Advanced Engineering Informatics最新文献_第3页

A unified LLM-KG framework for low‑annotation urban rail transit signal system operation: knowledge acquisition and dynamic update 低标注城市轨道交通信号系统运行的统一LLM-KG框架：知识获取和动态更新

IF 9.9 1区工程技术 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Advanced Engineering Informatics

Pub Date : 2026-04-01 Epub Date: 2026-01-24 DOI: 10.1016/j.aei.2026.104327

Wei Cai , Xiaomin Zhu , Zeyu Sun , Aihui Ye , Guanhua Fu , Runtong Zhang

Intelligent operation and maintenance (O&M) of urban rail transit signal systems (URTSS) is essential for ensuring train safety and operational efficiency. However, most O&M data exist as unstructured and sparsely labeled texts, posing major challenges for reliable knowledge extraction, semantic reasoning, and dynamic knowledge management. To address these issues, this paper proposes a unified large language model-knowledge graph framework (ULLM-KG) tailored for low-annotation, knowledge-intensive O&M environments. Firstly, a bidirectional knowledge graph construction mechanism (BKGC) is introduced to rapidly build a domain-specific initial knowledge graph. Secondly, a KG-enhanced distantly supervised entity and event extraction method (KG-DS3E) is designed to enhance critical knowledge extraction accuracy from unstructured texts. Thirdly, a prompt-driven knowledge-enhanced reasoning method (PD-KER) is proposed to improve semantic quality in fault diagnosis and maintenance recommendations. Lastly, a dynamic knowledge graph updating mechanism with temporal awareness and conflict resolution (DKG-UCF) is used to ensure efficient and accurate knowledge evolution. Based on real-world URTSS O&M data, experimental evaluations are conducted on state-of-the-art LLMs (GPT-4o, DeepSeek-V3, and Qwen3-32B). On datasets with varying annotation ratios and rare faults, ULLM-KG demonstrates significantly superior performance in knowledge extraction and reasoning tasks compared to other state-of-the-art methods. Its ability to dynamically update knowledge is also verified to be excellent. ULLM-KG provides a general solution for the intelligent O&M of URTSS under low-annotation conditions.

城市轨道交通信号系统（URTSS）的智能运维是保障列车安全和运行效率的关键。然而，大多数O&；M数据以非结构化和稀疏标记的文本形式存在，这对可靠的知识提取、语义推理和动态知识管理提出了重大挑战。为了解决这些问题，本文提出了一个统一的大型语言模型-知识图框架（ULLM-KG），该框架专为低注释、知识密集型的操作和管理环境量身定制。首先，引入双向知识图谱构建机制（BKGC），快速构建特定领域的初始知识图谱；其次，设计了一种kg增强的远程监督实体和事件提取方法（KG-DS3E），以提高从非结构化文本中提取关键知识的准确性。再次，提出了一种提示驱动的知识增强推理方法（PD-KER），以提高故障诊断和维修建议的语义质量。最后，采用一种具有时间感知和冲突解决的动态知识图更新机制（DKG-UCF）来保证知识进化的高效和准确。基于真实的URTSS o&m数据，在最先进的llm （gpt - 40、DeepSeek-V3和Qwen3-32B）上进行了实验评估。在具有不同标注比率和罕见错误的数据集上，ULLM-KG在知识提取和推理任务中表现出明显优于其他最先进方法的性能。其动态更新知识的能力也被证明是优秀的。ULLM-KG为低标注条件下URTSS的智能运维提供了一种通用的解决方案。

{"title":"A unified LLM-KG framework for low‑annotation urban rail transit signal system operation: knowledge acquisition and dynamic update","authors":"Wei Cai , Xiaomin Zhu , Zeyu Sun , Aihui Ye , Guanhua Fu , Runtong Zhang","doi":"10.1016/j.aei.2026.104327","DOIUrl":"10.1016/j.aei.2026.104327","url":null,"abstract":"<div><div>Intelligent operation and maintenance (O&M) of urban rail transit signal systems (URTSS) is essential for ensuring train safety and operational efficiency. However, most O&M data exist as unstructured and sparsely labeled texts, posing major challenges for reliable knowledge extraction, semantic reasoning, and dynamic knowledge management. To address these issues, this paper proposes a unified large language model-knowledge graph framework (ULLM-KG) tailored for low-annotation, knowledge-intensive O&M environments. Firstly, a bidirectional knowledge graph construction mechanism (BKGC) is introduced to rapidly build a domain-specific initial knowledge graph. Secondly, a KG-enhanced distantly supervised entity and event extraction method (KG-DS3E) is designed to enhance critical knowledge extraction accuracy from unstructured texts. Thirdly, a prompt-driven knowledge-enhanced reasoning method (PD-KER) is proposed to improve semantic quality in fault diagnosis and maintenance recommendations. Lastly, a dynamic knowledge graph updating mechanism with temporal awareness and conflict resolution (DKG-UCF) is used to ensure efficient and accurate knowledge evolution. Based on real-world URTSS O&M data, experimental evaluations are conducted on state-of-the-art LLMs (GPT-4o, DeepSeek-V3, and Qwen3-32B). On datasets with varying annotation ratios and rare faults, ULLM-KG demonstrates significantly superior performance in knowledge extraction and reasoning tasks compared to other state-of-the-art methods. Its ability to dynamically update knowledge is also verified to be excellent. ULLM-KG provides a general solution for the intelligent O&M of URTSS under low-annotation conditions.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"71 ","pages":"Article 104327"},"PeriodicalIF":9.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146078379","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}

