Advanced Engineering Informatics最新文献

{"title":"Spatio-temporal hypergraph-driven evolutionary Graph-Mamba method for remaining useful life prediction","authors":"Yonglei Ren,&nbsp;Zong Meng,&nbsp;Kai Chen,&nbsp;Weiliang Sun,&nbsp;Haoze Chen","doi":"10.1016/j.aei.2025.103925","DOIUrl":"10.1016/j.aei.2025.103925","url":null,"abstract":"<div><div>The effective fusion of multi-sensor information is crucial for predicting the remaining useful life of aero-engines. However, due to the complexity of variable operating conditions, sensor signals exhibit time-varying and nonlinear characteristics, making degradation information ambiguous. This poses challenges in constructing predictive models that can accurately extract degradation trends and effectively integrate the spatio-temporal characteristics of signals with prior knowledge. Therefore, this paper proposes a remaining useful life prediction method based on evolutionary Graph-Mamba. First, the mapping relationship between operating conditions and sensor signals in the healthy stage is learned through the Kolmogorov–Arnold Networks, and the residual between the output value of the network and the original signal is characterized as degradation information. Meanwhile, the energy transfer paths within the aircraft engine are embedded as knowledge to construct a hypergraph, thereby creating a spatio-temporal hypergraph to achieve information fusion. Second, we design a gating mechanism to simulate the crossover operation, fusing information from the previous generation to enhance the diversity of embeddings generated by Graph-Mamba, thereby leading to superior graph representations. Simultaneously, we add Gaussian white noise to simulate mutation operations, improving the robustness of the prediction model. Finally, the prediction model was validated on NASA’s N-CMAPSS dataset and further verified for its effectiveness using the C-MAPSS dataset. Experimental results demonstrate that this method has excellent predictive performance.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"69 ","pages":"Article 103925"},"PeriodicalIF":9.9,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145220692","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-objective optimisation of surveillance camera placement for bridge–ship collision early-warning using an improved non-dominated sorting genetic algorithm","authors":"Ruixuan Liao,&nbsp;Yiming Zhang,&nbsp;Hao Wang,&nbsp;Tianhao Zhao,&nbsp;Xu Wang","doi":"10.1016/j.aei.2025.103918","DOIUrl":"10.1016/j.aei.2025.103918","url":null,"abstract":"<div><div>Bridges spanning navigable waterways face increasing risk of accidental ship impacts due to the growing volume of waterborne transport, usually resulting in fatalities and substantial economic losses. Computer vision-based ship detection using camera networks provides an effective and cost-efficient solution for collision avoidance warnings. Although advanced algorithms have improved the robustness of visual systems under complex conditions such as night-time and atmospheric interference, their performance is still largely constrained by suboptimal camera deployment strategies. Determining an optimal surveillance layout remains challenging given the large-scale monitoring area and on-site installation constraints of bridge waterways. This study proposes a multi-objective-based camera placement framework integrated with an efficient optimisation approach to address this issue. Specifically, an improved Non-dominated Sorting Genetic Algorithm III (NSGA-III) is developed to reduce run-time complexity by eliminating redundant computations and incorporating adaptive memory matrices. A multi-objective function is designed to maximise camera coverage, enhance ship detectability, and minimise overall deployment costs. The effectiveness of the framework is validated through simulation-based experiments conducted on the waterway beneath a real-world long-span bridge. Two scenarios with different camera densities are explored. Compared to the standard NSGA-III and NSGA, the improved NSGA-III achieves higher computational efficacy and lower memory usage, leading to more effective camera deployment schemes. The optimised visual security systems are presented in a three-dimensional proxy virtual environment, with demonstration videos available at: <span><span>https://github.com/congliaoxueCV/Display</span><svg><path></path></svg></span>. The system-generated images consistently enable effective ship detection by the standard object detection model under various conditions.