand for high-rise structures, particularly Reinforced Concrete (RC) buildings, continues to rise. In response, numerous methods that automate structural design have recently emerged, aiming for efficient processes at lower cost. Due to the challenges these approaches present, we critically review publications from 2021 to 2025 on the conceptual layout stage of RC buildings, proposing a unified taxonomy that organizes methods by modeled objects (walls, beams, columns), data representations (raster, polygonal, graph), and their targets (e.g., wall/beam length, thickness, position). We analyze biases and constraints in the data and models, discuss how approaches circumvent them, and summarize recurring formulations in tables to help practitioners shortlist candidates. Persistent gaps include limited access to datasets, inconsistent evaluation protocols/metrics, and restricted generalization across plan styles and regulatory contexts. We conclude with guidance on method selection and opportunities to establish standard benchmarks. Although these methods remain largely at the proof-of-concept stage, with current evidence concentrated in high-seismicity shear-wall regimes and cross-code generalization still untested, physics-informed objectives, novel data representations, and cloud computing represent the most promising avenues toward reliable and ultimately scalable automation of RC building design.
Keywords: Conceptual layout; Intelligent design; Structural design; Generative AI; Graph neural networks

Paper: https://doi.org/10.1016/j.jobe.2026.116764

Note: The graphical abstract was generated by Gemini based on the paper.

Research Group of Xinzheng Lu

10/10/2026

29/09/2026

25/09/2026

19/08/2026

14/08/2026

12/08/2026

10/08/2026

30/07/2026

27/07/2026

20/07/2026

Address

Website

Alerts

Shortcuts

Share

Category

Listing takedown request