引用次数: 0

Vision–proprioception fusion with Mamba2 in end-to-end reinforcement learning for motion control 基于Mamba2的视觉本体感觉融合在端到端运动控制强化学习中的应用

IF 9.9 1区工程技术 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Advanced Engineering Informatics

Pub Date : 2026-04-01 Epub Date: 2026-01-29 DOI: 10.1016/j.aei.2026.104389

Xiaowen Tao , Yinuo Wang , Jinzhao Zhou

End-to-end reinforcement learning (RL) for motion control trains policies directly from sensor inputs to motor commands, enabling unified controllers for different robots and tasks. However, most existing methods are either blind (proprioception-only) or rely on fusion backbones with unfavorable compute–memory trade-offs. Recurrent controllers struggle with long-horizon credit assignment, and Transformer-based fusion incurs quadratic cost in token length, limiting temporal and spatial context. We present a vision-driven cross-modal RL framework built on SSD-Mamba2, a selective state–space backbone that applies state–space duality (SSD) to enable both recurrent and convolutional scanning with hardware-aware streaming and near-linear scaling. Proprioceptive states and exteroceptive observations (e.g., depth tokens) are encoded into compact tokens and fused by stacked SSD-Mamba2 layers. The selective state–space updates retain long-range dependencies with markedly lower latency and memory use than quadratic self-attention, enabling longer look-ahead, higher token resolution, and stable training under limited compute. Policies are trained end-to-end under curricula that randomize terrain and appearance and progressively increase scene complexity. A compact, state-centric reward balances task progress, energy efficiency, and safety. Across diverse motion-control scenarios, our approach consistently surpasses strong state-of-the-art baselines in return, safety (collisions and falls), and sample efficiency, while converging faster at the same compute budget. These results suggest that SSD-Mamba2 provides a practical fusion backbone for resource-constrained robotic and autonomous systems in engineering informatics applications.

用于运动控制的端到端强化学习（RL）直接从传感器输入到电机命令训练策略，为不同的机器人和任务实现统一的控制器。然而，大多数现有的方法要么是盲目的（只有本体感觉），要么依赖于融合主干，不利于计算内存的权衡。循环控制器与长期信用分配斗争，基于变压器的融合在令牌长度上产生二次成本，限制了时间和空间背景。我们提出了一个基于SSD- mamba2的视觉驱动的跨模态RL框架，这是一个选择性的状态空间主干，它应用状态空间对偶性（SSD）来实现循环扫描和卷积扫描，具有硬件感知流和近线性缩放。本体感觉状态和外感受观察（如深度标记）被编码成紧凑的标记，并通过堆叠的SSD-Mamba2层融合。选择性状态空间更新保留了长期依赖关系，比二次型自关注具有明显更低的延迟和内存使用，支持更长的前瞻性、更高的令牌分辨率和有限计算下的稳定训练。策略在随机化地形和外观并逐渐增加场景复杂性的课程中进行端到端训练。紧凑的、以国家为中心的奖励平衡了任务进度、能源效率和安全。在不同的运动控制场景中，我们的方法在回报、安全性（碰撞和坠落）和样本效率方面始终超过最先进的基线，同时在相同的计算预算下收敛得更快。这些结果表明，SSD-Mamba2为工程信息学应用中资源受限的机器人和自主系统提供了实用的融合骨干。

{"title":"Vision–proprioception fusion with Mamba2 in end-to-end reinforcement learning for motion control","authors":"Xiaowen Tao , Yinuo Wang , Jinzhao Zhou","doi":"10.1016/j.aei.2026.104389","DOIUrl":"10.1016/j.aei.2026.104389","url":null,"abstract":"<div><div>End-to-end reinforcement learning (RL) for motion control trains policies directly from sensor inputs to motor commands, enabling unified controllers for different robots and tasks. However, most existing methods are either <em>blind</em> (proprioception-only) or rely on fusion backbones with unfavorable compute–memory trade-offs. Recurrent controllers struggle with long-horizon credit assignment, and Transformer-based fusion incurs quadratic cost in token length, limiting temporal and spatial context. We present a vision-driven cross-modal RL framework built on <em>SSD-Mamba2</em>, a selective state–space backbone that applies <em>state–space duality (SSD)</em> to enable both recurrent and convolutional scanning with hardware-aware streaming and near-linear scaling. Proprioceptive states and exteroceptive observations (e.g., depth tokens) are encoded into compact tokens and fused by stacked SSD-Mamba2 layers. The selective state–space updates retain long-range dependencies with markedly lower latency and memory use than quadratic self-attention, enabling longer look-ahead, higher token resolution, and stable training under limited compute. Policies are trained end-to-end under curricula that randomize terrain and appearance and progressively increase scene complexity. A compact, state-centric reward balances task progress, energy efficiency, and safety. Across diverse motion-control scenarios, our approach consistently surpasses strong state-of-the-art baselines in return, safety (collisions and falls), and sample efficiency, while converging faster at the same compute budget. These results suggest that SSD-Mamba2 provides a practical fusion backbone for resource-constrained robotic and autonomous systems in engineering informatics applications.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"71 ","pages":"Article 104389"},"PeriodicalIF":9.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146077879","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}

引用次数: 0

Physics-informed edge-enhanced temporal graph convolutional network for multi-risk evolution prediction in deep excavation 基于物理信息的边缘增强时间图卷积网络在深基坑多风险演化预测中的应用

IF 9.9 1区工程技术 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Advanced Engineering Informatics