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"69 ","pages":"Article 103918"},"PeriodicalIF":9.9,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145221250","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-Spatial-Parametric evacuation modeling for data mining of route selection in University Libraries: an immersive VR-based approach","authors":"Zunhui Yang ,&nbsp;Wei Ling ,&nbsp;Fangyu Cheng ,&nbsp;Xi Deng ,&nbsp;Xin Wei ,&nbsp;Hua Wang ,&nbsp;Jichao Song ,&nbsp;Shen Wei","doi":"10.1016/j.aei.2025.103922","DOIUrl":"10.1016/j.aei.2025.103922","url":null,"abstract":"<div><div>The evacuation performance of university libraries directly impacts the safety of students’ lives during emergencies. Accurate evacuation models can provide evacuation design with reliable evidence for decision-making. While the Original Evacuation Model (OEM) relies solely on distance-based route selection, they ignore critical spatial parameters that influence human behavior. In this study, therefore, a Refined Evacuation Model (REM) with multi-spatial-parameter-based route selection logic has been developed through immersive virtual reality experiments, focusing on circulation spaces comprising corridors and open spaces (wider than corridors) in university libraries. The physiological data were collected to explain the route selection process, and the results indicated that the left–right positioning and width of open spaces significantly influence path selection in cases with equal distance. The REM models these behavioral patterns as rule-based logic, correcting the OEM evacuation time by up to 46.43%. Case studies show that widening right-side open spaces or narrowing left-side ones could reduce evacuation time. This strategic layout can shorten the evacuation time by up to 31.71%. This study bridges behavioral knowledge with computational modeling and provides a framework for knowledge-intensive evacuation design. It can be used as a practical tool for architects and safety planners to optimize library layout design, based on evidence-driven spatial parameter rules.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"69 ","pages":"Article 103922"},"PeriodicalIF":9.9,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145220693","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intelligent detection method for debonding and voids in concrete-filled steel/aluminum tubular structures based on impact acoustics and unsupervised learning","authors":"Yonghui An ,&nbsp;Chenning Ma ,&nbsp;Hailong Du ,&nbsp;Jianjun Wang ,&nbsp;Liang Chen ,&nbsp;Wei Shen","doi":"10.1016/j.aei.2025.103924","DOIUrl":"10.1016/j.aei.2025.103924","url":null,"abstract":"<div><div>Debonding and voids between concrete-filled steel/aluminum tubes and the internal concrete are recognized as critical defects that can significantly compromise structural integrity, load-bearing capacity, and service life. Impact-acoustics-based methods offer operational simplicity and low cost, yet most current approaches rely on manual tapping, making them highly dependent on operator skill, poorly generalized, and low in accuracy and automation, which limits large-scale engineering application. To address these limitations, firstly, this study proposes an impact-acoustics autoencoder framework that leverages the reconstruction error of tapping sound spectrograms as a primary indicator for defect identification. Power spectral density peak frequency and wavelet packet energy ratio are used to automatically label normal data samples, converting a semi-supervised autoencoder into a fully unsupervised model. Secondly, an anomaly threshold determination method based on exceedance theory is developed to enhance automation. Furthermore, a channel self-attention mechanism is embedded in the convolutional autoencoder to strengthen key feature extraction, thereby improving detection accuracy and robustness. Thirdly, an automatic crawling and tapping robot is developed and validated on an actual bridge. Experimental results show that the proposed method significantly outperforms traditional manual techniques in accuracy and recall, achieves performance close to supervised approaches, detects void regions with over 96 % accuracy, and produces results highly consistent with ultrasonic phased array imaging. In addition, the method maintains similarly high recognition accuracy in concrete-filled aluminum tubes. This method demonstrates strong generalization, high precision, and adaptive capability, making it particularly suitable for integration with intelligent robotic platforms for fully automated detection in practical engineering projects.