Advanced Engineering Informatics最新文献

{"title":"Dynamic heterogeneous resource allocation in post-disaster relief operation considering fairness","authors":"Yuying Long ,&nbsp;Peng Sun ,&nbsp;Gangyan Xu","doi":"10.1016/j.aei.2024.102858","DOIUrl":"10.1016/j.aei.2024.102858","url":null,"abstract":"<div><div>Efficient and fair resource allocation is essential in post-disaster relief operations to save lives and mitigate losses. However, due to the highly dynamic and uncertain relief supplies and rescue demands, as well as the complex interdependent relationships among heterogeneous relief resources, the practice of relief resource allocation frequently suffers from low efficiency or unfairness, thus delaying the response activities or even causing social tensions. To address these problems, this paper investigates the heterogeneous relief resource allocation problem and develops a dynamic solution method for efficient and fair allocations. Specifically, a heterogeneous resource allocation model is built to maximize efficiency considering the tight collaboration among resources. A Gini-based fairness evaluation metric is proposed for assessing allocation fairness, and an analysis of the balance between fairness and efficiency is conducted. Then, a dynamic resource allocation method is designed based on the rolling horizon framework, with an Adaptive Dynamic REsource Allocation Method (A-DREAM) developed to balance allocation fairness and efficiency in dynamic scenarios. The performance of the proposed method is verified through systematic experimental case studies, and potential factors affecting allocation fairness are investigated. Finally, the managerial implications for practical relief operations are also derived through sensitivity analysis.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"62 ","pages":"Article 102858"},"PeriodicalIF":8.0,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142442566","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":"Latent space alignment based domain adaptation (LSADA) for fault diagnosis of rotating machinery","authors":"Yong Chae Kim ,&nbsp;Jin Uk Ko ,&nbsp;Jinwook Lee ,&nbsp;Taehun Kim ,&nbsp;Joon Ha Jung ,&nbsp;Byeng D. Youn","doi":"10.1016/j.aei.2024.102862","DOIUrl":"10.1016/j.aei.2024.102862","url":null,"abstract":"<div><div>Fault diagnosis of rotating machinery is essential to minimize damage and downtime in industrial fields. With the development of artificial intelligence, deep-learning-based fault diagnosis has gained significant attention. However, changes in the data distribution from machinery operating under different conditions have led to insufficient diagnostic accuracy. Additionally, the lack of labeled data in industrial settings hampers the performance of these deep-learning algorithms. To address these issues, unsupervised domain adaptation (UDA)-based fault diagnosis methods have been increasingly explored for robust diagnosis under varying conditions. Traditional UDA methods, however, struggle to adapt to hard-to-adapt classes as they focus only on reducing global distribution discrepancies, leading to misclassification and reduced performance for these classes. In this paper, we propose a latent space alignment based domain adaptation (LSADA) approach to overcome this limitation. LSADA reduces local distribution discrepancies by sequentially aligning minority regions and minimizing the distance between source and target data in high-dimensional latent space. Additionally, the feature extractor and predictor in LSADA are synchronized by generating reliable pseudo labels from unlabeled target data. The proposed method is validated using both open-source and experimental datasets, demonstrating that LSADA outperforms existing UDA-based fault-diagnosis algorithms. Moreover, a physical analysis of the method addresses the black-box issue, a common limitation of deep-learning approaches.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"62 ","pages":"Article 102862"},"PeriodicalIF":8.0,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142442729","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":"Explainable AI for engineering design: A unified approach of systems engineering and component-based deep learning demonstrated by energy-efficient building design","authors":"Philipp Geyer ,&nbsp;Manav Mahan Singh ,&nbsp;Xia Chen","doi":"10.1016/j.aei.2024.102843","DOIUrl":"10.1016/j.aei.2024.102843","url":null,"abstract":"<div><div>Data-driven models created by machine learning (ML) have gained importance in all fields of design and engineering. They have high potential to assist decision-makers in creating novel artifacts with better performance and sustainability. However, limited generalization and the black-box nature of these models lead to limited explainability and reusability. To overcome this situation, we developed a component-based approach to create partial component models by ML. This component-based approach aligns deep learning with systems engineering (SE). The key contribution of the component-based method is that activations at interfaces between the components