Pub Date : 2026-04-01 Epub Date: 2026-02-03 DOI: 10.1016/j.aei.2026.104391

Jian Wei, Yue Pan, Jin-Jian Chen

Accurate prediction of excavation-induced multi-risk evolution is essential for intelligent construction and on-site safety management. This study proposes a Physics-Informed Edge-Enhanced Temporal Graph Convolutional Network (PI-ETGCN) that seamlessly integrates mechanistic priors with data-driven learning for spatiotemporal multi-risk forecasting in deep excavations. During graph modeling, multi-source construction information is encoded as node attributes to construct a Multi-Source Risk Graph (MRG) that links heterogeneous variables across space and time. Mechanical laws governing wall–soil–pipeline interactions are parameterized with learnable edge coefficients, enabling adaptive modeling of spatial–physical couplings under varying construction conditions. During graph learning, PI-ETGCN combines edge-enhanced graph convolution with temporal modules to capture coupled data–mechanics relationships and spatiotemporal dependencies within the MRG. A physics-informed regularization term is incorporated into the training objective to promote mechanically consistent risk-evolution patterns and improve robustness and generalization. Validated on a real-world Shanghai Rail Transit project, PI-ETGCN delivers superior predictive performance, reducing errors by over 20% relative to the second-best baseline. Ablation studies further confirm that the proposed physics–data fusion strategy maintains high accuracy under limited samples, noise, and outliers. Overall, PI-ETGCN provides interpretable, decision-ready risk information for real-time monitoring and reliability-aware on-site safety management.

准确预测开挖引发的多风险演化，对智能施工和现场安全管理至关重要。该研究提出了一种基于物理信息的边缘增强时态图卷积网络（PI-ETGCN），该网络将机械先验与数据驱动学习无缝集成，用于深度挖掘的时空多风险预测。在图建模过程中，将多源构建信息编码为节点属性，构建跨空间和时间连接异构变量的多源风险图（MRG）。控制墙-土-管道相互作用的力学规律用可学习的边缘系数参数化，使空间-物理耦合在不同施工条件下的自适应建模成为可能。在图学习过程中，PI-ETGCN将边缘增强的图卷积与时间模块相结合，以捕获MRG内的耦合数据力学关系和时空依赖关系。一个物理信息正则化项被纳入训练目标，以促进机械一致的风险演化模式，提高鲁棒性和泛化。经过上海轨道交通实际项目的验证，PI-ETGCN提供了卓越的预测性能，相对于第二好的基线减少了20%以上的误差。消融研究进一步证实了所提出的物理数据融合策略在有限的样本、噪声和异常值下保持了很高的精度。总体而言，PI-ETGCN为实时监控和可靠性感知现场安全管理提供了可解释的、决策就绪的风险信息。

{"title":"Physics-informed edge-enhanced temporal graph convolutional network for multi-risk evolution prediction in deep excavation","authors":"Jian Wei, Yue Pan, Jin-Jian Chen","doi":"10.1016/j.aei.2026.104391","DOIUrl":"10.1016/j.aei.2026.104391","url":null,"abstract":"<div><div>Accurate prediction of excavation-induced multi-risk evolution is essential for intelligent construction and on-site safety management. This study proposes a Physics-Informed Edge-Enhanced Temporal Graph Convolutional Network (PI-ETGCN) that seamlessly integrates mechanistic priors with data-driven learning for spatiotemporal multi-risk forecasting in deep excavations. During graph modeling, multi-source construction information is encoded as node attributes to construct a Multi-Source Risk Graph (MRG) that links heterogeneous variables across space and time. Mechanical laws governing wall–soil–pipeline interactions are parameterized with learnable edge coefficients, enabling adaptive modeling of spatial–physical couplings under varying construction conditions. During graph learning, PI-ETGCN combines edge-enhanced graph convolution with temporal modules to capture coupled data–mechanics relationships and spatiotemporal dependencies within the MRG. A physics-informed regularization term is incorporated into the training objective to promote mechanically consistent risk-evolution patterns and improve robustness and generalization. Validated on a real-world Shanghai Rail Transit project, PI-ETGCN delivers superior predictive performance, reducing errors by over 20% relative to the second-best baseline. Ablation studies further confirm that the proposed physics–data fusion strategy maintains high accuracy under limited samples, noise, and outliers. Overall, PI-ETGCN provides interpretable, decision-ready risk information for real-time monitoring and reliability-aware on-site safety management.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"71 ","pages":"Article 104391"},"PeriodicalIF":9.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146188617","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}

引用次数: 0

Motion system modeling and acceleration analysis of five-axis hybrid machine tool 五轴混合动力机床运动系统建模及加速度分析

IF 9.9 1区工程技术 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Advanced Engineering Informatics

Pub Date : 2026-04-01 Epub Date: 2026-02-04 DOI: 10.1016/j.aei.2026.104368

Guang Yu , Jia Liu , Lai Hu , Anbang Jiang , Liping Wang

Aiming to improve the machining efficiency and accuracy of five-axis hybrid machine tool (FaHMT), the kinematics system of FaHMT was modeled. According to the kinematics model, the velocity mapping model and error transfer model of the FaHMT were obtained by derivation and perturbation differentiation. The three-loop control model of permanent magnet synchronous motor used in machine tools was focused on modeling. Meanwhile, the mapping characteristics of the movement speed of the tool and the feed speed of each driving shaft under different postures of the parallel mechanism were analyzed. In the acceleration experiment, the position where the inflection point of error change appeared at a = 4.6 mm/s². When the acceleration was greater than this value, the X_W axis follow-up error increased significantly. For Z₁, Z₂ and Z₃ axes, their movement positions and errors were consistent basically. The modeling method and practical conclusions analyzed provide effective theoretical support and experimental verification for studying kinematics and acceleration analysis of FaHMT.