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"69 ","pages":"Article 103924"},"PeriodicalIF":9.9,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145220694","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CO-DOSP: A hierarchical optimization-based motion planner for multi-robot manipulation in confined and task-constrained workspace","authors":"Zhao Jin,&nbsp;Jichuan Yu,&nbsp;Yixuan Liang,&nbsp;Yunan Wang,&nbsp;Ze Wang,&nbsp;Chuxiong Hu","doi":"10.1016/j.aei.2025.103923","DOIUrl":"10.1016/j.aei.2025.103923","url":null,"abstract":"<div><div>Efficient and robust motion planning for multi-robot systems is critical to advancing industrial automation tasks such as logistics, assembly, and surface finishing. However, achieving reliable coordination under complex task constraints, obstacle avoidance, and high-dimensional configuration spaces remains challenging. This paper presents CO-DOSP, a novel hierarchical optimization framework that integrates convex decomposition with duality-aware second-order optimization for multi-arm systems operating in constrained environments. The proposed method sequentially decomposes complex planning problems into tractable subproblems and utilizes the strong duality properties of second-order approximations to enable efficient null-space searches and manifold projections, effectively avoiding local minima. Extensive simulations and real-world experiments on redundant collaborative robots demonstrate that CO-DOSP achieves the highest planning success rate and over threefold faster computation times compared to the best baseline. These results validate the framework’s scalability, robustness, and practical applicability, offering a valuable contribution to industrial automation manufacturing and confined collaborative operations.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"69 ","pages":"Article 103923"},"PeriodicalIF":9.9,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145220690","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated “E”-aware data processing for construction ESG using building information modeling and large language model","authors":"Xingbo Gong ,&nbsp;Xingyu Tao ,&nbsp;Yuqing Xu ,&nbsp;Helen H.L. Kwok ,&nbsp;Weiwei Chen ,&nbsp;Da Shi ,&nbsp;Dezhi Li ,&nbsp;Jack C.P. Cheng","doi":"10.1016/j.aei.2025.103920","DOIUrl":"10.1016/j.aei.2025.103920","url":null,"abstract":"<div><div>Environmental, Social and Governance (ESG) assessment and disclosure are critical for architecture, engineering, and construction (AEC) companies to market their financial results, reputational position, and compliance with regulatory requirements. Within this framework, the environmental (“E”) dimension presents unique and formidable data management challenges distinct from social and governance aspects. Specifically, the complex interplay of quantitative metrics and qualitative descriptions within ‘E’-aware data (e.g., measurable resource consumption alongside descriptive material sourcing practices, emissions figures coupled with compliance narratives), amplified by its sheer volume and the persistent ambiguity of environmental indicators and reporting standards, poses significant obstacles to effective ‘E’-aware data disclosure. Large Language Models (LLMs) possess inherent advantages in processing such complex environmental information due to their proficient language processing and generalization capabilities. Nonetheless, the development of LLM-based methods explicitly tailored for environmental data management within the construction sector remains underexplored. To this end, this study introduces an automated, LLM-enhanced “E”-aware data processing approach for the construction industry. The innovation of this framework is threefold. First, fifteen “E”-aware indicators are meticulously crafted to align with the specific needs of construction entities. Second, an “E”-aware algorithm, integrated within the Building Information Modeling (BIM) framework, is devised to streamline the aggregation and quantification of environmental data. Third, an LLM-enhanced complex structured data processing mechanism using retrieval augmented generation (RAG) is proposed to facilitate the efficient processing of “E”-aware data pertinent to construction projects. An illustrative case study is employed to validate the feasibility and efficacy of the proposed methodology. The results demonstrate that the developed automated RAG-LLM enhanced framework significantly advances current practice by: (1) enabling standardized “E”-aware data specifications and source mapping; (2) drastically reducing processing time for large-scale ESG documentation (saving 64.4% of time); and (3) providing a robust solution for handling multi-source, multi-format data, thereby enhancing the efficiency and reliability of environmental management and ESG disclosure in the AEC industry.