Advanced Engineering Informatics最新文献

{"title":"Pixel-level concrete crack quantification through super resolution reconstruction and multi-modality fusion","authors":"Mingyang Ren,&nbsp;Yancheng Li,&nbsp;Tasneem Hussain,&nbsp;Yingjie Wu,&nbsp;Jianchun Li","doi":"10.1016/j.aei.2025.103807","DOIUrl":"10.1016/j.aei.2025.103807","url":null,"abstract":"<div><div>Cracks pose severe threats to the integrity of concrete structures and hence timely detection of concrete cracks are essential for assessment and maintenance of built concrete infrastructure. In particular, the accurate quantification of cracks, preferably in pixel-level with assistance of computer vision, has immense value to explicitly assess the in-service concrete structures. However, current approaches fail to capture fine cracks necessary for early-stage damage identification, and lack both accuracy and robustness under challenging environmental conditions. This study introduces a comprehensive concrete crack quantification algorithm based on the integration of super-resolution and multi-modal feature fusion. It incorporates a super-resolution network to recover fine crack details lost due to motion blur, compression artifacts, or low sensor quality, and a multi-modality feature fusion-based segmentation network (SQFormer) designed to improve segmentation accuracy in visually challenging environments. Extensive experiments demonstrate that the proposed method significantly outperforms state-of-the-art approaches, achieving 92.29% F1-score and 90.62% mIoU for crack segmentation, accurately quantifies thin cracks as narrow as 0.25 mm with an error rate of 7.3% The proposed algorithm enhances crack quantification precision while exceptional robustness, provides reliable quantitative metrics for concrete structural assessment.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"69 ","pages":"Article 103807"},"PeriodicalIF":9.9,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145027226","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":"RTDSeg: Hard example sampling driven Real-Time Concrete Structural Damage Segmentation network","authors":"Jing Wang ,&nbsp;Haizhou Yao ,&nbsp;Qian Hu ,&nbsp;Jinbin Hu ,&nbsp;Jin Wang ,&nbsp;Yafei Ma","doi":"10.1016/j.aei.2025.103811","DOIUrl":"10.1016/j.aei.2025.103811","url":null,"abstract":"<div><div>Concrete material will gradually lose its original structural strength over time and suffer from a variety of structural damages, such as cracks, potholes, etc. Diverse damage patterns and complex geometries of material make accurate multi-class material structural damage segmentation more difficult than the segmentation of a single type of damage. Integrating detection methods with other systems and applying them to engineering practice imposes demands on the efficiency of model inference. In response to these challenges, Real-Time concrete structural Damage Segmentation network (RTDSeg) was proposed. In this network, efficient feature extraction backbone was introduced to improve the perceptual capabilities of the model. In order to alleviate the problem of feature redundancy when fusing features from different scales, semantic enhancement module was designed to filter the encoding features. Furthermore, auxiliary prediction head and hard example sampling training method were introduced to optimize the training effectiveness of the model, which improved the model’s prediction accuracy without extra inference cost. A series of experiments demonstrated the superiority of RTDSeg and the effectiveness of several improvements. In the compared state-of-the-art networks, RTDSeg achieved 8.98% mIoU and 13.89% FPS lead on a bridge damage dataset, and 3.88% mIoU and 92.03% FPS lead on a reinforced concrete damage dataset compared to the ones with the highest accuracy.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"69 ","pages":"Article 103811"},"PeriodicalIF":9.9,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145020209","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":"Physics-informed deep learning method for surface roughness prediction in milling process","authors":"Liangshi Sun ,&nbsp;Xianzhen Huang ,&nbsp;Xu Wang ,&nbsp;Yongchao Zhang ,&nbsp;Mingze Li ,&nbsp;Zheng Liu","doi":"10.1016/j.aei.2025.103803","DOIUrl":"10.1016/j.aei.2025.103803","url":null,"abstract":"<div><div>Surface roughness is critical to the functionality and aesthetic performance of mechanical components, necessitating precise prediction and control during the milling process. However, physics-based methods and data-driven methods either exhibit poor performance or lack interpretability, limiting their practical application. To address the issues, this article proposes a novel physics-informed deep learning (PIDL) for milling surface roughness prediction. The core idea is to leverage the principles of cutting mechanics and surface roughness to guide the model construction and regulate the network learning process. Firstly, a high-fidelity dynamic milling force model is established to generate simulated force signals for multi-sensor fusion with other measured signals. Then, the output of the surface roughness physical model is used as physics-guided knowledge to construct an attention-enhanced BiLSTM-BiGRU network based on cross physics-data fusion. In addition, a physics-informed loss function is designed to guide model training, thereby enhancing prediction performance and interpretability. The feasibility and superiority of the proposed method are validated through a series of milling tests under varying conditions. The results indicate that the proposed PIDL can achieve accurate surface roughness prediction in complex milling scenarios, with a coefficient of determination of 0.9845, a root mean square error of 0.0350, a mean absolute percentage error of 1.2895%, and a mean absolute error of 0.0284, outperforming both physics-based methods and data-driven methods.