Query：
学者姓名：项程
Refining：
Year
Type
Indexed by
Source
Complex
Former Name
Co-
Language
Clean All
Abstract ：
Topology optimization is a critical tool for modern structural design, yet existing methods often prioritize single objectives (e.g., compliance minimization) and suffer from prohibitive computational costs, especially in multi-objective scenarios. To address these limitations, this paper introduces a novel two-stage multi-objective topology optimization (MOTO) method that uniquely integrates data-driven learning with physics-informed refinement, and both stages are implemented within nearly identical network frameworks, ensuring simplicity and consistency in execution. Firstly, a MOTO mathematical model based on the constraint programming method that considers competing objectives of compliance, stress distribution, and material usage was constructed. Secondly, a novel neural network that incorporates shifted windows attention mechanism and lightweight modules was developed to enhance feature extraction while maintaining computational efficiency. Finally, the proposed model was trained in two stages: In Stage-1, utilizing adaptive input tensors, the network predicts near-optimal geometries across variable design domains (including rectangular and L-shaped configurations) and diverse boundary conditions in real time, requiring only 1,650 samples per condition. In Stage-2, the near-optimal structures from Stage-1 were physically optimized to achieve optimal performance. Experimental results demonstrate that the method's capability to generate high-accuracy, computationally efficient solutions with robust generalization capabilities. It effectively tackles challenges associated with multi-scale design domains and non-convex geometries, various and even untrained boundary conditions while significantly reducing data dependency, a critical advancement for data-driven topology optimization. The novel approach offers new insights for multi-objective structural design and promotes advancements in structural design practices.
Keyword ：
Deep learning Deep learning Generalization ability Generalization ability Multi-object optimization Multi-object optimization Physics-informed neural networks Physics-informed neural networks Self-attention mechanism Self-attention mechanism Topology optimization Topology optimization
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Xiang, Cheng , Chen, Airong , Li, Hua et al. Two stage multiobjective topology optimization method via SwinUnet with enhanced generalization [J]. | SCIENTIFIC REPORTS , 2025 , 15 (1) . |
| MLA | Xiang, Cheng et al. "Two stage multiobjective topology optimization method via SwinUnet with enhanced generalization" . | SCIENTIFIC REPORTS 15 . 1 (2025) . |
| APA | Xiang, Cheng , Chen, Airong , Li, Hua , Wang, Dalei , Ge, Baixue , Chang, Haocheng . Two stage multiobjective topology optimization method via SwinUnet with enhanced generalization . | SCIENTIFIC REPORTS , 2025 , 15 (1) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
As bridges increasingly serve not only to meet traffic demands but also to fulfill aesthetic expectations, ensuring high aesthetic quality in bridge design has become more important. This paper proposes a deep-learning-based aesthetic evaluation network for the automatic assessment of bridge pylon aesthetics and elaborates on a design method that integrates this network with topology optimization. Firstly, a standardized database and anaesthetic quality evaluation framework specifically for bridge pylons of long-span cable-supported bridges were developed. High-quality bridge pylon data were acquired through a series of image processing methods, followed by an extensive questionnaire to gather aesthetic quality labels for each pylon. Then, different kinds of base models were designed and trained with the labeled dataset, with comparisons made across accuracy and complexity indicators to establish the Pylon Aesthetic Evaluation Network (PAENet). Finally, anaesthetics- oriented bridge pylon design method is proposed which integrates the PAENet with topology optimization, and the design of suspension bridge pylons were given as examples. Through this study, a high-quality database for bridge pylon aesthetics quality evaluation was constructed. Results indicate that the PAENet, using ShuffleNet v2x1 as the base model and enhanced through transfer learning, achieved the highest accuracy in assessing the aesthetic quality of bridge pylons, in alignment with human evaluations. Moreover, the integration of topology optimization and aesthetic evaluation facilitates designs that balance mechanical performance with aesthetic appeal. The proposed method promotes the practical incorporation of aesthetics into bridge design, contributing to the conceptual design of future bridges.