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"69 ","pages":"Article 103920"},"PeriodicalIF":9.9,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145220691","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A closed-loop design approach based on the combination of knowledge graph and digital twin: a high-speed train bogie case study","authors":"Xinyu Liu ,&nbsp;Honghui Wang ,&nbsp;Xu Han ,&nbsp;Yunlei Zan ,&nbsp;Jinying Zhang ,&nbsp;Guijie Liu","doi":"10.1016/j.aei.2025.103912","DOIUrl":"10.1016/j.aei.2025.103912","url":null,"abstract":"<div><div>With the increasing complexity of industrial products, data-complete closed-loop feedback design throughout the product lifecycle has become a research frontier in the field of modern intelligent manufacturing. However, the accuracy and efficiency of optimization iterations in existing design methods are hindered by inconsistent formats and semantics of multi-source data, difficulties in dynamically updating model parameters, and challenges in mapping associations between models and data. To address the above issues, this paper proposes a closed-loop design approach based on the combination of knowledge graph (KG) and digital twin (DT). Firstly, the DT model is divided into three dimensions, namely information model, mechanism model and field model, based on metamodel theory, and adopts a unified paradigm expression to improve the generality among models. Then, a multi-dimensional information mapping mechanism based on KG is proposed. It uses KG as an information exchange mediator between physical data and DT models, regulates the interaction of heterogeneous data from multiple sources, and realizes data transmission and mapping between models. On this basis, the DT model parameters are corrected in combination with the querying and reasoning capabilities of the KG to form a continuous feedback knowledge update loop and an enhanced closed-loop design process. Finally, a case study is conducted in the design of high-speed train bogie. The results show that the modification accuracy of the model’s low-order modal frequency is improved to 97.79%, and the maximum stress, lightweight and safety indexes are improved by 14.96%, 13.81% and 2.82%, respectively. Comparative experiments on the next generation bogie show that the iterations of the method have a positive effect, with the stiffness performance improving by up to 17.79% at critical locations.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"69 ","pages":"Article 103912"},"PeriodicalIF":9.9,"publicationDate":"2025-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145158692","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intelligent transformation in the operational maintenance of pumped storage units: Hydraulic-mechanical multi-scenario fault diagnosis based on tensor feature extraction indicators","authors":"Fei Chen ,&nbsp;Zhigao Zhao ,&nbsp;Xiaoxi Hu ,&nbsp;Dong Liu ,&nbsp;Xiuxing Yin ,&nbsp;Jiandong Yang","doi":"10.1016/j.aei.2025.103894","DOIUrl":"10.1016/j.aei.2025.103894","url":null,"abstract":"<div><div>The intelligent transformation of pumped storage units (PSUs) is an essential step in the construction of smart power stations, with intelligent fault diagnosis being a crucial component of this process. Deep mining of anomaly information in massive equipment data is key to achieving fault diagnosis of PSUs, directly influencing the success or failure of intelligent operation and maintenance for power stations. To overcome the challenge of existing feature extraction techniques in jointly mining anomaly information across temporal and spectral domains, this study proposes tensor-weighted fuzzy dispersion entropy (TWFDE), a nonlinear dynamic feature extraction indicator enhanced through tensor learning for multi-scenario hydraulic–mechanical applications in PSUs. This indicator effectively extracts signal state features from the dual space of temporal and spectral domains, and a data-driven diagnostic framework encompassing data acquisition, feature extraction, and pattern recognition is developed around TWFDE. Firstly, a nonlinear dynamics index named weighted fuzzy dispersion entropy (WFDE) is proposed, which combines structural complexity and magnitude quantitative dynamics. Secondly, WFDE is generalized to TWFDE by incorporating hierarchical analysis and multiscale analysis, thereby facilitating the extraction of multi-dimensional anomaly characteristics from the tensor-space perspective. Ultimately, TWFDE and random forest (RF) are fused to construct a data-driven fault diagnostic framework applicable to multiple scenarios. In cases of hydraulic anomaly identification and mechanical fault diagnosis of the micro pumped storage power plant, the model achieves diagnostic accuracies of at least 98.428 % and 99.928 %, respectively, demonstrating significant advantages over other mainstream methods. The proposed feature extraction indicator provides effective support for improving the operation and maintenance level and the energy conversion efficiency of pumped storage hydropower plants.