alexandria engineering journal最新文献_第10页

Performance enhancement and hydraulic optimization of water treatment processes: A case study of Kafr El-Sheikh Water Purification Plant, Egypt 水处理工艺的性能增强和水力优化：以埃及Kafr El-Sheikh净水厂为例

IF 6.8 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

alexandria engineering journal

Pub Date : 2025-12-26 DOI: 10.1016/j.aej.2025.12.034

Shimaa.M. Meleha, Mohamed Tarek Sorour, Medhat Moustafa, Samia A. Aly

Access to clean drinking water remains a significant challenge in developing countries due to increasing demand. This study evaluates the efficiency of the Kafr El-Sheikh Water Purification Plant (KWPP). KWPP is a conventional plant without any advanced units. Hydraulic analysis revealed that the existing sedimentation tanks exceeded the allowable surface overflow rate (108 m³/m²/day) and weir loading rate (864 m³/m²/day), necessitating redesign in accordance with the Egyptian Code of Design Principles. The focus is on redesigning the plant to meet current and future water demands efficiently, with a phased expansion plan extending to 2062. Using the WatPro 4.0 water treatment process simulator, the study explores optimized chlorination strategies and advanced treatment technologies to minimize the formation of Disinfection byproducts (DBPs). The simulation examines adjustments to chlorine dosing based on influent water quality, integrating granular activated carbon (GAC) adsorption to remove organic matter, and applying ultrafiltration (UF) membrane technology to stabilize chlorine levels. The optimized approach successfully reduced the required initial chlorine dose to 2 mg/L and consistently maintained a chlorine residual of 2 mg/L, while maintaining THMs and HAA5s concentrations below 10 µg/L throughout the year. The findings highlight the importance of pre-treatment techniques in reducing DBP precursors before post-chlorination, ensuring safer drinking water.

由于需求不断增加，在发展中国家获得清洁饮用水仍然是一项重大挑战。本研究评估了Kafr El-Sheikh净水厂（KWPP）的效率。KWPP是一个没有先进装置的常规电厂。水力分析表明，现有的沉淀池超过了允许的地表溢流率（108 m³/m²/天）和堰加载率（864 m³/m²/天），需要根据埃及设计原则规范重新设计。重点是重新设计工厂，以有效地满足当前和未来的用水需求，分阶段扩建计划将持续到2062年。利用WatPro 4.0水处理过程模拟器，该研究探索了优化的氯化策略和先进的处理技术，以最大限度地减少消毒副产物（DBPs）的形成。模拟研究了根据进水水质调整氯剂量，整合颗粒活性炭（GAC）吸附去除有机物，并应用超滤（UF）膜技术稳定氯水平。优化后的方法成功地将所需的初始氯剂量降低到2 mg/L，并始终保持2 mg/L的氯残留量，同时将THMs和HAA5s浓度全年保持在10 µg/L以下。研究结果强调了预处理技术在氯化后减少DBP前体的重要性，从而确保更安全的饮用水。

{"title":"Performance enhancement and hydraulic optimization of water treatment processes: A case study of Kafr El-Sheikh Water Purification Plant, Egypt","authors":"Shimaa.M. Meleha, Mohamed Tarek Sorour, Medhat Moustafa, Samia A. Aly","doi":"10.1016/j.aej.2025.12.034","DOIUrl":"10.1016/j.aej.2025.12.034","url":null,"abstract":"<div><div>Access to clean drinking water remains a significant challenge in developing countries due to increasing demand. This study evaluates the efficiency of the Kafr El-Sheikh Water Purification Plant (KWPP). KWPP is a conventional plant without any advanced units. Hydraulic analysis revealed that the existing sedimentation tanks exceeded the allowable surface overflow rate (108 m³/m²/day) and weir loading rate (864 m³/m²/day), necessitating redesign in accordance with the Egyptian Code of Design Principles. The focus is on redesigning the plant to meet current and future water demands efficiently, with a phased expansion plan extending to 2062. Using the WatPro 4.0 water treatment process simulator, the study explores optimized chlorination strategies and advanced treatment technologies to minimize the formation of Disinfection byproducts (DBPs). The simulation examines adjustments to chlorine dosing based on influent water quality, integrating granular activated carbon (GAC) adsorption to remove organic matter, and applying ultrafiltration (UF) membrane technology to stabilize chlorine levels. The optimized approach successfully reduced the required initial chlorine dose to 2 mg/L and consistently maintained a chlorine residual of 2 mg/L, while maintaining THMs and HAA5s concentrations below 10 µg/L throughout the year. The findings highlight the importance of pre-treatment techniques in reducing DBP precursors before post-chlorination, ensuring safer drinking water<strong>.</strong></div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"134 ","pages":"Pages 610-620"},"PeriodicalIF":6.8,"publicationDate":"2025-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145837780","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}