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"69 ","pages":"Article 103803"},"PeriodicalIF":9.9,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145020211","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-LLM-based augmentation and synthetic data generation of construction schedules and task descriptions with SLM-as-a-judge assessment","authors":"Akarsth Kumar Singh,&nbsp;Shang-Hsien Hsieh","doi":"10.1016/j.aei.2025.103825","DOIUrl":"10.1016/j.aei.2025.103825","url":null,"abstract":"<div><div>The fragmented structure, semantic inconsistency, and limited availability of construction schedule data significantly hinder the development of intelligent planning tools in the architecture, engineering, and construction (AEC) domain. In particular, the absence of high-quality, hierarchically structured Work Breakdown Structure with Task Dependency (WBS-TD) datasets restricts the training and evaluation of AI-based models for automated construction workflows. This study investigates whether Large Language Models (LLMs) can be systematically applied to enhance and generate construction schedule and task description data, and whether lightweight, locally deployed Small Language Models (SLMs) can effectively evaluate these outputs using domain-specific rubrics in a scalable and privacy-preserving manner. To address this, an integrated methodology is proposed, consisting of three components: (1) Role-Guided Modular Prompt Chaining (RGPC), which transforms inconsistent WBS-TD inputs into logically ordered and semantically enriched outputs; (2) synthetic data generation via a multi-LLM pipeline using structured prompt strategies to produce diverse, realistic construction schedules and descriptions; and (3) SLM-as-a-Judge, a rubric-based evaluation approach that uses a lightweight, locally deployed SLMs to assess output quality across structural, logical, and domain-specific dimensions without requiring sensitive data to leave secure environments. Experimental results show that Claude-3.5-Sonnet achieved 77 % quality in augmented schedule generation, Gemini-2.0-Flash reached 92 % in synthetic schedule generation, and DeepSeek-R1 provided the best balance of quality and diversity in synthetic construction task description generation, demonstrating strong domain alignment across tasks. The framework generates reusable, machine-readable knowledge graph datasets supporting downstream applications such as AI-assisted planning, progress monitoring, and risk analysis. This study delivers a scalable, model-agnostic pipeline that advances automation and evaluation in construction informatics.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"69 ","pages":"Article 103825"},"PeriodicalIF":9.9,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145020210","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":"Quality aware operational transfer path analysis for gas turbines","authors":"Chao Song ,&nbsp;Wei Cheng ,&nbsp;Mingsui Yang ,&nbsp;Xuefeng Chen ,&nbsp;Liqi Yan ,&nbsp;Baijie Qiao ,&nbsp;Lin Gao ,&nbsp;Hai Huang ,&nbsp;Yang Lu","doi":"10.1016/j.aei.2025.103829","DOIUrl":"10.1016/j.aei.2025.103829","url":null,"abstract":"<div><div>Operational transfer path analysis (OTPA) is a promising methodology for evaluating vibration transmission in mechanical equipment at industrial sites. However, its accuracy requires high-quality vibration data. The long-standing absence of true benchmarks due to practical constraints has hindered the assessment and improvement of data quality (DQ) for OTPA. Motivated by data quality awareness, this paper proposes quality aware OTPA, which addresses this gap by defining and optimizing a heuristic DQ index. First, based on the central limit theorem, we analyze the statistical distribution characteristics of potential data errors and identify factors affecting transmissibility error. Then, by constructing the DQ index as the objective function, we iteratively optimize it to update both the data subset and transmissibility synchronously. Finally, the iteration terminates when the data subset stabilizes, and this final subset serves as input for OTPA. Validation was performed on simulation, test bed, and gas turbine vibration datasets. Comparative results indicate that the proposed method is more accurate and robust. Without additional experimental work, it improves the analysis accuracy and reliability of OTPA. In summary, this method advances the maturity and practical applicability of OTPA for large equipment like gas turbines, supporting vibration reduction and health management.