Advanced Engineering Informatics最新文献

{"title":"AI-powered NUN-SEDFN framework for addressing sparse data challenges in geotechnical parameter prediction","authors":"Zeliang Wang ,&nbsp;Rui Gao ,&nbsp;Xiuren Hu","doi":"10.1016/j.aei.2025.103226","DOIUrl":"10.1016/j.aei.2025.103226","url":null,"abstract":"<div><div>Accurate and comprehensive geological parameter acquisition is a persistent challenge in engineering geological mapping, particularly in construction environments with complex conditions where conventional drilling is impractical. Addressing the issue of sparse drilling data, this study introduces a novel prediction framework combining Non-Uniform Normalization (NUN) and a Spectral-Enhanced Deep Fusion Network (SEDFN). The proposed framework enhances the ability to predict geotechnical characteristic parameters critical for construction and infrastructure management. Specifically, the NUN-SEDFN framework transforms sparse textual drilling data into high-resolution geotechnical parameter maps by leveraging advanced AI techniques for data processing and prediction. The characterization stage employs NUN to ensure robust mapping between geotechnical data and image representations, addressing challenges in integrating large-span geological feature parameters. The prediction stage uses Frequency-Domain High Preservation Fast Fourier Convolution (FHP-FFC) and a Modified Super Resolution Convolutional Neural Network (mSRCNN) to learn and reconstruct high- and low-frequency geotechnical features, achieving over 80% prediction accuracy. This method enhances the reliability of geological mapping, offering significant potential for optimizing resource allocation, cost reduction, and safety in engineering and construction tasks. Furthermore, it demonstrates how AI can address data scarcity and improve decision-making in construction environments, aligning with current industry needs and technological trends.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103226"},"PeriodicalIF":8.0,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143512131","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":"Influence of design interaction modes on conceptual design behavior and inter-brain synchrony in designer teams: A fNIRS hyperscanning study","authors":"Jinchun Wu ,&nbsp;Yixuan Liu ,&nbsp;Xiaoxi Du ,&nbsp;Xinyu Zhang ,&nbsp;Chengqi Xue","doi":"10.1016/j.aei.2025.103223","DOIUrl":"10.1016/j.aei.2025.103223","url":null,"abstract":"<div><div>Conceptual design is inherently a social and creative activity. Most studies on conceptual design of designer teams focused primarily on behavioral aspects, leaving cross-brain coupling neural mechanisms underlying designer teams’ collaboration unexplored. Investigating inter-brain synchrony (IBS) offers a critical perspective on how shared neural activity supports key collaborative processes, such as coordination, communication, and team creativity. This study investigated the effects of design interaction modes (face-to-face vs. remote virtual vs. electronic brainstorming; FTF vs. RV vs. EBS) on designer teams’ interactive behaviors and IBS during conceptual design. Using fNIRS-based hyperscanning, neural activities in the right prefrontal cortex and right temporoparietal junction (r-TPJ) were recorded for 72 designers (36 dyads), and behavioral characteristics, IBS, and temporal dynamics of these metrics across modes were analyzed. Results showed that FTF teams outperformed RV and EBS in creative design performance, cooperation level, team flexibility, perspective-taking, and turn-taking. Creative design performance and cooperation level increased over time across all modes, particularly in FTF and RV, while team flexibility, perspective-taking, and turn-taking initially rose before declining, notably in FTF and RV. fNIRS data revealed greater IBS in r-TPJ and between r-TPJ and right dorsolateral prefrontal cortex (r-DLPFC) in RV compared to FTF and EBS, both following a U-shaped temporal trend. Cooperation level, perspective-taking, and turn-taking positively correlated with △IBS in r-TPJ, while cooperation level correlated with △IBS between r-TPJ and r-DLPFC. These results highlight distinct behavioral and neural synchronization patterns across interaction modes in designer teams during conceptual design process, with FTF mode performing best. These findings enhanced understanding of designer teams’ interactive cognition, contributed to design neurocognition research, and offered practical implications for designing tools and training programs to optimize team performance.