引用次数: 0

Impact of numerical simulation and fractionality of the 3D fractional WBBM model using GERF and MGERF methods 基于GERF和MGERF方法的三维分数WBBM模型数值模拟和分数性影响

IF 6.8 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

alexandria engineering journal

Pub Date : 2025-12-26 DOI: 10.1016/j.aej.2025.12.043

Abdulla Al Mamun , Samsun Nahar Ananna , Chunhui Lu , Zhenfeng Zhang , Mithun Biswas , Shaik Baized Al Limon , Md. Asaduzzaman

This study recovers several novel accurate solutions to the 3D fractional Wazwaz-Benjamin-Bona-Mahony (WBBM) equation within the framework of numerous nonlinear physical phenomena originating from water wave mechanics. This is accomplished by transforming the WBBM equation into an ordinary differential equation (ODE). The ODE then uses two effective methods based on the conformable derivative: the Generalized Exponential Rational Function (GERF) and Modified Generalized Exponential Rational Function (MGERF) Methods. Periodic solutions, w-shaped solitons, single and multiple solitons, dark-bright, and Jacobi elliptic doubly periodic type solutions are thus explored. Applications of the GERF and MGERF approach in many scientific and technical domains assist in expanding our understanding of nonlinear systems, establishing mathematical methodologies, and supporting research solutions. The Modified Variational Iteration (MVI) method, a numerical technique, is employed to derive the approximate solutions to the WBBM problem. An analysis is conducted between this inquiry's findings and those previously acquired through different approaches. All produced wave solutions are determined to be novel in the sense of applied technique, fractionality, and unconstrained parameters. The consequences of unconstrained parameters and fractionality on the resulting solutions are explained physically and shown in a figure. When fractionality and the number of unbound parameters rise, the wave portents shift. Finally, this article dynamically demonstrates that appropriate transformation and relevant GERF and MGERF techniques are more helpful in studying the dynamics of water waves and might be used in future research to clarify other physical phenomena.

本文在水波力学的非线性物理现象框架下，对三维分数阶wazwazz - benjamin - bona - mahony （WBBM）方程恢复了几种新的精确解。这是通过将WBBM方程转换为常微分方程（ODE）来实现的。在此基础上，采用了两种有效的基于可调导数的方法：广义指数有理函数法（GERF）和修正广义指数有理函数法（MGERF）。研究了周期解、w型孤子、单孤子和多孤子、暗亮解和Jacobi椭圆双周期解。GERF和MGERF方法在许多科学和技术领域的应用有助于扩展我们对非线性系统的理解，建立数学方法，并支持研究解决方案。采用改进变分迭代（MVI）方法，推导了WBBM问题的近似解。对这次调查的结果和以前通过不同方法获得的结果进行了分析。所有产生的波解在应用技术、分数性和无约束参数方面都是新颖的。无约束参数和分数对结果解的影响在物理上得到解释，并在图中显示。当分数度和非定界参数的数量增加时，波的前兆发生移位。最后，本文动态地论证了适当的变换以及相关的GERF和MGERF技术更有助于研究水波的动力学，并可能在未来的研究中用于阐明其他物理现象。

{"title":"Impact of numerical simulation and fractionality of the 3D fractional WBBM model using GERF and MGERF methods","authors":"Abdulla Al Mamun , Samsun Nahar Ananna , Chunhui Lu , Zhenfeng Zhang , Mithun Biswas , Shaik Baized Al Limon , Md. Asaduzzaman","doi":"10.1016/j.aej.2025.12.043","DOIUrl":"10.1016/j.aej.2025.12.043","url":null,"abstract":"<div><div>This study recovers several novel accurate solutions to the 3D fractional Wazwaz-Benjamin-Bona-Mahony (WBBM) equation within the framework of numerous nonlinear physical phenomena originating from water wave mechanics. This is accomplished by transforming the WBBM equation into an ordinary differential equation (ODE). The ODE then uses two effective methods based on the conformable derivative: the Generalized Exponential Rational Function (GERF) and Modified Generalized Exponential Rational Function (MGERF) Methods. Periodic solutions, w-shaped solitons, single and multiple solitons, dark-bright, and Jacobi elliptic doubly periodic type solutions are thus explored. Applications of the GERF and MGERF approach in many scientific and technical domains assist in expanding our understanding of nonlinear systems, establishing mathematical methodologies, and supporting research solutions. The Modified Variational Iteration (MVI) method, a numerical technique, is employed to derive the approximate solutions to the WBBM problem. An analysis is conducted between this inquiry's findings and those previously acquired through different approaches. All produced wave solutions are determined to be novel in the sense of applied technique, fractionality, and unconstrained parameters. The consequences of unconstrained parameters and fractionality on the resulting solutions are explained physically and shown in a figure. When fractionality and the number of unbound parameters rise, the wave portents shift. Finally, this article dynamically demonstrates that appropriate transformation and relevant GERF and MGERF techniques are more helpful in studying the dynamics of water waves and might be used in future research to clarify other physical phenomena.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"134 ","pages":"Pages 621-643"},"PeriodicalIF":6.8,"publicationDate":"2025-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145837783","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}

