alexandria engineering journal最新文献

{"title":"Predicting the condition of small and medium-span bridges using hybrid machine learning","authors":"Luo-meng Zhang ,&nbsp;Dong Liang ,&nbsp;Hai-bin Huang ,&nbsp;Yao-zong Hu ,&nbsp;Jin-song Zhang","doi":"10.1016/j.aej.2025.12.056","DOIUrl":"10.1016/j.aej.2025.12.056","url":null,"abstract":"<div><div>Medium- and small-span beam bridges are critical components of modern transportation networks. Studying their degradation patterns based on long-term inspection data is crucial for making informed maintenance and repair decisions. To accurately predict the technical condition of medium and small-span bridges, this study proposes a bridge degradation prediction model based on a hybrid machine learning algorithm integrating Recursive Feature Elimination (RFE), Seagull Optimization Algorithm (SSOA), Genetic Algorithm (GA), and Natural Gradient Boosting (NGBoost). First, a comprehensive database of bridge technical conditions was constructed using 12 years of inspection data from 600 bridges in a specific province. RFE was employed to select 10 key factors, including bridge age, traffic volume, and bearing ratings, to optimize the model's input dimensions. Subsequently, the SSOA-GA method was used to optimize the hyperparameters of the NGBoost model, improving the prediction accuracy and generalization capabilities. To further improve the model’s interpretability, SHAP analysis was conducted, revealing the critical influence of factors like bridge age, traffic volume, and bearing ratings on bridge technical conditions. The results indicate that the proposed model demonstrates excellent performance in prediction accuracy and generalization, achieving an R² value of 0.975 and an RMSE of 0.115. It effectively captures the nonlinear relationships between bridge conditions and multiple influencing factors. Moreover, with the help of SHAP analysis, the relative contributions of input factors were quantified, confirming the critical influence of bridge age, traffic volume, and bearing ratings on bridge technical conditions. This significantly enhances the model's interpretability and practicality, providing a scientific basis for formulating bridge maintenance and repair strategies.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"137 ","pages":"Pages 270-287"},"PeriodicalIF":6.8,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146074935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fiber reinforced cementitious matrix bond behavior on masonry substrate","authors":"Jin Lu ,&nbsp;Xiaofan Liao","doi":"10.1016/j.aej.2026.01.008","DOIUrl":"10.1016/j.aej.2026.01.008","url":null,"abstract":"<div><div>In this study, the Multi Pier MP method, previously presented for Fiber Reinforced Polymer (FRP) delamination on masonry substrates, is adapted for the Fiber Reinforced Cementitious Matrix (FRCM) single lap shear behavior. Based on this method, an assemblage of vertical (piers) and diagonal (braces) truss members forms a two-dimensional truss structure, representing the entire composite system, including fibers, matrix, and masonry substrate. Piers and braces carry the normal and shear stresses of the system, respectively. With the help of the materials' axial stress-strain curve, the non-linear behavior of truss members was identified. All possible failure modes, such as rupture, fiber slippage, and matrix shear damage, were considered. Validation on four experimental FRCM reinforced masonry pillars demonstrated that the model can estimate the composite's single lap shear behavior and their failure mechanisms with acceptable accuracy. Additionally, all internal stresses and displacement profiles were obtained across the reinforcements for both elastic and plastic ranges up to failure. Despite its accuracy and comprehensiveness, minimal time was required to implement this method in any commercial code, only needing to address non-linearity in unidirectional elements.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"137 ","pages":"Pages 225-241"},"PeriodicalIF":6.8,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146036710","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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 resource provision method for UAV-assisted edge computing based on improved DPoS consensus mechanism","authors":"Jing Zhang,&nbsp;Tianming Yang,&nbsp;Qiang Guo,&nbsp;Zhiqiang Yang,&nbsp;Jingfang Wang","doi":"10.1016/j.aej.2026.01.043","DOIUrl":"10.1016/j.aej.2026.01.043","url":null,"abstract":"<div><div>With the proliferation of IoT devices and the widespread adoption of 5G technology, UAV-assisted edge computing (UAVAEC) architecture is rapidly expanding. However, the openness of wireless communication links renders the network vulnerable to malicious attacks, making security a significant concern in UAVAEC scenarios. We propose a blockchain-based approach for resource provisioning in UAVAEC architecture, ensuring secure network communication. To solve the service response latency of IoT terminals rendered by blockchain consensus process, this article adopts an offline strategy when recording the resource allocation process and crucially introduces an improved DPoS consensus mechanism. This mechanism aims to make the blockchain lightweight, and make the entire system run more efficiently in the UAVAEC environment. To strike a balance between efficiency and decentralization, we have designed an improved transaction authentication procedure centered around the competition for accounting rights. Extensive simulation experiments confirm the performance of our proposed algorithm. Compared to benchmark algorithms, it achieves higher throughput, lower block generation delay, and greater utility for candidate nodes.