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103223"},"PeriodicalIF":8.0,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143488317","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":"Auxiliary-feature-embedded causality-inspired dynamic penalty networks for open-set domain generalization diagnosis scenario","authors":"Ning Jia ,&nbsp;Weiguo Huang ,&nbsp;Chuancang Ding ,&nbsp;Yifan Huangfu ,&nbsp;Juanjuan Shi ,&nbsp;Zhongkui Zhu","doi":"10.1016/j.aei.2025.103220","DOIUrl":"10.1016/j.aei.2025.103220","url":null,"abstract":"<div><div>Domain generalization techniques are often used to address the distribution differences between training and testing data. Existing studies are mostly based on the assumption that the label spaces of the training and testing data are consistent. However, as complex industrial equipment operates, unknown faults may emerge in the testing data. This scenario is referred to as open-set domain generalization (OSDG), where traditional domain generalization diagnosis models tend to fail. Therefore, an auxiliary-feature-embedded causality-inspired dynamic penalty network (ACDPN) is proposed for OSDG diagnosis. A label reconstruction strategy and a memory dynamic penalty term are designed to enhance the model’s sensitivity to low-probability unknown classes. The dynamic penalty helps balance the model’s learning of known classes with its attention to unknown classes. To enhance the model’s generalization performance for diagnosing known classes, a causal loss under causal intervention is constructed to extract domain-invariant causal features. Meanwhile, auxiliary features that can reflect the physical characteristics of the signals are extracted to jointly drive the classification predictions of the diagnosis model, enhancing the model’s decision-making ability. In the target domain decision stage, a dual-path optimal matching strategy and a multi-class similarity quantification strategy are incorporated to enhance the model’s diagnosis performance and quantitatively predict the categories of unknown faults, thereby increasing the practical engineering value of OSDG diagnosis. Comparative experiments, ablation studies, and model interpretability analysis experiments are conducted on two multi-domain datasets, and the results demonstrate the effectiveness and superiority of the proposed method in OSDG scenario.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103220"},"PeriodicalIF":8.0,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143479751","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":"Actual construction cost prediction using hypergraph deep learning techniques","authors":"Hao Liu ,&nbsp;Mingkai Li ,&nbsp;Jack C.P. Cheng ,&nbsp;Chimay J. Anumba ,&nbsp;Liqiao Xia","doi":"10.1016/j.aei.2025.103187","DOIUrl":"10.1016/j.aei.2025.103187","url":null,"abstract":"<div><div>Accurate construction cost estimation at early stages is critical to enable project stakeholders to make financial decisions (e.g., set up the project budget). However, the heavy reliance on cost engineers’ subjective experience and manual effort in practice makes the estimation an error-prone and time-consuming process. To this end, this study proposes a novel hypergraph deep learning-based framework to predict the actual costs of construction projects accurately and efficiently at early stages. It starts with a systematic hypergraph formulation incorporating construction cost factors and their interrelationships. A hypergraph deep learning model is then developed based on the formulated hypergraph for end-to-end construction cost prediction. Afterwards, model interpretation is undertaken to reveal the cost factor importance from the model training results in a quantitative manner. The framework is validated using an actual construction cost dataset of school projects. The results show high accuracy in cost prediction without human intervention and meaningful interpretations of cost factor importance for better understanding of construction cost patterns.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103187"},"PeriodicalIF":8.0,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143479750","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":"Federated learning based on dynamic hierarchical game incentives in Industrial Internet of Things","authors":"Yuncan Tang ,&nbsp;Lina Ni ,&nbsp;Jufeng Li ,&nbsp;Jinquan Zhang ,&nbsp;Yongquan Liang","doi":"10.1016/j.aei.2025.103214","DOIUrl":"10.1016/j.aei.2025.103214","url":null,"abstract":"<div><div>Federated Learning (FL) can effectively protect user data privacy while performing distributed machine learning, which has shown a mighty capability to safely train intelligent industrial models on the Industrial Internet of Things (IIoT). However, in real scenarios, the performance of the global model is threatened by the possibility of IIoT devices launching malicious attacks; at the same time, it is difficult for devices to actively participate in the FL process without sufficient utility, resulting in a model that is not sufficiently data-driven. In this paper, we propose a dynamic hierarchical game incentive mechanism to achieve secure and fair FL in IIoT. Specifically, we design a cloud-factory-device three-layer collaborative FL architecture. In the cloud-factory layer, we design each iteration of FL as a cooperative game process and propose a reward allocation scheme based on the Shapley value to accomplish the incentive process. After theoretical deduction, we demonstrate that the scheme is consistent with rationality, fairness, and additionality. In the factory-device layer, we construct the problem for the FL iteration process and model this problem as a two-stage Stackelberg game process. We design a reputation-based adaptive local FL iteration algorithm and a non-cooperative game-based incentive mechanism to solve the game process. While solving the problem, we further consider the device’s dynamics and delay time to fit the real IIoT scenario. Theoretical analyses and experimental results show that our proposed mechanism has good performance.