为了提高五轴混合动力机床的加工效率和加工精度，对五轴混合动力机床的运动系统进行了建模。在运动学模型的基础上，通过导数和微扰微分，建立了FaHMT的速度映射模型和误差传递模型。重点研究了机床用永磁同步电机三环控制模型的建模。同时，分析了并联机构不同姿态下刀具运动速度与各传动轴进给速度的映射特性。在加速度实验中，误差变化拐点出现的位置为a = 4.6 mm/s2。当加速度大于该值时，XW轴随动误差明显增大。对于Z1、Z2和Z3轴，它们的运动位置和误差基本一致。所分析的建模方法和实际结论为研究FaHMT的运动学和加速度分析提供了有效的理论支持和实验验证。

{"title":"Motion system modeling and acceleration analysis of five-axis hybrid machine tool","authors":"Guang Yu , Jia Liu , Lai Hu , Anbang Jiang , Liping Wang","doi":"10.1016/j.aei.2026.104368","DOIUrl":"10.1016/j.aei.2026.104368","url":null,"abstract":"<div><div>Aiming to improve the machining efficiency and accuracy of five-axis hybrid machine tool (FaHMT), the kinematics system of FaHMT was modeled. According to the kinematics model, the velocity mapping model and error transfer model of the FaHMT were obtained by derivation and perturbation differentiation. The three-loop control model of permanent magnet synchronous motor used in machine tools was focused on modeling. Meanwhile, the mapping characteristics of the movement speed of the tool and the feed speed of each driving shaft under different postures of the parallel mechanism were analyzed. In the acceleration experiment, the position where the inflection point of error change appeared at <em>a</em> = 4.6 mm/s<sup>2</sup>. When the acceleration was greater than this value, the <em>X<sub>W</sub></em> axis follow-up error increased significantly. For <em>Z</em><sub>1</sub>, <em>Z</em><sub>2</sub> and <em>Z</em><sub>3</sub> axes, their movement positions and errors were consistent basically. The modeling method and practical conclusions analyzed provide effective theoretical support and experimental verification for studying kinematics and acceleration analysis of FaHMT.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"71 ","pages":"Article 104368"},"PeriodicalIF":9.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146188618","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}

引用次数: 0

A Multi-Source Attention Graph Neural Network for modeling long and short-term dependencies in chemical process forecasting 化工过程预测中长、短期依赖关系建模的多源注意图神经网络

IF 9.9 1区工程技术 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Advanced Engineering Informatics

Pub Date : 2026-04-01 Epub Date: 2026-02-05 DOI: 10.1016/j.aei.2026.104395

Jian Long , Bin Wang , Haifei Peng , Hengmin Zhang

Chemical process data exhibit both long-term physical dependencies and short-term dynamic variations due to complex interactions among variables. To simultaneously model these heterogeneous dependencies, this paper proposes a Multi-Source Attention Graph Neural Network (MSAGNN) for soft sensing in chemical processes. MSAGNN adopts a dual-path graph recurrent architecture, where a static graph encodes prior physical relationships, and an adaptive graph structure learning module dynamically captures time-varying correlations from data. A multi-source attention mechanism is further introduced to integrate node and neighborhood information and enhance the representation of spatial–temporal dependencies. The proposed MSAGNN is evaluated on three representative industrial processes, including the Debutanizer Column (DC), the Tennessee Eastman (TE) process, and the Fluid Catalytic Cracking (FCC) unit. Experimental results show that MSAGNN consistently achieves lower RMSE, MAE, and MAPE, and higher R

^{2}

than state-of-the-art deep learning and graph-based models, demonstrating its superior prediction accuracy and robustness. Visualization of the learned dynamic graphs and attention scores indicates that MSAGNN can reveal meaningful variable interactions, confirming the effectiveness and interpretability of the proposed approach for complex chemical processes.

化学过程数据既表现出长期的物理依赖性，又表现出由于变量之间复杂的相互作用而产生的短期动态变化。为了同时对这些异构依赖性进行建模，本文提出了一种用于化工过程软检测的多源注意图神经网络（MSAGNN）。MSAGNN采用双路径图循环架构，其中静态图编码先验物理关系，自适应图结构学习模块动态捕获数据中的时变相关性。进一步引入多源关注机制，整合节点和邻域信息，增强时空依赖关系的表征。在三个具有代表性的工业过程中，包括脱硝塔（DC）、田纳西伊士曼（TE）过程和流体催化裂化（FCC）装置，对所提出的MSAGNN进行了评估。实验结果表明，与最先进的深度学习和基于图的模型相比，MSAGNN的RMSE、MAE和MAPE均较低，R2较高，显示了其优越的预测精度和鲁棒性。学习到的动态图和注意力分数的可视化表明，MSAGNN可以揭示有意义的变量相互作用，证实了所提出的方法在复杂化学过程中的有效性和可解释性。

{"title":"A Multi-Source Attention Graph Neural Network for modeling long and short-term dependencies in chemical process forecasting","authors":"Jian Long , Bin Wang , Haifei Peng , Hengmin Zhang","doi":"10.1016/j.aei.2026.104395","DOIUrl":"10.1016/j.aei.2026.104395","url":null,"abstract":"<div><div>Chemical process data exhibit both long-term physical dependencies and short-term dynamic variations due to complex interactions among variables. To simultaneously model these heterogeneous dependencies, this paper proposes a Multi-Source Attention Graph Neural Network (MSAGNN) for soft sensing in chemical processes. MSAGNN adopts a dual-path graph recurrent architecture, where a static graph encodes prior physical relationships, and an adaptive graph structure learning module dynamically captures time-varying correlations from data. A multi-source attention mechanism is further introduced to integrate node and neighborhood information and enhance the representation of spatial–temporal dependencies. The proposed MSAGNN is evaluated on three representative industrial processes, including the Debutanizer Column (DC), the Tennessee Eastman (TE) process, and the Fluid Catalytic Cracking (FCC) unit. Experimental results show that MSAGNN consistently achieves lower RMSE, MAE, and MAPE, and higher R<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span> than state-of-the-art deep learning and graph-based models, demonstrating its superior prediction accuracy and robustness. Visualization of the learned dynamic graphs and attention scores indicates that MSAGNN can reveal meaningful variable interactions, confirming the effectiveness and interpretability of the proposed approach for complex chemical processes.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"71 ","pages":"Article 104395"},"PeriodicalIF":9.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146188619","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}