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"137 ","pages":"Pages 386-400"},"PeriodicalIF":6.8,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146074982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advancing sustainable water management: The pivotal role of civil engineering in navigating environmental and urban challenges","authors":"Ali Akbar Firoozi ,&nbsp;Ali Asghar Firoozi ,&nbsp;Taoufik Saidani","doi":"10.1016/j.aej.2026.01.034","DOIUrl":"10.1016/j.aej.2026.01.034","url":null,"abstract":"<div><div>This study rigorously evaluates the critical role of civil engineering in advancing sustainable water management, a cornerstone for achieving global environmental sustainability and resource conservation objectives. Amid increasing water demands, exacerbated by climate change and rapid urbanization, the imperative to incorporate innovative practices within water management systems has intensified. This manuscript offers a comprehensive analysis of cutting-edge technological advancements and methodologies currently transforming water supply, wastewater treatment, and stormwater management. It highlights the significant impact of these innovations in meeting sustainability goals and confronts the complex challenges that obstruct their broader adoption. Additionally, the paper outlines strategic approaches to surmount financial, technological, regulatory, and societal obstacles, thereby promoting a sustainable, efficient, and equitable water resource management paradigm. Through the integration of theoretical frameworks with empirical case studies, this research aims to ignite further academic exploration, policy refinement, and practical applications that uphold the principles of sustainability within the field of civil engineering.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"137 ","pages":"Pages 360-385"},"PeriodicalIF":6.8,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146074985","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analysis of cycloid motor output characteristics based on fluid simulation","authors":"Jiaxing Lu ,&nbsp;Lingrong Kong ,&nbsp;Yu Wang ,&nbsp;Jiong Li","doi":"10.1016/j.aej.2026.01.019","DOIUrl":"10.1016/j.aej.2026.01.019","url":null,"abstract":"<div><div>In the field of drilling engineering, the rubber screw motor adopts the cycloidal principle for drilling, and the rubber bushing will carbonize and fail when the drilling at 180°C and above. As a positive displacement motor, the cycloidal motor has high temperature and corrosion resistance, low speed, and high torque. It is used in traditional mechanical engineering fields, such as the hydraulic cycloidal motor of the hoist, while the hydraulic cycloidal motor applied in the drilling fluid field has been blank. Therefore, the cycloidal motor in drilling fluid medium is proposed in this paper, which is different from the traditional mechanical cycloidal motor in oil medium and applied in the field of high-temperature drilling engineering. Based on the clearance flow theory and energy conservation law, the mathematical model of fluid leakage of the cycloidal motor was calculated. Through Matlab programming, the cloud diagram of fluid pressure drop, clearance, and viscosity on the leakage of the cycloidal motor was calculated numerically. The characteristic curve of motor numerical calculation was compared and verified by experimental data of the OMT 160 cycloidal motor produced by Danfoss Company. A theoretical basis for selecting clearance of machining and manufacturing all-metal cycloidal motor were provided.