Advanced Engineering Informatics最新文献

{"title":"Human–Robot collaboration in construction: Robot design, perception and Interaction, and task allocation and execution","authors":"Jiajing Liu ,&nbsp;Hanbin Luo ,&nbsp;Dongrui Wu","doi":"10.1016/j.aei.2025.103109","DOIUrl":"10.1016/j.aei.2025.103109","url":null,"abstract":"<div><div>Human–robot collaboration (HRC) is a vital area for enhancing safety and productivity in the construction industry. Despite its growing importance, current literature lacks comprehensive reviews on the technological and methodological advancements supporting the design and deployment of HRC systems in construction industry. This review aims to fill this gap by providing a detailed examination of recent progress in HRC technologies and methods within the construction industry, with a focus on three main areas: (1) collaborative robot design, (2) perception and interaction, and (3) task allocation and execution of HRC systems. The review highlights significant challenges in current construction research and underscores the necessity for future research to prioritize the development of: (1) exoskeleton robots designed for construction trades and non-exoskeleton collaborative robots with rigid-flexible-soft configurations; (2) multimodal perception and interactive methods; and (3) digital twin-based HRC systems. This review study not only addresses the existing gap but also identifies promising research avenues to promote the development of safe and efficient HRC systems in the construction industry.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103109"},"PeriodicalIF":8.0,"publicationDate":"2025-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143137303","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":"Enhancing understanding of asphalt mixture dynamic modulus prediction through interpretable machine learning method","authors":"Ke Zhang ,&nbsp;Zhaohui Min ,&nbsp;Xiatong Hao ,&nbsp;Theunis F.P. Henning ,&nbsp;Wei Huang","doi":"10.1016/j.aei.2025.103111","DOIUrl":"10.1016/j.aei.2025.103111","url":null,"abstract":"<div><div>Dynamic modulus is a key parameter in pavement design and pavement mechanics analysis. It is essential to accurately predict dynamic modulus and study the relationships between influencing factors and dynamic modulus. In this study, a hybrid prediction model is developed based on Extreme Gradient Boosting (XGBoost) and Whale Optimization Algorithm (WOA). Based on this model, the effects of asphalt binder properties, test condition, asphalt mixture volume parameters, and asphalt mixture gradation on dynamic modulus are analyzed. The contribution of each variable to the model predictions is quantified through Shapley Additive Explanations (SHAP), and the interaction between dynamic modulus and influencing factors is evaluated by Partial Dependence Plot (PDP). The results indicate that the WOA-XGBoost model has excellent accuracy and robustness in predicting dynamic modulus. The three most important factors affecting dynamic modulus prediction results are the complex shear modulus of binder, the test temperature and the asphalt binder viscosity. The increase in dynamic modulus can be achieved through the utilization of asphalt binders characterized by relatively large complex modulus, high viscosity, small phase angle, and high asphalt PG indexes. Reducing the effective binder volume and air voids of the mixture, optimizing the mixture gradation to a suitable level, and increasing the mineral powder content can also lead to the increase of dynamic modulus. Besides, low test temperature and high frequency generally mean a large value of dynamic modulus. This study clarifies the impact of influencing factors on the performance of asphalt mixtures based on machine learning, which lay a foundation for the intelligent design of asphalt mixtures.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103111"},"PeriodicalIF":8.0,"publicationDate":"2025-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143136813","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":"Optimising predictive accuracy in sheet metal stamping with advanced machine learning: A LightGBM and neural network ensemble approach","authors":"Ema Stefanovska,&nbsp;Tomaž Pepelnjak","doi":"10.1016/j.aei.2024.103103","DOIUrl":"10.1016/j.aei.2024.103103","url":null,"abstract":"<div><div>This article presents an innovative ensemble model that integrates advanced machine learning techniques to enhance the precision of sheet metal stamping processes. By combining a light gradient boosting machine (LightGBM) with deep neural networks (DNNs), the model achieves high accuracy in predicting the final geometry of stamped sheet metal parts, and proactively identifies potential deviations to guarantee strict compliance to geometrical tolerances. In a comprehensive evaluation based on diverse performance metrics, the ensemble model demonstrates substantial improvements over the individual models, achieving a high coefficient of determination <em>R</em>² of 0.951. Significantly, an extensive dataset derived from finite element method simulations is found to facilitate the training of our models in a variety of stamping scenarios, giving superior generalisability and reliability in terms of predictions. In addition, the integration of the ensemble model into an interactive web platform for real-time predictive analytics underscores its practical application in manufacturing settings, as it can optimise decision-making and operational efficiency. The predictive power of the ensemble model and its integration into a real-time framework provide a solid foundation for further advancements in developing a digital twin of the sheet metal stamping process. Our findings highlight the transformative potential of combining diverse machine learning techniques to revolutionise manufacturing processes, thus ensuring higher quality, adaptability, and cost efficiency.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103103"},"PeriodicalIF":8.0,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143137302","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}