引用次数: 0

Real-time multimodal fusion and semantic mapping for robotic tower crane perception 机器人塔吊感知的实时多模态融合与语义映射

IF 9.9 1区工程技术 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Advanced Engineering Informatics

Pub Date : 2026-04-01 Epub Date: 2026-02-05 DOI: 10.1016/j.aei.2026.104373

Yifan Lu , Xiuzhi Deng , Peter E.D. Love , Wei Zhou , Weili Fang

Robotic tower crane operation requires real-time perception of complex and rapidly changing construction environments. Conventional Simultaneous Localization and Mapping (SLAM) methods assume smooth sensor motion and emphasize geometry over semantics, limiting their suitability for crane-mounted sensing affected by vibration, rotation, and intermittent movement. This research proposes a multimodal perception framework that integrates Light Detection and Ranging (LiDAR), camera, and Inertial Measurement Unit (IMU) data within a tightly coupled fusion and semantic reconstruction pipeline. A Mahony-filter-based attitude optimization module stabilizes high-frequency vibrations, while a Fast LiDAR-Inertial Odometry (FAST-LIVO2)-inspired LiDAR–visual–inertial fusion strategy achieves centimeter-level three-dimensional (3D) mapping. To enhance scene understanding, an improved Random Sampled and Lightweight Aggregated Network (RandLA-Net) jointly exploits geometric and visual cues for point-level semantic segmentation, with color-aware spatial encoding. Field deployment on an operational tower crane demonstrates superior performance, yielding the lowest global reconstruction errors and highest semantic accuracy. The framework provides a robust perception foundation for autonomous planning, safety monitoring, and intelligent lifting assistance.

机器人塔式起重机操作需要实时感知复杂和快速变化的施工环境。传统的同步定位和测绘（SLAM）方法假设传感器运动平滑，强调几何而不是语义，限制了它们对受振动、旋转和间歇性运动影响的起重机安装传感的适用性。本研究提出了一个多模态感知框架，该框架将光探测和测距（LiDAR）、相机和惯性测量单元（IMU）数据集成在一个紧密耦合的融合和语义重建管道中。基于mahoney滤波器的姿态优化模块可稳定高频振动，而受Fast - livo2启发的快速激光雷达-惯性里程计（Fast - livo2）激光雷达-视觉-惯性融合策略可实现厘米级三维（3D）映射。为了增强场景理解，改进的随机采样和轻量级聚合网络（RandLA-Net）结合颜色感知空间编码，共同利用几何和视觉线索进行点级语义分割。在塔式起重机上的现场部署显示出卓越的性能，产生最低的全局重建误差和最高的语义精度。该框架为自主规划、安全监控和智能起重辅助提供了强大的感知基础。

{"title":"Real-time multimodal fusion and semantic mapping for robotic tower crane perception","authors":"Yifan Lu , Xiuzhi Deng , Peter E.D. Love , Wei Zhou , Weili Fang","doi":"10.1016/j.aei.2026.104373","DOIUrl":"10.1016/j.aei.2026.104373","url":null,"abstract":"<div><div>Robotic tower crane operation requires real-time perception of complex and rapidly changing construction environments. Conventional Simultaneous Localization and Mapping (SLAM) methods assume smooth sensor motion and emphasize geometry over semantics, limiting their suitability for crane-mounted sensing affected by vibration, rotation, and intermittent movement. This research proposes a multimodal perception framework that integrates Light Detection and Ranging (LiDAR), camera, and Inertial Measurement Unit (IMU) data within a tightly coupled fusion and semantic reconstruction pipeline. A Mahony-filter-based attitude optimization module stabilizes high-frequency vibrations, while a Fast LiDAR-Inertial Odometry (FAST-LIVO2)-inspired LiDAR–visual–inertial fusion strategy achieves centimeter-level three-dimensional (3D) mapping. To enhance scene understanding, an improved Random Sampled and Lightweight Aggregated Network (RandLA-Net) jointly exploits geometric and visual cues for point-level semantic segmentation, with color-aware spatial encoding. Field deployment on an operational tower crane demonstrates superior performance, yielding the lowest global reconstruction errors and highest semantic accuracy. The framework provides a robust perception foundation for autonomous planning, safety monitoring, and intelligent lifting assistance.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"71 ","pages":"Article 104373"},"PeriodicalIF":9.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146188700","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}

引用次数: 0

Multi-fidelity Kriging method based on active and ensemble learning for structural reliability analysis 基于主动学习和集成学习的结构可靠性分析多保真度Kriging方法

IF 9.9 1区工程技术 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Advanced Engineering Informatics