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"137 ","pages":"Pages 159-170"},"PeriodicalIF":6.8,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146036657","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Driver emotion regulation via ambient lighting and music: An EEG-based ergonomic evaluation for intelligent cockpit","authors":"Yong Peng ,&nbsp;Ziteng Zhang ,&nbsp;Zhuoxi Jiang ,&nbsp;Chenxi Li ,&nbsp;Chaojie Fan ,&nbsp;Meng Zheng ,&nbsp;Xianhui Wu","doi":"10.1016/j.aej.2026.02.001","DOIUrl":"10.1016/j.aej.2026.02.001","url":null,"abstract":"<div><div>Effective regulation of drivers’ negative emotions is crucial for traffic safety, particularly in intelligent vehicles increasingly rely on multimodal human-machine interactions. This study integrates neuroergonomics and automotive engineering perspectives to investigate the neural mechanisms through which sensory modulation supports emotional recovery during driving, and to determine whether combined auditory-visual cues produce synergistic benefits beyond unimodal effects. Twenty participants were exposed to aversive audiovisual stimuli followed by simulated driving, during which EEG features (energy, differential entropy, and asymmetric entropy), behavioral indicators, and subjective ratings were obtained. Source-level analysis focused on the dorsolateral prefrontal cortex (dlPFC), one of the regions central to autonomic and affective regulation. Results within this participants group indicated that multisensory stimulation improved emotional and functional recovery, with EEG activity showing tighter coupling with driving performance than with subjective reports, suggesting neural responses may provide more direct markers of safety-relevant restoration. Fast-tempo music paired with green lighting elicited a clear synergistic effect under the tested conditions, whereas its combination with yellow lighting yielded only additive improvements. These findings advance neuroergonomic understanding of how multisensory cues modulate affective and cognitive states during driving and offer preliminary guidance for developing adaptive, emotion-aware cockpit systems aimed at improving driver safety and well-being.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"138 ","pages":"Pages 51-65"},"PeriodicalIF":6.8,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146186311","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Vote3D-AD: Unsupervised point cloud anomaly localization via varied defect synthesis and differentiable vote-clustering","authors":"Dinh-Cuong Hoang ,&nbsp;Phan Xuan Tan ,&nbsp;Anh-Nhat Nguyen ,&nbsp;Ta Huu Anh Duong ,&nbsp;Tuan-Minh Huynh ,&nbsp;Minh-Anh Nguyen ,&nbsp;Duc-Manh Nguyen ,&nbsp;Minh-Duc Cao ,&nbsp;Duc-Huy Ngo ,&nbsp;Minh-Quang Vu ,&nbsp;Van-Duc Vu ,&nbsp;Van-Thiep Nguyen ,&nbsp;Thu-Uyen Nguyen ,&nbsp;Khanh-Toan Phan ,&nbsp;Van-Hiep Duong","doi":"10.1016/j.aej.2026.01.024","DOIUrl":"10.1016/j.aej.2026.01.024","url":null,"abstract":"<div><div>Existing three-dimensional (3D) anomaly detection approaches typically rely on reconstruction, external memory banks, or fixed-radius clustering and often fail to generalize to noisy, irregularly sampled industrial scans or to capture the full diversity of real defects. We present Vote3D-AD, a single-pass framework that trains only on defect-free data and addresses these gaps with two principal contributions. First, we introduce Varied Defect Synthesis (VDS), a saliency-guided pseudo-anomaly generator that produces diverse, physically plausible defects (bulges, dents, holes, cracks, and surface roughness) together with sensor-level degradations to narrow the synthetic-to-real gap. Second, we develop a vote-and-cluster architecture in which local geometric representations predict learned, scale-aware votes that encode both spatial and boundary cues, and a differentiable soft-assignment clustering module aggregates these votes into coherent anomaly regions without relying on fixed-radius grouping or external memory structures. We evaluated our method on the synthetic Anomaly-ShapeNet benchmark and a new industrial dataset using three metrics: point-level Area Under the Receiver Operating Characteristic curve (AUROC), object-level Area Under the Precision-Recall curve (AUPR), and F1-Score. On average across both benchmarks, our method improves point-level AUROC by 6.7%, AUPR by 10.1% and F1 by 11.2%, and improves object-level AUROC by 5.3%, AUPR by 3.8% and F1 by 5.4% over the strongest baseline, while maintaining inference speeds above 9 frames per second (FPS).</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"137 ","pages":"Pages 171-193"},"PeriodicalIF":6.8,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146036658","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reinforcement learning with priority decentralized PPO for multi-vessel cooperative rescue scheduling in flood disaster","authors":"Yufeng Zhou,&nbsp;Wei Yang,&nbsp;Ying Gong","doi":"10.1016/j.aej.2026.01.047","DOIUrl":"10.1016/j.aej.2026.01.047","url":null,"abstract":"<div><div>Flood rescue operations often suffer from inefficient task assignment and poor coordination among multiple rescue vessels, especially when water conditions change rapidly and rescue demands vary in urgency. This study aims to enhance multi-vessel scheduling by introducing a reinforcement learning-based approach that prioritizes rescue tasks and improves cooperative decision-making. We develop a Priority-aware Distributed Proximal Policy Optimization method (PD_PPO), which combines graph-based environment modeling, a multi-attribute priority evaluation mechanism using the best–worst method, and a distributed reinforcement learning framework. The method guides vessels toward high-value tasks through a priority mask mechanism and reduces joint action-space growth from exponential to linear. The proposed approach is evaluated through extensive simulations, including comparative studies across three rescue scenarios of different scales, tests under varying hydrological and task distribution conditions, and ablation experiments that isolate key model components. Results demonstrate significant improvements over benchmark algorithms, with PD_PPO achieving up to 31.7% higher Task Assignment Rate, 50.0% higher High-priority Task Assignment Rate, and 46.4% higher Resource Utilization Rate. These findings confirm the effectiveness and robustness of the proposed method in supporting coordinated rescue operations.