Keyword ：
Bridge aesthetics Bridge aesthetics Bridge design Bridge design Deep learning Deep learning Performance evaluation Performance evaluation Topology optimization Topology optimization
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Xiang, Cheng , Chen, Airong , Wang, Dalei et al. Deep-learning-based aesthetic evaluation network for bridge pylon and aesthetics-oriented bridge design [J]. | STRUCTURES , 2025 , 71 . |
| MLA | Xiang, Cheng et al. "Deep-learning-based aesthetic evaluation network for bridge pylon and aesthetics-oriented bridge design" . | STRUCTURES 71 (2025) . |
| APA | Xiang, Cheng , Chen, Airong , Wang, Dalei , Ning, Yun . Deep-learning-based aesthetic evaluation network for bridge pylon and aesthetics-oriented bridge design . | STRUCTURES , 2025 , 71 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Bridges are critical components of transportation systems and are susceptible to various natural and man-made disasters throughout their lifecycle. With the rapid development of the transportation industry, the frequency of vehicle-induced disasters has been steadily increasing. These incidents not only result in structural damage to bridges but also have the potential to cause traffic interruptions, weaken social service functions, and impose significant economic losses. In recent years, research on resilience has become a new focus in civil engineering disaster prevention and mitigation. This study proposes a concept of generalized bridge resilience and presents an evaluation framework for cable-stayed bridges under disasters. The framework includes a resilience evaluation indicator system from multiple dimensions, including safety, society, environment, and economy, which facilitates the dynamic and comprehensive control of bridge resilience throughout its entire lifecycle with the ultimate goals of enhancing structural safety and economic efficiency while promoting the development of environmentally friendly structural ecosystems. Furthermore, considering the influence of recovery speed, the study evaluates various repair strategies through resilience assessment, revealing the applicable environments and conditions for different repair strategies. This methodology offers significant implications for enhancing the safety, efficiency, and environmental sustainability of infrastructure systems, providing valuable guidance for future research in this field.
Keyword ：
disaster disaster evaluation framework evaluation framework functionality functionality resilience resilience
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Yanjie Liu , Cheng Xiang . A Comprehensive Framework for Evaluating Bridge Resilience: Safety, Social, Environmental, and Economic Perspectives [J]. | Sustainability , 2024 , 16 (3) . |
| MLA | Yanjie Liu et al. "A Comprehensive Framework for Evaluating Bridge Resilience: Safety, Social, Environmental, and Economic Perspectives" . | Sustainability 16 . 3 (2024) . |
| APA | Yanjie Liu , Cheng Xiang . A Comprehensive Framework for Evaluating Bridge Resilience: Safety, Social, Environmental, and Economic Perspectives . | Sustainability , 2024 , 16 (3) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The advent of deep learning provides a promising opportunity to improve the efficiency of topology optimization. However, existing methods make it difficult to achieve a balance between efficiency, accuracy, and generalization ability. To tackle this challenge, we propose a novel method based on a two -stage network framework. In the network, the partial convolution block and shifted windows attention mechanism are integrated to improve the model performance. In the first stage, a convolutional neural network -based model trained with a novel -designed loss function is employed to achieve real-time prediction of suboptimal structures. In the second stage, transfer learning is introduced to inherit the output of the first stage. Subsequently, the second stage optimizes the suboptimal structures to get the final optimal structures in a physical information -driven way. On the 2000 dataset, the two -stage method achieves an average compliance error of -1.45%, and 95.5% of the optimal structures perform better than that obtained by the traditional method and strictly meet volume constraints while eliminating structural disconnections. Finally, the proposed method is applied to a real -world engineering application for the first time, and the design of bridge pylons is given as an example. The results show that the proposed method is a promising exploration of topology optimization based on deep learning.
Keyword ：
Bridge pylon design Bridge pylon design Convolutional neural network Convolutional neural network Deep learning Deep learning Physical information Physical information Self-attention mechanism Self-attention mechanism Topology optimization Topology optimization
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wang, Dalei , Ning, Yun , Xiang, Cheng et al. A two-stage network framework for topology optimization incorporating deep learning and physical information [J]. | ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE , 2024 , 133 . |
| MLA | Wang, Dalei et al. "A two-stage network framework for topology optimization incorporating deep learning and physical information" . | ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 133 (2024) . |
| APA | Wang, Dalei , Ning, Yun , Xiang, Cheng , Chen, Airong . A two-stage network framework for topology optimization incorporating deep learning and physical information . | ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE , 2024 , 133 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