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"69 ","pages":"Article 103829"},"PeriodicalIF":9.9,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145010823","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":"AviationCopilot: Building a reliable LLM-based Aviation Copilot inspired by human pilot training","authors":"Zhuorui Zhang ,&nbsp;Shanshan Feng ,&nbsp;Tiance Yang ,&nbsp;Ruobing Huang ,&nbsp;Hao Wang ,&nbsp;Fu Wang ,&nbsp;Fan Li","doi":"10.1016/j.aei.2025.103806","DOIUrl":"10.1016/j.aei.2025.103806","url":null,"abstract":"<div><div>Modern pilots routinely face high cognitive loads during complex flight operations. Although large language models (LLMs) demonstrate exceptional natural language understanding and exhibit tremendous potential as copilots, there is a notable gap in LLMs specifically designed to handle the knowledge-intensive tasks required of pilots. Inspired by pilots’ learning and manual retrieval patterns, we introduce <strong>AviationCopilot</strong>—a novel framework that efficiently injects both aviation knowledge content and knowledge structure into LLMs. Specifically, we employ differentiated data fusion and generalization strategies for two training stages including continual pre-training and instruction tuning. This approach equips the model with enhanced domain-specific knowledge retention and instruction-following capabilities, akin to human pilots. During inference, AviationCopilot activates its knowledge structure memory to adaptively retrieve comprehensive context, improving factual accuracy. To evaluate effectiveness, we construct a comprehensive benchmark named <strong>OpenAviation</strong> featuring both LLM-synthesized and expert-designed questions. Experimental results show that models with fewer than two billion parameters, trained with the AviationCopilot framework, consistently outperform strong LLM baselines, including those utilizing Retrieval-Augmented Generation (RAG). Additionally, AviationCopilot enhances structured aviation understanding and enables LLMs to serve as retrievers for improving other models, supporting more reliable AI copilots. The dataset and source code are available at <span><span>https://github.com/zhuorui-zhang/AviationCopilot</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"69 ","pages":"Article 103806"},"PeriodicalIF":9.9,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145010821","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":"An automatic detection method for road damage in UAV images based on multi-level perception and feature aggregation","authors":"Huixia Li ,&nbsp;Ruohan Chen ,&nbsp;Nyirandayisabye Ritha ,&nbsp;Jian Wang ,&nbsp;Zi’ang Chen","doi":"10.1016/j.aei.2025.103814","DOIUrl":"10.1016/j.aei.2025.103814","url":null,"abstract":"<div><div>Road infrastructure monitoring is critical for transportation safety and maintenance efficiency. However, existing road damage detection methods face challenges in multi-scale target recognition within complex environments, primarily attributed to their inadequate detection accuracy when processing drone-captured images. To overcome these limitations, this paper introduces the MFD-YOLO model. To tackle the insufficient detection accuracy of existing methods under complex backgrounds, this study designs two key structures: (1) A DS-MDPB backbone network that integrates three feature focusing mechanisms—MANet, SimAM, and BRA—to enhance feature extraction capabilities for pavement cracks and irregular distresses. (2) An MFDPN architecture that employs bidirectional feature propagation and dynamic weight allocation strategies, optimizing feature fusion through DG-C and RE-C modules. Experimental results demonstrate that on the RDD2022_China_Drone dataset, the model achieves an mAP50 of 73.1 %, reflecting a 5.5 % relative improvement over the baseline, and a 30.03 % relative enhancement in AP_s. The model also exhibits consistent performance on UAV-PDD2023 and self-constructed datasets, demonstrating cross-scenario generalization capability. This method maintains high efficiency (FPS &gt; 300) while improving detection accuracy for road damage in complex environments, providing reliable technical support for intelligent road maintenance.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"69 ","pages":"Article 103814"},"PeriodicalIF":9.9,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145010822","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 fault mechanism-guided interpretable causal disentanglement domain generalization detection method for typical faults of induction motor","authors":"You He ,&nbsp;Xinwei Zhao ,&nbsp;Lei Su ,&nbsp;Jiefei Gu ,&nbsp;Ke Li ,&nbsp;Michael Pecht","doi":"10.1016/j.aei.2025.103813","DOIUrl":"10.1016/j.aei.2025.103813","url":null,"abstract":"<div><div>Induction motors are widely used in the industrial field such as electric drive systems for new energy vehicles and synchronous condenser for improving the power factor of the power grid. The motor health condition often influences the operation of the entire mechanical system, so it is necessary to conduct a health assessment on it. Current induction motor fault diagnosis largely relies on expert knowledge, while many deep learning methods suffer from limited generalization and poor interpretability, leading to unreliable results. To address these issues, a fault mechanism-guided interpretable causal