{"title":"Digital twin-based smart shop-floor management and control: A review","authors":"Cunbo Zhuang ,&nbsp;Lei Zhang ,&nbsp;Shimin Liu ,&nbsp;Jiewu Leng ,&nbsp;Jianhua Liu ,&nbsp;Fengque Pei","doi":"10.1016/j.aei.2024.103102","DOIUrl":"10.1016/j.aei.2024.103102","url":null,"abstract":"<div><div>Propelled by the latest advancements in information technology, shop-floor management and control (SMC) is transitioning towards a more intelligent paradigm, predominantly marked by data-driven insights and the integration of virtual reality. The digital twin (DT) stands out as a pivotal technology for the realization of cyber-physical systems, and its role in smart shop-floor management and control (SSMC) has attracted significant interest from both the industrial sector and academic circles. However, the application of DT in achieving SSMC remains diverse and lacks a structured methodology. In light of this, this review provides an in-depth analysis and discussion of the current state, limitations, and prospective trends of DT in SSMC. Initially, a DT-based SSMC framework is introduced to guide the subsequent literature review and thematic discussions. This is followed by an examination of DT-based SSMC research across four key dimensions: the development of shop-floor DT models, dynamic monitoring and forecasting of the shop-floor leveraging DT, DT-assisted shop-floor scheduling, and DT-driven production process control. The review culminates with an outline of challenges and future research directions for DT-based SSMC. This comprehensive review not only enhances researchers’ comprehension of SSMC but also offers a valuable reference for the continued application and integration of DT within this domain.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"65 ","pages":"Article 103102"},"PeriodicalIF":8.0,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143136972","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":"Advancements in AI-Driven detection and localisation of solar panel defects","authors":"Ali Ghahremani,&nbsp;Scott D. Adams,&nbsp;Michael Norton,&nbsp;Sui Yang Khoo,&nbsp;Abbas Z. Kouzani","doi":"10.1016/j.aei.2024.103104","DOIUrl":"10.1016/j.aei.2024.103104","url":null,"abstract":"<div><div>Renewable energy production has experienced rapid growth over the past three decades and is projected to triple its global capacity by 2030. Given that the utilisation of solar photovoltaic (PV) technology plays a vital role in generating renewable electricity, it is crucial to continuously monitor the condition of solar panels because a variety of defects can significantly reduce their power production. In this paper, we review the latest artificial intelligence (AI) algorithms developed for inspecting solar panels. We also discuss various low-resource hardware systems used to execute these algorithms. AI algorithms are trained using datasets and images, including optical, infrared, and electroluminescence images of solar panels. These images can be captured by unmanned aerial vehicles (UAVs), ground vehicles, and fixed cameras. In this paper, we compare the precision, accuracy, and recall rates of a selection of reviewed AI algorithms. To gain a deeper understanding of these AI algorithms, we introduce a generic framework of AI-driven systems that can autonomously detect and localise solar panel defects and we analyse the literature based on this framework. Some of the main AI and image processing algorithms reviewed are YOLO V5 BDL, weight imprinting, custom-designed CNN, modified edge detection, fuzzy-based edge detection, and the modified Canny algorithm. We also discuss the main hardware systems used to execute image processing algorithms to localise and detect defects in solar panels: the central processing unit (CPU), field programmable gate array (FPGA), and graphics processing unit (GPU). Finally, as a future direction, we suggest developing image processing algorithms specifically designed for hardware systems tailored for machine learning, such as tensor processing units (TPUs). This development would further enhance the capabilities of solar panel inspection and defect detection.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"64 ","pages":"Article 103104"},"PeriodicalIF":8.0,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143130278","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":"Identification and precise optimization of key assembly error links for complex aviation components driven by mechanism and data fusion model","authors":"Feiyan Guo ,&nbsp;Zhang Yongliang ,&nbsp;Song Changjie ,&nbsp;Sha Xiliang","doi":"10.1016/j.aei.2024.103059","DOIUrl":"10.1016/j.aei.2024.103059","url":null,"abstract":"<div><div>As assembling complex aviation products, due to factors such as part deformation under loads, numerous process parameters, and complex error transmission path, the effective identification and optimization of key error links that affecting assembly accuracy significantly is challenging. In this paper, a mechanism and data fusion method for solving this problem was proposed. Firstly, the geometric-physical coupling relationship