are interpretable engineering quantities. In this way, the hierarchical component system forms a deep neural network (DNN) that a priori integrates interpretable information for explainability of predictions. The large range of possible configurations in composing components allows the examination of novel unseen design cases outside training data. The matching of parameter ranges of components using similar probability distributions produces reusable, well-generalizing, and trustworthy models. The approach adapts the model structure to SE methods and domain knowledge. We examine the performance of the approach in the field of energy-efficient building design: First, we observed better generalization of the component-based method by analyzing prediction accuracy outside the training data. Especially for representative designs that are different in structure, we observed a much higher accuracy (<em>R</em>² = 0.94) compared to conventional monolithic methods (<em>R</em>² <em>=</em> 0.71). Second, we illustrate explainability by demonstrating how sensitivity information from SE and an interpretable model based on rules from low-depth decision trees serve engineering design. Third, we evaluate explainability using qualitative and quantitative methods that demonstrate the matching of preliminary knowledge and data-driven derived strategies and show correctness of activations at component interfaces compared to white-box simulation results (envelope components: <em>R</em>² = 0.92..0.99; zones: <em>R</em>² = 0.78..0.93).</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"62 ","pages":"Article 102843"},"PeriodicalIF":8.0,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142442730","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":"Interpreting what typical fault signals look like via prototype-matching","authors":"Qian Chen ,&nbsp;Xingjian Dong ,&nbsp;Zhike Peng","doi":"10.1016/j.aei.2024.102849","DOIUrl":"10.1016/j.aei.2024.102849","url":null,"abstract":"<div><div>Neural networks, with powerful nonlinear mapping and classification capabilities, are widely applied in mechanical fault diagnosis to ensure safety. However, being typical black-box models, their application is restricted in high-reliability-required scenarios. To understand the classification logic and explain what typical fault signals look like, the prototype matching network (PMN) is proposed by combining the human-inherent prototype-matching with the autoencoder (AE). The PMN matches AE-extracted feature with each prototype and selects the most similar prototype as the prediction result. This novel PMN has three interpreting paths, which explains the classification logic, depicts the typical fault signals and pinpoints the crucial fault-related frequency causing high similarity with matched prototype in model’s view. Conventional diagnosis and domain generalization experiments demonstrate its competitive diagnostic performance and distinguished advantages in representation learning. Besides, the learned typical fault signals (<em>i.e.</em>, sample-level prototypes) showcase the ability for denoising and extracting subtle key features that experts find challenging to capture. This ability broadens human understanding and provides a promising solution to feedback from interpretable research into the knowledge of fault diagnosis.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"62 ","pages":"Article 102849"},"PeriodicalIF":8.0,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142446800","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":"Depth-informed point cloud-to-BIM registration for construction inspection using augmented reality","authors":"Han Liu ,&nbsp;Donghai Liu ,&nbsp;Junjie Chen","doi":"10.1016/j.aei.2024.102867","DOIUrl":"10.1016/j.aei.2024.102867","url":null,"abstract":"<div><div>Augmented reality (AR) is increasingly being used to assist construction inspection onsite. Underpinning this AR-assisted inspection is a technique called registration, which aims to align the physical world with a digital building information model (BIM) so that the as-built can be intuitively compared with the as-designed. Despite its importance, how to precisely and efficiently register BIM to the physical world still remains a challenge. This paper contributes to tackling the challenge by proposing a novel depth-informed point cloud-to-BIM registration (D-PC2BIM) algorithm. The idea is to enhance registration performance by estimating the depth of a sparse point cloud to inform interpolation of the missing points and to extract the endpoints that matter most in a registration. A novel integration algorithm is proposed to improve the success rate of final registration. Experiments demonstrate the effectiveness of the proposed algorithm, which outperformed existing approaches with higher accuracy and faster speed. The contribution of the study resides in the development of the D-PC2BIM algorithm and a demonstration of its applicability in enabling construction inspection using AR.