Pub Date : 2026-04-01 Epub Date: 2026-02-07 DOI: 10.1016/j.aei.2026.104411

Bingyi Li , Qian Zhao , Xiang Jia , Guang Jin

Structural reliability analysis (SRA) plays an important role in uncertainty theory and engineering application. A basic problem is estimating failure probability, and a popular idea is sequential strategy. With digital twin and alternative technologies, multiple data sources, considered as different fidelities, are available, including physical experiments and simulations. Multi-fidelity (MF) data include finite high-fidelity (HF) data and abundant low-fidelity (LF) data. MF methods for SRA tend to focus on single aspects to select more samples, and the TC (termination criterion) are fixed, limiting efficiency and prediction accuracy. To address these issues, an MF-Kriging method based on active learning and ensemble learning is proposed herein. First, a MF-Kriging model is constructed using initial LF and HF samples. Second, a multi-fidelity ensemble learning function (MELF) framework determines the position and fidelity of the next ideal sample. This framework provides rich information on learning functions and three factors connecting different fidelities. The TC based on double stability of relative error and solution convergence process balances accuracy and efficiency. Finally, results of five numerical examples and two application cases show that the proposed method can estimate failure probabilities with high efficiencies, high accuracies, and low costs.

结构可靠度分析（SRA）在不确定性理论和工程应用中占有重要地位。一个基本问题是估计故障概率，一个流行的想法是顺序策略。使用数字孪生和替代技术，可以使用多种被认为是不同保真度的数据源，包括物理实验和模拟。多保真度（MF）数据包括有限的高保真度（HF）数据和丰富的低保真度（LF）数据。用于SRA的MF方法往往侧重于单一方面以选择更多的样本，并且TC（终止准则）是固定的，限制了效率和预测精度。为了解决这些问题，本文提出了一种基于主动学习和集成学习的MF-Kriging方法。首先，利用初始LF和HF样本构建MF-Kriging模型。其次，多保真度集成学习函数（MELF）框架确定下一个理想样本的位置和保真度。该框架提供了丰富的学习功能信息和连接不同保真度的三个因素。基于相对误差和解收敛过程双重稳定性的TC平衡了精度和效率。最后，5个数值算例和2个应用实例的结果表明，该方法具有效率高、精度高、成本低等优点。

{"title":"Multi-fidelity Kriging method based on active and ensemble learning for structural reliability analysis","authors":"Bingyi Li , Qian Zhao , Xiang Jia , Guang Jin","doi":"10.1016/j.aei.2026.104411","DOIUrl":"10.1016/j.aei.2026.104411","url":null,"abstract":"<div><div>Structural reliability analysis (SRA) plays an important role in uncertainty theory and engineering application. A basic problem is estimating failure probability, and a popular idea is sequential strategy. With digital twin and alternative technologies, multiple data sources, considered as different fidelities, are available, including physical experiments and simulations. Multi-fidelity (MF) data include finite high-fidelity (HF) data and abundant low-fidelity (LF) data. MF methods for SRA tend to focus on single aspects to select more samples, and the TC (termination criterion) are fixed, limiting efficiency and prediction accuracy. To address these issues, an MF-Kriging method based on active learning and ensemble learning is proposed herein. First, a MF-Kriging model is constructed using initial LF and HF samples. Second, a multi-fidelity ensemble learning function (MELF) framework determines the position and fidelity of the next ideal sample. This framework provides rich information on learning functions and three factors connecting different fidelities. The TC based on double stability of relative error and solution convergence process balances accuracy and efficiency. Finally, results of five numerical examples and two application cases show that the proposed method can estimate failure probabilities with high efficiencies, high accuracies, and low costs.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"71 ","pages":"Article 104411"},"PeriodicalIF":9.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146188823","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}

引用次数: 0

Hybrid-sequence self-learning model: Unsupervised anomaly detection and localization in multivariate time series 混合序列自学习模型：多变量时间序列的无监督异常检测与定位

IF 9.9 1区工程技术 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Advanced Engineering Informatics

Pub Date : 2026-04-01 Epub Date: 2026-02-11 DOI: 10.1016/j.aei.2026.104415

Mingjie Hou , Zhenyu Liu , Jiacheng Sun , Guodong Sa , Zhinan Li , Jianrong Tan

Throughout the operational lifecycle of equipment, extensive multivariate time series are generated, encapsulating critical status information about the equipment. Accurately detecting anomalous sensor data and precisely localizing these positions pose significant challenges. To address these, a hybrid-sequence self-learning model is proposed for unsupervised anomaly detection and localization in multivariate time series of equipment. This model incorporates forward-sequence, reverse-sequence, and random-sequence features into its analysis processes. Key components include a Siamese Network prediction module trained on forward-sequence and reverse-sequence, a generative reconstruction module trained on random-sequence, and a joint inference module. Leveraging a hybrid-sequence self-learning mechanism, the model autonomously learns sequence patterns from multivariate time series, enabling it to adapt to complex behaviors under varying operating conditions. Its joint inference mechanism, which combines prediction and reconstruction errors, significantly enhances the accuracy and reliability of anomaly detection. Experimental studies on computer numerical control (CNC) machine tools spindle and CNC grinder machining processes demonstrate that the proposed model surpasses state-of-the-art models in accurately identifying the timing of anomalies in multivariate time series. These findings confirm the superiority and practicality of the methodology in industrial applications, providing robust technical support for intelligent manufacturing.