among composite thin-walled parts and the entire locating/clamping/joining/rebounding operations was analyzed. Then with the actual error information, the Jacobian-torsor matrix that representing error accumulation relationship was modified, and assembly error was calculated with the mechanism model. Secondly, with actual data processing solution to obtain the deviation of theoretical calculation results, the fusion model of integrating mechanism and data analysis results was proposed for predicting the final assembly accuracy. Subsequently, with massive data samples from the fusion model, the Sobol method was adopted to gain the global sensitivity coefficients of different error elements, and the key error links could be identified. Thirdly, with the accurate error fusion results, three single tolerance optimization models for the entire production process were established, i.e. manufacturing cost, assembly quality loss and repair cost. Then a weight parameters design method was proposed, which can avoid the conflict phenomena of data imbalance and optimization deviation problems among different goals, and the multi-objective tolerance allocation model was solved with intelligent algorithm. Finally, for the assembly work of wing-box component, key error links that having an obvious impact on the profile gap and step difference accuracy were identified and optimized, and beneficial quality/efficiency results were gained. This research could provide a strong interpretability for assembly accuracy analysis results, and a good applicability to practical assembly site.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"64 ","pages":"Article 103059"},"PeriodicalIF":8.0,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143129625","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":"Robust operating performance assessment of flotation processes using convolutional neural networks and feature learning","authors":"Runda Jia ,&nbsp;Mingxuan Ren ,&nbsp;Jinglong Wang ,&nbsp;Feng Yu ,&nbsp;Dakuo He","doi":"10.1016/j.aei.2024.103087","DOIUrl":"10.1016/j.aei.2024.103087","url":null,"abstract":"<div><div>The use of computer vision, rather than manual observation, to assess flotation performance based on froth characteristics is crucial for optimizing and controlling the flotation process. Convolutional neural networks (CNNs) are widely employed for image recognition tasks related to evaluating flotation operating performance. However, previous studies have often overlooked the quality of feature learning within these networks, resulting in limited robustness, especially when industrial applications encounter image distortions that challenge network performance.</div><div>To address this issue, this paper proposes a CNN-based algorithm for robust assessment of flotation operating performance, focusing on learning features that accurately reflect froth characteristics. The network is guided through regression training to prioritize froth-specific features, while classification training enhances its ability to evaluate flotation performance. Iterative optimization is achieved by adjusting the regression training loss using feedback from classification results and expert knowledge, thereby refining the network’s performance.</div><div>Experimental results from industrial applications validate the effectiveness of the proposed algorithm, demonstrating its ability to learn key features of froth images and showing high robustness under various types and levels of image distortion.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"64 ","pages":"Article 103087"},"PeriodicalIF":8.0,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143129698","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":"LGGFormer: A dual-branch local-guided global self-attention network for surface defect segmentation","authors":"Gaowei Zhang ,&nbsp;Yang Lu ,&nbsp;Xiaoheng Jiang ,&nbsp;Shaohui Jin ,&nbsp;Shupan Li ,&nbsp;Mingliang Xu","doi":"10.1016/j.aei.2024.103099","DOIUrl":"10.1016/j.aei.2024.103099","url":null,"abstract":"<div><div>In industrial manufacturing, efficient and accurate surface defect detection is paramount. Recently, CNN-based defect segmentation networks have achieved significant success but have limitations in capturing global contextual information. Although Transformer models excel in global modeling, they often lack sufficient attention to local details. To combine the advantages of CNN and Transformer, this paper proposes a dual-branch local-guided global self-attention network (LGGFormer) for Surface Defect Segmentation. Considering the unique characteristics and computational differences between CNN and Transformer, we propose Local-Guided Global Attention Self-Attention (LGGSA) for extracting global and local information. LGGSA computes localized attention through a sliding window to capture rich contextual details. These local features are then aggregated for global attention computation, enabling the model to focus on areas signified as important by local information. To address the problems of tiny defects and low background contrast, we enhance the learning process by adding supervision to the CNN branch, forcing the branch to learn detailed boundary information. In addition, to take full advantage of the different modeling potentials of CNN and Transformer, we designed the Cross-Branch Feature Interaction Module (CBFI), which achieves a deep interaction between the two features through correlation-weighted integration to optimize feature extraction and representation. Finally, the edge-guided decoder (EGD) utilizes the boundary information extracted by the CNN to guide feature fusion to compensate for the loss of detail information. Experimental results on three public defect datasets demonstrate that our method exhibits promising performance.