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"62 ","pages":"Article 102867"},"PeriodicalIF":8.0,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142446801","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":"Entity alignment method for aeronautical metrology domain based on multi-perspective entity embedding","authors":"Shengjie Kong ,&nbsp;Xiang Huang ,&nbsp;Shuanggao Li ,&nbsp;Gen Li ,&nbsp;Dong Zhang","doi":"10.1016/j.aei.2024.102908","DOIUrl":"10.1016/j.aei.2024.102908","url":null,"abstract":"<div><div>The accuracy and consistency of metrology data are the cornerstones of the safety and reliability of aircraft throughout aeronautical products’ lifecycles. Due to the heterogeneous nature of metrology data derived from various sources, knowledge silos commonly emerge, complicating the integration and reuse of knowledge. This study introduces an entity alignment model leveraging multi-perspective embedding. It employs a multi-scale graph convolutional network enhanced by a gating mechanism that aggregates multi-hop neighborhood features to capture the structural embeddings of nodes. Additionally, the model utilizes TransD for representing complex relationships and BERT for capturing entity attributes, facilitating more comprehensive entity representations. Entity alignment is then accomplished by integrating structural, relational, and attribute embeddings using a weighted strategy. In this study, we conducted experimental validation on aeronautical metrology data and also assessed our proposed model on five benchmark datasets. The results indicate that our model significantly outperforms comparative models, demonstrating its potential to enhance the management and application of aeronautical metrology data.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"62 ","pages":"Article 102908"},"PeriodicalIF":8.0,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142552950","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":"Segmentation-aware prior assisted joint global information aggregated 3D building reconstruction","authors":"Hongxin Peng ,&nbsp;Yongjian Liao ,&nbsp;Weijun Li ,&nbsp;Chuanyu Fu ,&nbsp;Guoxin Zhang ,&nbsp;Ziquan Ding ,&nbsp;Zijie Huang ,&nbsp;Qiku Cao ,&nbsp;Shuting Cai","doi":"10.1016/j.aei.2024.102904","DOIUrl":"10.1016/j.aei.2024.102904","url":null,"abstract":"<div><div>Multi-View Stereo plays a pivotal role in civil engineering by facilitating 3D modeling, precise engineering surveying, quantitative analysis, as well as monitoring and maintenance. It serves as a valuable tool, offering high-precision and real-time spatial information crucial for various engineering projects. However, Multi-View Stereo algorithms encounter challenges in reconstructing weakly-textured regions within large-scale building scenes. In these areas, the stereo matching of pixels often fails, leading to inaccurate depth estimations. Based on the Segment Anything Model and RANSAC algorithm, we propose an algorithm that accurately segments weakly-textured regions and constructs their plane priors. These plane priors, combined with triangulation priors, form a reliable prior candidate set. Additionally, we introduce a novel global information aggregation cost function. This function selects optimal plane prior information based on global information in the prior candidate set, constrained by geometric consistency during the depth estimation update process. Experimental results on both the ETH3D benchmark dataset, aerial dataset, building dataset and real scenarios substantiate the superior performance of our method in producing 3D building models compared to other state-of-the-art methods. In summary, our work aims to enhance the completeness and density of 3D building reconstruction, carrying implications for broader applications in urban planning and virtual reality.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"62 ","pages":"Article 102904"},"PeriodicalIF":8.0,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142552954","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 two-stage learning framework for imbalanced semi-supervised domain generalization fault diagnosis under unknown operating conditions","authors":"Chuanxia Jian,&nbsp;Heen Chen,&nbsp;Yinhui Ao,&nbsp;Xiaobo Zhang","doi":"10.1016/j.aei.2024.102878","DOIUrl":"10.1016/j.aei.2024.102878","url":null,"abstract":"<div><div>The diagnosis of mechanical faults under unknown operating conditions has been extensively investigated. In real industrial scenarios, fault diagnosis often faces challenges such as class imbalance, scarcity of class labels, and domain shifts. Existing methods cannot simultaneously address these issues. Therefore, this study proposes an imbalanced semi-supervised domain generalization-based fault diagnosis (ISDGFD) learning paradigm and develops a two-stage learning framework to tackle these issues. In the first stage, labeled data is preprocessed to address class imbalance, key features are extracted using a multi-scale convolutional neural network with a self-attention mechanism, and domain-invariant and class-aware features are initially learned through multi-domain adversarial learning and supervised learning, respectively. In the second