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"69 ","pages":"Article 103894"},"PeriodicalIF":9.9,"publicationDate":"2025-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145158816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The spatiotemporal band-gated modal decomposition method and its application in compound fault diagnosis of gearbox","authors":"Ziyang Ding ,&nbsp;Fucai Li ,&nbsp;Xiaolei Xu ,&nbsp;Haidong Shao","doi":"10.1016/j.aei.2025.103880","DOIUrl":"10.1016/j.aei.2025.103880","url":null,"abstract":"<div><div>Mechanical systems are characterized by complex structures, multi-source vibrations, and strong coupling. Existing multi-channel signal analysis methods do not fully consider the characteristics of fault mechanisms and thus struggle to achieve decoupling and feature extraction for compound faults. To tackle this challenge, this paper proposes a novel multi-channel signal analysis method—Spatiotemporal band-gated modal decomposition (SBGMD). The method consists of three main steps: First, SBGMD decomposes multi-channel signals into temporal and spatial modes, establishing a spatiotemporal representation structure for the signals. Second, by introducing a nonlinear matching pursuit mechanism, the method applies time-varying frequency modulation constraints to the temporal modes, thereby extracting physically interpretable modal components. Finally, by leveraging the unique frequency evolution characteristics of mechanical faults, SBGMD innovatively constructs a band-gated structure. Within this structure, the method iteratively searches for the optimal distribution of sidebands, achieving precise separation of strongly coupled fault features and ultimately extracting fault modal components with interpretable mechanisms. As a multi-channel signal processing method that combines band-gated with spatiotemporal modal decomposition, SBGMD proposes a decomposition strategy based on band-gated characteristics. This strategy closely matches the typical frequency domain manifestations of faults and possesses strong capabilities for feature interpretation and weak signal mining. Therefore, the method effectively extracts and separates multi-source complex coupled feature signals. When being applied to the simulation and experimental signal analysis of compound fault diagnosis in gearboxes, the method exhibits good robustness and superiority in feature extraction and fault identification. Thus, it offers a novel solution for the fault diagnosis of complex mechanical systems.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"69 ","pages":"Article 103880"},"PeriodicalIF":9.9,"publicationDate":"2025-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145220689","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AutoStruct: Intelligent design system for shear wall building structures","authors":"Sixian Chan ,&nbsp;Yage Xia ,&nbsp;Jiafa Mao ,&nbsp;Chao Li","doi":"10.1016/j.aei.2025.103900","DOIUrl":"10.1016/j.aei.2025.103900","url":null,"abstract":"<div><div>Architects and engineers frequently face substantial communication challenges in the building design process. By learning the design experience of structural drawings through neural networks, an automated structural design system can be developed to transfer the structural experience of engineers to architects, effectively reducing communication costs. Currently, research on AI-assisted automated structural design remains in a nascent stage. Existing public models exhibit notable limitations, particularly in their insufficient ability to learn drawing features comprehensively and their high usability thresholds. To overcome these challenges, we present AutoStruct, an intelligent AI-powered system for shear wall structure design. The core innovation of the system lies in its efficient Transformer-Wavelet architecture, which simultaneously captures both global features and local details from structural drawings while enhancing the learning of high-frequency information characteristics, such as wall elements. Specifically, to resolve the common issues of discontinuity and irregular distribution in generated layouts, we develop a computer vision-based post-processing method capable of repairing wall defects across various scales, thereby improving both continuity and surface regularity. Furthermore, our system incorporates a specialized sketch tool customized for architects. This web-based interface enables architects to quickly draft building schematics and input them into the model for structural layout generation, resulting in an easy-to-use and end-to-end automated design process. Finally, through comprehensive experiments on four datasets, we demonstrate that AutoStruct generates layouts that are more consistent with engineers’ designs compared to existing open-source solutions, and also shows its robust generalization capabilities.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"69 ","pages":"Article 103900"},"PeriodicalIF":9.9,"publicationDate":"2025-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145158693","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}