disentanglement domain generalization detection method (ICGN) is proposed for typical fault diagnosis of induction motor. Firstly, a primary feature extractor is constructed based on transformer, which adaptively screens causal and non-causal factors through the self-attention mechanism, and an attention score evaluation mechanism is constructed to visually demonstrate interpretability. Secondly, to further disentangle and refine causal features and non-causal features, the developed causal aggregation loss and causal decoupling loss are combined, ensuring the cross-domain consistency of causal factors and promote the domain generalization ability of the network. Finally, the proposed method is validated using vibration signals collected from two Spectra Quest test benches from University of Ottawa and the private laboratory. The cases of cross device motor fault diagnosis are included, and the ICGN is compared with several advanced domain generalization algorithms. The results demonstrate that the proposed method achieves superior performance both in interpretability and domain generalization capability.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"69 ","pages":"Article 103813"},"PeriodicalIF":9.9,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145010824","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 physical causality-informed generative latent variable modeling paradigm for industrial virtual metrology","authors":"Weiming Shao ,&nbsp;Hongjian Yu ,&nbsp;Wenxue Han ,&nbsp;Zeyu Yang ,&nbsp;Junghui Chen","doi":"10.1016/j.aei.2025.103809","DOIUrl":"10.1016/j.aei.2025.103809","url":null,"abstract":"<div><div>Generative latent variable models (GLVMs) have played an important role and been attracting widespread interest in industrial virtual metrology for predicting key variables in real-time, due to their outstanding capabilities of handling correlations, high dimensionality, uncertainties, and missing values. However, there is an overlooked issue associated with the GLVMs. That is, the existing GLVMs develop predictive models by establishing correlations between process variables, ignoring the causal dependence, which impairs the interpretability and generalization performance of the GLVMs because it is nontrivial to capture the true correlations. In view of such limitation of the GLVMs, with the aid of process knowledge for causal analysis, a novel physical causality-informed (PCI) modeling paradigm for the GLVMs, named PCI-GLVM, is proposed in this paper. The PCI-GLVM paradigm is further instantiated using a semi-supervised probabilistic principal component analysis (SsPPCA) model, for which a highly-efficient training algorithm based on the expectation–maximization algorithm is developed. Comprehensive performance evaluations of the PCI-SsPPCA are conducted on a numerical example and two industrial processes, validating the superiorities of the PCI-SsPPCA over state-of-the-art benchmark models.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"69 ","pages":"Article 103809"},"PeriodicalIF":9.9,"publicationDate":"2025-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145010958","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":"Artificial intelligence to enhance BIM-BEPS integration via IFC: Challenges, solutions, and future directions","authors":"Liége Garlet ,&nbsp;Matheus Körbes Bracht ,&nbsp;Roberto Lamberts ,&nbsp;Ana Paula Melo ,&nbsp;James O’Donnell","doi":"10.1016/j.aei.2025.103824","DOIUrl":"10.1016/j.aei.2025.103824","url":null,"abstract":"<div><div>In the Architecture, Engineering, and Construction (AEC) domain, integrating Building Information Modeling (BIM) and Building Performance Simulations (BEPS) is essential for optimizing building design and performance. This study investigates the potential of AI to enhance the integration of BIM and BEPS through Industry Foundation Classes (IFC). This study also examines the challenges inherent in the BIM-BEPS workflow and the barriers to AI adoption in this domain. The paper aims to present solutions that support IFC-based interoperability, identifying the most effective approaches within the categories of the mapped problems. These include tools for extracting geometry from IFC models, algorithms for geometric enrichment, ontologies for rule-based model verification, machine learning techniques for space classification, external libraries, and IFC extensions for property addition to models. The integration of AI demonstrates significant potential to improve BIM-BEPS workflows, particularly in automating geometry extraction from BIM, enriching model data, and detecting inconsistencies in IFC models. The study also explores opportunities to enhance the BIM-BEPS workflow through IFC4 and future IFC generations, focusing on combining ontology frameworks with machine learning. Furthermore, the study emphasizes the industry’s role in developing better user support solutions, underscoring the need for users to adhere to well-defined design requirements and workflows to maximize the benefits of these advancements.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"69 ","pages":"Article 103824"},"PeriodicalIF":9.9,"publicationDate":"2025-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145007795","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}