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103214"},"PeriodicalIF":8.0,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143479756","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":"Enhanced Multi-Attribute Ideal-Real comparative analysis with the circular intuitionistic fuzzy framework: Application to hybrid cloud services","authors":"Ting-Yu Chen","doi":"10.1016/j.aei.2025.103184","DOIUrl":"10.1016/j.aei.2025.103184","url":null,"abstract":"<div><div>This paper underscores the utilization of the Circular Intuitionistic Fuzzy (CIF) framework to enhance the Multi-Attribute Ideal-Real Comparative Analysis (MAIRCA) methodology, emphasizing its practical relevance through an application to hybrid cloud services. The CIF framework incorporates membership and non-membership components accompanied by a radius, forming a deformable circular structure within an intuitionistic fuzzy interpretation triangle. The study utilizes geometric mean techniques to maintain consistency in CIF evaluative ratings and importance levels while reducing the impact of outliers. By incorporating upper and lower importance levels and parameterized CIF scoring functions, the methodology ensures balanced weight determination. Refined radius operations further enhance CIF data analysis, improving the methodology’s comprehensiveness. The enhanced CIF MAIRCA approach balances theoretical and real-world evaluations, harmonizes criteria, and computes aggregate disadvantage gap measures to rank alternatives, with smaller gaps indicating better options. This research illustrates the real-world effectiveness of the developed methodology through a hybrid cloud services case study. By exploring various parameter configurations, it highlights the approach’s robustness, adaptability, and ability to ensure stability and reliability in complex real-world scenarios. To extend the utility of the enhanced CIF MAIRCA methodology to other decision-making scenarios, this study applies it to a vendor evaluation case. Comparative analyses with other models highlight its strengths in managing uncertainty, adaptability, and precision, affirming its value as a reliable decision-support tool.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103184"},"PeriodicalIF":8.0,"publicationDate":"2025-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143471252","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":"Real-time scheduling for production-logistics collaborative environment using multi-agent deep reinforcement learning","authors":"Yuxin Li,&nbsp;Xinyu Li,&nbsp;Liang Gao","doi":"10.1016/j.aei.2025.103216","DOIUrl":"10.1016/j.aei.2025.103216","url":null,"abstract":"<div><div>With the extensive application of automated guided vehicle (AGV), production-logistics collaborative scheduling problem (PLCSP) becomes challenging for enterprises. Meanwhile, large-scale order and dynamic events bring more complexity and uncertainty. At present, deep reinforcement learning (DRL) has emerged as a promising scheduling approach. Therefore, this paper proposes a real-time scheduling method based on multi-agent DRL for PLCSP with dynamic job arrivals to minimize the total weighted tardiness. Specifically, a novel scheduling framework is designed in which a new logistics task release moment is given to reserve lots of AGV preparation time and avoid unnecessary premature decisions. Then, a training algorithm based on multi-agent proximal policy optimization is proposed to achieve job filtering, job selection and AGV selection. The action space and action space pruning strategy are designed for each agent to ensure the sufficient exploration and reduce the learning difficulty. Moreover, three state spaces with serial relationship and a reward function considering job classification are proposed. Experiments on 120 instances show that the proposed method has superiority and generality compared with scheduling rules and genetic programming, as well as three popular DRL-based methods, and the performance improvement mostly exceeds 10%. Furthermore, a real-world case is studied to show that the proposed method is applicable to solve the complex production-logistics collaborative scheduling problems.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103216"},"PeriodicalIF":8.0,"publicationDate":"2025-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143471251","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 nonlinear dynamics method using multi-sensor signal fusion for fault diagnosis of rotating machinery","authors":"Fei Chen ,&nbsp;Zhigao Zhao ,&nbsp;Xiaoxi Hu ,&nbsp;Dong Liu ,&nbsp;Xiuxing Yin ,&nbsp;Jiandong Yang","doi":"10.1016/j.aei.2025.103190","DOIUrl":"10.1016/j.aei.2025.103190","url":null,"abstract":"<div><div>Deep mining abnormal information from operation data is a crucial step in fault diagnosis of equipment, and it holds significant importance for ensuring the efficient operation of rotating machinery. The nonlinear dynamics methods represented by multivariate multiscale entropy have shown good application effects in quantifying the fault characteristics of rotating machinery using multiple sensor signals. However, these methods essentially belong to the category