在设备的整个运行周期中，会生成大量的多变量时间序列，其中包含了设备的关键状态信息。准确检测异常传感器数据并精确定位这些位置构成了重大挑战。为了解决这些问题，提出了一种混合序列自学习模型，用于设备多变量时间序列的无监督异常检测和定位。该模型将正向序列、反向序列和随机序列特征纳入其分析过程。关键组件包括基于正序和反序训练的Siamese网络预测模块、基于随机序列训练的生成重建模块和联合推理模块。该模型利用混合序列自学习机制，从多变量时间序列中自主学习序列模式，使其能够适应不同操作条件下的复杂行为。其联合推理机制将预测误差与重构误差相结合，显著提高了异常检测的准确性和可靠性。对数控机床主轴和数控磨床加工过程的实验研究表明，所提出的模型在准确识别多变量时间序列异常时间方面优于目前最先进的模型。这些研究结果证实了该方法在工业应用中的优越性和实用性，为智能制造提供了强有力的技术支持。

{"title":"Hybrid-sequence self-learning model: Unsupervised anomaly detection and localization in multivariate time series","authors":"Mingjie Hou , Zhenyu Liu , Jiacheng Sun , Guodong Sa , Zhinan Li , Jianrong Tan","doi":"10.1016/j.aei.2026.104415","DOIUrl":"10.1016/j.aei.2026.104415","url":null,"abstract":"<div><div>Throughout the operational lifecycle of equipment, extensive multivariate time series are generated, encapsulating critical status information about the equipment. Accurately detecting anomalous sensor data and precisely localizing these positions pose significant challenges. To address these, a hybrid-sequence self-learning model is proposed for unsupervised anomaly detection and localization in multivariate time series of equipment. This model incorporates forward-sequence, reverse-sequence, and random-sequence features into its analysis processes. Key components include a Siamese Network prediction module trained on forward-sequence and reverse-sequence, a generative reconstruction module trained on random-sequence, and a joint inference module. Leveraging a hybrid-sequence self-learning mechanism, the model autonomously learns sequence patterns from multivariate time series, enabling it to adapt to complex behaviors under varying operating conditions. Its joint inference mechanism, which combines prediction and reconstruction errors, significantly enhances the accuracy and reliability of anomaly detection. Experimental studies on computer numerical control (CNC) machine tools spindle and CNC grinder machining processes demonstrate that the proposed model surpasses state-of-the-art models in accurately identifying the timing of anomalies in multivariate time series. These findings confirm the superiority and practicality of the methodology in industrial applications, providing robust technical support for intelligent manufacturing.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"71 ","pages":"Article 104415"},"PeriodicalIF":9.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146188745","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}

引用次数: 0

Mapping high-resolution real estate value distribution: a multi-attention deep generative model inspired by image inpainting 高分辨率房地产价值分布映射：基于图像绘画的多注意力深度生成模型

IF 9.9 1区工程技术 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Advanced Engineering Informatics

Pub Date : 2026-04-01 Epub Date: 2026-02-01 DOI: 10.1016/j.aei.2026.104386

Feifeng Jiang , Jun Ma

Accurate real estate valuation is essential for urban planning, investment, and policy development. Traditional point-based methods treat properties as isolated units, oversimplifying complex urban environments and failing to capture spatial interactions and continuous value variation for informed decision-making. This study introduces REIN (Real Estate Inpainting Network), a novel deep generative model that leverages both local and surrounding context to predict high-resolution, spatially continuous property value distributions. By reframing valuation as a spatial inpainting task, REIN transforms multi-source urban data into image-like inputs and employs a hybrid multi-attention architecture—integrating channel–spatial interactions and dense–sparse contextual dependencies—to learn urban spatial structure and infer center values from their surroundings. A relative value estimation strategy further enhances adaptability across diverse regions. Applied to New York City, REIN outperforms existing models in both accuracy and visual coherence, demonstrating the effectiveness of its attention mechanisms and context-to-center inference strategy in property valuation. The model also exhibits strong generalizability under missing spatial context, incomplete features, and cross-region transfer, making it suitable for data-scarce planning scenarios. Feature importance analysis through the Squeeze-and-Excitation block reveals globally consistent and regionally adaptive value drivers across heterogeneous settings. By combining predictive precision, adaptivity, and interpretability, REIN provides an engineering informatics framework that supports planning simulations and data-driven urban policy decisions.

准确的房地产估值对城市规划、投资和政策制定至关重要。传统的基于点的方法将属性视为孤立的单元，过度简化了复杂的城市环境，无法捕捉空间相互作用和连续的价值变化，从而无法做出明智的决策。本研究引入了REIN (Real Estate Inpainting Network)，这是一种新颖的深度生成模型，它利用本地和周围环境来预测高分辨率、空间连续的财产价值分布。通过将评估重新定义为空间绘制任务，REIN将多源城市数据转换为类似图像的输入，并采用混合多关注架构（集成通道-空间交互和密集-稀疏上下文依赖）来学习城市空间结构并从周围环境中推断中心值。相对价值估计策略进一步增强了跨不同区域的适应性。在纽约市的应用中，REIN在准确性和视觉一致性方面都优于现有模型，证明了其注意机制和上下文到中心推理策略在房地产估值中的有效性。该模型在空间背景缺失、特征不完整、跨区域迁移等情况下具有较强的泛化能力，适用于数据稀缺的规划场景。通过挤压和激励块进行特征重要性分析，揭示了跨异构设置的全球一致和区域自适应的价值驱动因素。通过结合预测精度、适应性和可解释性，REIN提供了一个工程信息学框架，支持规划模拟和数据驱动的城市政策决策。