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"138 ","pages":"Pages 96-113"},"PeriodicalIF":6.8,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146186274","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DGGAT: Dual-branch gated graph attention transformer for high-accuracy semantic segmentation","authors":"Jie He","doi":"10.1016/j.aej.2026.01.027","DOIUrl":"10.1016/j.aej.2026.01.027","url":null,"abstract":"<div><div>Semantic segmentation requires both global context and fine-grained details, yet CNNs struggle with long-range dependencies and Transformers can under-represent low-level structure and be computationally heavy. We propose DGGAT, a dual-branch gated graph attention Transformer: a global branch models long-range context, while a graph-embedded local branch groups semantically related pixels into nodes and applies gated graph attention to sharpen boundaries and small objects. An Attention-Based Feature Selection Fusion Module (ASFM) fuses global and local features to suppress redundancy and balance detail with context. On Cityscapes, DGGAT reaches 84.7% mIoU with a ResNet-101 backbone (82.8% with ResNet-50), and on ADE20K it attains 48.2% mIoU, validating both accuracy and efficiency. These results demonstrate that DGGAT effectively integrates global semantics with fine-detail representation.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"137 ","pages":"Pages 123-132"},"PeriodicalIF":6.8,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146036708","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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 gene expression programming-enabled prediction for hot flow stress of 5A06 aluminum alloy used in large structures","authors":"Jing Wang ,&nbsp;Qiang Liang ,&nbsp;Yan Li ,&nbsp;Yong Wang","doi":"10.1016/j.aej.2026.01.011","DOIUrl":"10.1016/j.aej.2026.01.011","url":null,"abstract":"<div><div>Hot rolling of 5A06 aluminum alloy is crucial for manufacturing large structural components in the aerospace and shipbuilding industries. Accurate prediction of the alloy’s hot flow stress is essential for optimizing the rolling process and ensuring product quality. Hot compression experiments were conducted to obtain the experimental data using the Gleeble-3500 in this study. Research was performed at several temperature levels for deformation (specifically 573 K, 623 K, etc., up to 773 K), utilizing diverse strain rates (from 0.01 s⁻¹ to 10 s⁻¹, increasing by 10 times each), concluding with a peak deformation percentage of 60 %. It established Johnson-Cook (J-C), Zerilli-Armstrong (Z-A), and Gene Expression Programming (GEP) constitutive models, evaluating accuracy via statistics and DEFORM-2D finite element simulation (FES). Statistics showed GEP was best: R²= 0.98 (J-C:0.96, Z-A:0.95), lowest RMSE= 11.41(J-C:26.51, Z-A=30.43), MAE= 8.62(J-C:18.83, Z-A: 15.86), AARE= 9.47 % (J-C: 31.40 %, Z-A: 11.64 %). FES further confirmed the GEP model’s superiority, as it exhibited the smallest load deviation from experimental values. Furthermore, deformation stress predictions of non-experimental conditions were conducted under two sets of conditions: a strain rate of 0.1 s⁻¹ with deformation temperatures of 593 K and 643 K, and a deformation temperature of 573 K with strain rates of 0.05 s⁻¹, 0.5 s⁻¹, and 2.5 s⁻¹. The results show that the stress curves at 593 K and 643 K align with the trend of experimental curves at 573 K, 623 K, and 673 K and lie within their corresponding intervals; similarly, the stress curves at 0.05 s⁻¹, 0.5 s⁻¹, and 2.5 s⁻¹ conform to the trend of experimental curves at 0.01 s⁻¹, 0.1 s⁻¹, and 1 s⁻¹, with their positions following the rule that higher strain rates lead to greater deformation stresses. The GEP model can not only effectively predict the flow stress under experimental conditions but also forecast the flow stress under non-experimental deformation conditions, thus providing a valuable tool for the numerical simulation and process optimization of the hot rolling process of 5A06 aluminum alloy.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"137 ","pages":"Pages 537-551"},"PeriodicalIF":6.8,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146074959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}