of data-level fusion, which suffers from drawbacks such as poor real-time performance, limited capability to handle only similar types of sensors, and significant influence from sensor information. This paper develops a novel tool named enhanced hierarchical Poincaré plot index (EHPPI), for extracting anomaly information from multi-source signals via feature-level fusion. Firstly, the Poincaré plot index is extended to create the EHPPI, allowing for the extraction of information from signals at various frequency scales. Subsequently, EHHPI is utilized to extract information from all channel signals. Ultimately, we concatenate the information extracted from all channels by EHPPI to form features and integrate them with random forests to identify faults in rotating machinery. The EHPPI and other popular nonlinear dynamics metrics are applied in different scenarios, such as simulation faults, experimental bench faults, and real machine faults, whose results strongly prove its advantages. The EHPPI has a favorable effect on improving the operational efficiency of rotating machinery.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103190"},"PeriodicalIF":8.0,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143463983","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":"Developing A novel AI enabled extended reality system for real-time automatic facial expression recognition and system performance evaluation","authors":"Amirarash Kashef ,&nbsp;Yu Wang ,&nbsp;Mohammad Nafe Assafi ,&nbsp;Junfeng Ma ,&nbsp;Jun Wang ,&nbsp;J. Adam Jones ,&nbsp;Ladda Thiamwong","doi":"10.1016/j.aei.2025.103207","DOIUrl":"10.1016/j.aei.2025.103207","url":null,"abstract":"<div><div>Facial Expression Recognition (FER) is vital for understanding human behavior but faces challenges from varying facial features due to different poses, lighting, and angles. Addressing the growing demand for real-time FER is critical. Extended Reality (XR) offers significant potential in training, education, healthcare, user experience, and relevant data collection. This study aims to develop an AI-enabled XR system for FER by combining a novel Depthwise Separable Convolutional Neural Network (DS-CNN) approach with XR technology. The FER2013 image dataset was used to train and build the proposed FER model. The model’s performance was validated using two separate image datasets, demonstrating that the proposed CNN model outperformed existing models on both. Subsequently, the CNN model was integrated with Microsoft HoloLens 2 XR technology to create a real-time, automatic FER system. System evaluation was conducted using System Usability Scale (SUS) and NASA-TLX measures, with results indicating that the proposed smart system is high usability and lower cognitive workload compared with FER using eyes. The AI-enabled XR system offers significant practical applications and potential across various domains, providing valuable managerial insights. The integration of CNN with XR technology represents a substantial advancement in real-time FER, offering improved accuracy and usability under diverse conditions.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103207"},"PeriodicalIF":8.0,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143463981","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":"Deep learning-based rebar detection and instance segmentation in images","authors":"Tao Sun ,&nbsp;Qipei Fan ,&nbsp;Yi Shao","doi":"10.1016/j.aei.2025.103224","DOIUrl":"10.1016/j.aei.2025.103224","url":null,"abstract":"<div><div>Automated rebar cage assembly and quality inspection rely on reliable rebar perception. Recent studies have explored image-based rebar perception via object detection and instance segmentation algorithms. However, existing models are limited across various scenarios, especially with different rebar categories, arrangement patterns, and camera views, which limits their application. This is primarily attributed to the absence of a benchmark considering these factors. This study introduces an image benchmark designed for the effective training and selection of rebar detection and instance segmentation algorithms. It is the first to encompass two types of commonly used rebars, multiple camera views, and various rebar placement patterns at different assembly phases in a single dataset. Six object detection methods and four instance segmentation methods are evaluated to assess the applicability of the state-of-the-art methods. Additionally, a new shape-prior-based post-processing method is developed to address the merged detection problem in clustering. The experiment shows that Deformable DETR and Mask2Former achieved the highest bounding box mAP (80.4) and mask mAP (66.3) respectively. The Simple Copy-Paste technique was introduced, improving the mask mAP of Mask2Former by 2.8 points. Finally, the developed model was validated in the real-world scenarios of three downstream tasks. Notably, in the rebar spacing measurement task, the proposed post-processing method improves Mask2Former by increasing its bounding box mAP by 18.0 and mask mAP by 2.4.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103224"},"PeriodicalIF":8.0,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143463342","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}