{"title":"Mapping high-resolution real estate value distribution: a multi-attention deep generative model inspired by image inpainting","authors":"Feifeng Jiang , Jun Ma","doi":"10.1016/j.aei.2026.104386","DOIUrl":"10.1016/j.aei.2026.104386","url":null,"abstract":"<div><div>Accurate real estate valuation is essential for urban planning, investment, and policy development. Traditional point-based methods treat properties as isolated units, oversimplifying complex urban environments and failing to capture spatial interactions and continuous value variation for informed decision-making. This study introduces REIN (Real Estate Inpainting Network), a novel deep generative model that leverages both local and surrounding context to predict high-resolution, spatially continuous property value distributions. By reframing valuation as a spatial inpainting task, REIN transforms multi-source urban data into image-like inputs and employs a hybrid multi-attention architecture—integrating channel–spatial interactions and dense–sparse contextual dependencies—to learn urban spatial structure and infer center values from their surroundings. A relative value estimation strategy further enhances adaptability across diverse regions. Applied to New York City, REIN outperforms existing models in both accuracy and visual coherence, demonstrating the effectiveness of its attention mechanisms and context-to-center inference strategy in property valuation. The model also exhibits strong generalizability under missing spatial context, incomplete features, and cross-region transfer, making it suitable for data-scarce planning scenarios. Feature importance analysis through the Squeeze-and-Excitation block reveals globally consistent and regionally adaptive value drivers across heterogeneous settings. By combining predictive precision, adaptivity, and interpretability, REIN provides an engineering informatics framework that supports planning simulations and data-driven urban policy decisions.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"71 ","pages":"Article 104386"},"PeriodicalIF":9.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146188922","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}

引用次数: 0

Hierarchical system decomposition and semantic enrichment of BIM for lifecycle support of MEP systems 面向MEP系统生命周期支持的BIM分层系统分解和语义丰富

IF 9.9 1区工程技术 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Advanced Engineering Informatics

Pub Date : 2026-04-01 Epub Date: 2026-02-11 DOI: 10.1016/j.aei.2026.104428

Zhuohao Zhang , Weiya Chen , Jianhua Cai , Hanbin Luo , Miroslaw Skibniewski

The effective lifecycle management of modular Mechanical, Electrical, and Plumbing (MEP) systems is often compromised by a significant data gap between the digital design in Building Information Modeling (BIM) and the as-built conditions of prefabricated components. This paper specifically addresses the challenge of defining and structuring functionally independent component groups, or ’blocks,’ within complex BIM models that lack explicit system-level semantics and suffer from disorganized data. To solve this, a framework was proposed for hierarchical MEP system decomposition and semantic enrichment and implemented through a hybrid topological-geometric matching method that first identifies all structurally identical component assemblies via a topological search and then verifies these candidates by comparing their morphological signatures. Experimental validation demonstrates the method’s high accuracy and scalability, achieving an F1-score of 0.98, near-linear time complexity, and above 99% precision in large-scale applications, as verified by domain experts. This research provides a robust, bottom-up approach to automatically populate a structured system hierarchy, bridging the critical data gap between the design model and physical, prefabricated modules. By creating semantically enriched and well-structured models, this work establishes a foundational data layer that enables future advancements in automated quantity take-off, modular maintenance, and end-of-life management, such as component reuse.

模块化机械、电气和管道（MEP）系统的有效生命周期管理经常受到建筑信息模型（BIM）中的数字设计与预制组件的建成条件之间的重大数据差距的影响。本文特别解决了在复杂的BIM模型中定义和构建功能独立的组件组（或“块”）的挑战，这些模型缺乏明确的系统级语义，并且受到数据混乱的影响。为了解决这一问题，提出了一种分层MEP系统分解和语义丰富框架，并通过混合拓扑-几何匹配方法实现，该方法首先通过拓扑搜索识别所有结构相同的组件组件，然后通过比较它们的形态特征来验证这些候选组件。实验验证表明，该方法具有较高的准确度和可扩展性，经领域专家验证，在大规模应用中，该方法的f1得分为0.98，时间复杂度接近线性，精度在99%以上。这项研究提供了一种健壮的、自下而上的方法来自动填充结构化的系统层次结构，弥合了设计模型和物理预制模块之间的关键数据差距。通过创建语义丰富且结构良好的模型，这项工作建立了一个基础数据层，使自动化数量起飞、模块化维护和生命周期结束管理（例如组件重用）的未来发展成为可能。

{"title":"Hierarchical system decomposition and semantic enrichment of BIM for lifecycle support of MEP systems","authors":"Zhuohao Zhang , Weiya Chen , Jianhua Cai , Hanbin Luo , Miroslaw Skibniewski","doi":"10.1016/j.aei.2026.104428","DOIUrl":"10.1016/j.aei.2026.104428","url":null,"abstract":"<div><div>The effective lifecycle management of modular Mechanical, Electrical, and Plumbing (MEP) systems is often compromised by a significant data gap between the digital design in Building Information Modeling (BIM) and the as-built conditions of prefabricated components. This paper specifically addresses the challenge of defining and structuring functionally independent component groups, or ’blocks,’ within complex BIM models that lack explicit system-level semantics and suffer from disorganized data. To solve this, a framework was proposed for hierarchical MEP system decomposition and semantic enrichment and implemented through a hybrid topological-geometric matching method that first identifies all structurally identical component assemblies via a topological search and then verifies these candidates by comparing their morphological signatures. Experimental validation demonstrates the method’s high accuracy and scalability, achieving an F1-score of 0.98, near-linear time complexity, and above 99% precision in large-scale applications, as verified by domain experts. This research provides a robust, bottom-up approach to automatically populate a structured system hierarchy, bridging the critical data gap between the design model and physical, prefabricated modules. By creating semantically enriched and well-structured models, this work establishes a foundational data layer that enables future advancements in automated quantity take-off, modular maintenance, and end-of-life management, such as component reuse.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"71 ","pages":"Article 104428"},"PeriodicalIF":9.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146188928","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}

引用次数: 0