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"64 ","pages":"Article 103099"},"PeriodicalIF":8.0,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143129636","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":"EEG-based floor vibration serviceability evaluation using machine learning","authors":"Jiang Li ,&nbsp;Weizhao Tang ,&nbsp;Jiepeng Liu ,&nbsp;Yunfei Zhao ,&nbsp;Y.Frank Chen","doi":"10.1016/j.aei.2024.103089","DOIUrl":"10.1016/j.aei.2024.103089","url":null,"abstract":"<div><div>The emergence of novel floor systems has made the vibration serviceability evaluation, conducted through testing and finite element simulation, a time-consuming process that struggles to accurately reflect the user experience. Even when occupant feelings are taken into account, the evaluations may be subjective. This study introduced electroencephalogram (EEG) to grade the ranges of peak accelerations (ACCs) and maximum transient vibration values (MTVVs). To achieve this goal, a supervised learning algorithm, the eXtreme Gradient Boosting (XGBoost), were adopted to conduct binary classification to recognize the threshold of peak ACCs and MTVVs. Accelerometers and an EEG acquisition instrument were utilized to simultaneously capture the ACC dataset and the EEG of volunteers. Characteristic EEG time-domain curves were then obtained by averaging the preprocessed curves corresponding to specific ranges of peak ACCs. The vibration-induced event-related potential components, P50 (the positive potential component with 50 ms latency) and N200 (the negative potential component with 200 ms latency), were identified based on the averaged EEG curves. Additionally, the peak amplitude and peak latency were calculated using cognitive neuroscience methods. The study results suggest that the potential for floor vibration-induced components is around 10 μV. Lastly, XGBoost was utilized to identify the thresholds of different ranges of peak ACCs and MTVVs using EEG time-domain and frequency-domain features. The classification accuracy according to MTVV using XGBoost can reach up to 99 %. This study quantified human perception of floor vibrations based on EEG and optimized peak ACC and MTVV threshold for the cold-formed steel floor vibration serviceability evaluation.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"64 ","pages":"Article 103089"},"PeriodicalIF":8.0,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143129699","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 fuzzy dematel-based delegated Proof-of-Stake consensus mechanism for medical model fusion on blockchain","authors":"Zhi Li ,&nbsp;Fuhe Liang ,&nbsp;Ming Li","doi":"10.1016/j.aei.2024.103095","DOIUrl":"10.1016/j.aei.2024.103095","url":null,"abstract":"<div><div>To ensure consensus regarding the contribution of distributed medical institutions to data models and the transformation of their application value, this paper proposes a fuzzy DEMATEL-based delegated proof-of-stake consensus mechanism for medical model fusion on blockchain. By utilizing transparent, verifiable consensus methods and monitorable on-chain distributed service logic, this framework determines the value-added performance and value-added application of distributed models. Considering that traditional consensus mechanisms are designed primarily for static, deterministic numerical data, they fall short in terms of accommodating consensus for dynamic, interval-based models. To address this limitation, we propose an enhancement to the DPOS consensus mechanism by using fuzzy DEMATEL. This approach enables contribution measurement and consensus for distributed models on the basis of interval-based model characteristics, thereby improving the interpretability of contribution assessments in medical institutions. Since the current lack of application paradigms for data models in distributed environments limits the value conversion of models at the application layer, we propose the construction of a distributed application logic using blockchain and smart contracts. By leveraging smart contracts to protect data privacy and model ownership, this approach enables the standardized and service-oriented transformation of application values. Finally, we conducted an experimental case study using a real medical image diagnostic model to verify and evaluate the feasibility and efficiency of the proposed framework, and a prototype system is established to demonstrate the distributed model consensus and service requirements when collaborating with companies in real-life scenarios. Four sets of experiments were conducted to ensure the feasibility and efficiency of both the distributed consensus and the distributed service process. The results indicate that the proposed consensus mechanism achieves distributed consensus with a latency of approximately 0.2853 s. While the proposed distributed service framework has disadvantages in terms of the throughput and average latency, the differences are minimal—only 0.3937 requests per second and 0.4060 s, respectively, compared with on-chain business creation. Additionally, compared with on-chain business creation, the framework increases CPU and memory utilization by just 15.8902% and 2.4697%, respectively.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"64 ","pages":"Article 103095"},"PeriodicalIF":8.0,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143130279","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}