stage, reliable pseudo-labeled samples are selected and a weighted pseudo-labeled loss is used to retrain the model, further enhancing generalization capability. Extensive experiments were conducted on the CWRU and HUST datasets. The proposed method achieved average scores of 0.85 in <em>Recall</em>, 0.87 in <em>F-score</em>, and 0.92 in <em>Accuracy</em> on the CWRU dataset, and 0.8052 in <em>Recall</em>, 0.7747 in <em>F-score</em>, and 0.8398 in <em>Accuracy</em> on the HUST dataset. These results outperform those of existing state-of-the-art semi-supervised Domain Generalization-based Fault Diagnosis (DGFD) methods and are comparable to the results of fully-supervised imbalanced DGFD methods, demonstrating its effectiveness for ISDGFD under unknown operating conditions.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"62 ","pages":"Article 102878"},"PeriodicalIF":8.0,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142532006","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 visual identification method with position recovering and contour comparison for highly similar non-planar aviation angle pieces","authors":"Qiang He ,&nbsp;Jun Yang ,&nbsp;Haoyun Li ,&nbsp;Yang Hui ,&nbsp;Aiming Xu ,&nbsp;Ruchen Chen ,&nbsp;Zhengjie Xue ,&nbsp;Junkun Qi","doi":"10.1016/j.aei.2024.102901","DOIUrl":"10.1016/j.aei.2024.102901","url":null,"abstract":"<div><div>The assembly quality of angle-piece connectors in aviation equipment significantly affects its structural stability and flight safety. In the production environment, there are many highly similar angle pieces mixed together, making it difficult for workers to distinguish them. Additionally, the complex non-planar structure of the angle pieces and the extremely small differences between them render conventional identification methods ineffective. This paper proposes a new visual identification method for highly similar non-planar aviation angle pieces based on position recovering and contour comparison. Our method integrates overhead and side-view information, effectively separating non-planar regions in angle piece images and accurately extracting the characteristic contours of planar regions. By using the fillet features of the angle pieces for position recognition and adjustment, the method addresses the issue of difficult position recovering of small-sized angle pieces, achieving precise identification of their types. The results indicate that for 30 types of highly similar angle pieces with minimum dimension differences of 0.1 mm and minimum angle variances of 0.1 degrees, the method proposed achieves a position recovering error of less than 1 % and a correct identification rate of 94.33 %. This demonstrates practical significance for the automation of angle pieces production in aviation equipment.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"62 ","pages":"Article 102901"},"PeriodicalIF":8.0,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142572917","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":"Improved air traffic flow prediction in terminal areas using a multimodal spatial–temporal network for weather-aware (MST-WA) model","authors":"Yang Zeng ,&nbsp;Minghua Hu ,&nbsp;Haiyan Chen ,&nbsp;Ligang Yuan ,&nbsp;Sameer Alam ,&nbsp;Dabin Xue","doi":"10.1016/j.aei.2024.102935","DOIUrl":"10.1016/j.aei.2024.102935","url":null,"abstract":"<div><div>Accurately predicting air traffic flow in terminal areas is critical for balancing demand and capacity, particularly under challenging weather conditions. However, the complex interactions between weather patterns and air traffic make reliable predictions difficult. To address this issue, we propose a novel approach called the Multimodal Spatial-Temporal network for Weather-Aware prediction (MST-WA), designed to enhance air traffic flow prediction (ATFP) in terminal areas. Our method begins by constructing a spatial–temporal graph that captures the topology of the terminal area, including airports, routes, and fixes as nodes. A weather-aware module is then introduced, leveraging a Residual Network (ResNet) and attention mechanism to model the deep spatial–temporal correlations in the Weather Avoidance Field (WAF). The proposed model architecture integrates five key branches: arrival flow, departure flow, graph network topology, weather conditions, and flow constraint control, with predictions generated via an attention-based Long Short-Term Memory (LSTM) network. Experimental results using real-world data from Guangzhou Baiyun Airport, China, show that MST-WA outperforms baseline models in ATFP. Furthermore, a case study in convective weather scenarios demonstrates the model’s adaptability and effectiveness. We believe that the proposed model can serve as a valuable tool for air traffic controllers, enhancing decision-making and improving overall air traffic management.</div></div>","PeriodicalId":50941,"journal":{"name":"Advanced Engineering Informatics","volume":"62 ","pages":"Article 102935"},"PeriodicalIF":8.0,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142659193","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}