引用次数: 0

SR-PAN-EffNet: A collaborative optimization approach for low-quality image classification and restoration SR-PAN-EffNet：一种低质量图像分类与恢复的协同优化方法

IF 6.8 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

alexandria engineering journal

Pub Date : 2025-12-24 DOI: 10.1016/j.aej.2025.12.029

Jun Li , Dong Liu

Low-quality images, due to degradation issues such as noise and compression artifacts, often lead to feature extraction distortion in classification models, thereby reducing classification accuracy. This issue is particularly prominent in practical computer vision applications. To address this, this paper proposes the SR-PAN-EffNet model, which integrates a semantic-guided SRGAN restoration module with a noise-aware PANet attention module, and employs end-to-end joint training to achieve the collaborative optimization of “restoration serving classification”. Experimental results show that the model achieves Top-1 accuracy of 68.5% and 57.6% on the ImageNet-1K and CIFAR-100 low-quality datasets, respectively, improving by 4.7–6.4 percentage points over NFNet-F4, with PSNR and SSIM also leading. Ablation experiments reveal that removing core modules results in a 2.9–6.8 percentage point decrease in accuracy. Future work will focus on improving the model’s real-time performance and robustness through lightweight design, extreme degradation adaptive optimization, and category-adaptive guidance, aiming to promote its application in scenarios such as surveillance and medical imaging.

低质量图像由于噪声和压缩伪影等退化问题，往往会导致分类模型的特征提取失真，从而降低分类精度。这个问题在实际的计算机视觉应用中尤为突出。针对这一问题，本文提出SR-PAN-EffNet模型，该模型将语义引导的SRGAN恢复模块与噪声感知的PANet关注模块集成在一起，采用端到端联合训练实现“恢复服务分类”的协同优化。实验结果表明，该模型在ImageNet-1K和CIFAR-100低质量数据集上分别达到了68.5%和57.6%的Top-1准确率，比NFNet-F4提高了4.7-6.4个百分点，其中PSNR和SSIM也处于领先地位。烧蚀实验表明，去除核心模块会导致精度降低2.9-6.8个百分点。未来的工作将重点通过轻量化设计、极端退化自适应优化和类别自适应制导来提高模型的实时性和鲁棒性，以促进其在监控和医学成像等场景中的应用。

{"title":"SR-PAN-EffNet: A collaborative optimization approach for low-quality image classification and restoration","authors":"Jun Li , Dong Liu","doi":"10.1016/j.aej.2025.12.029","DOIUrl":"10.1016/j.aej.2025.12.029","url":null,"abstract":"<div><div>Low-quality images, due to degradation issues such as noise and compression artifacts, often lead to feature extraction distortion in classification models, thereby reducing classification accuracy. This issue is particularly prominent in practical computer vision applications. To address this, this paper proposes the SR-PAN-EffNet model, which integrates a semantic-guided SRGAN restoration module with a noise-aware PANet attention module, and employs end-to-end joint training to achieve the collaborative optimization of “restoration serving classification”. Experimental results show that the model achieves Top-1 accuracy of 68.5% and 57.6% on the ImageNet-1K and CIFAR-100 low-quality datasets, respectively, improving by 4.7–6.4 percentage points over NFNet-F4, with PSNR and SSIM also leading. Ablation experiments reveal that removing core modules results in a 2.9–6.8 percentage point decrease in accuracy. Future work will focus on improving the model’s real-time performance and robustness through lightweight design, extreme degradation adaptive optimization, and category-adaptive guidance, aiming to promote its application in scenarios such as surveillance and medical imaging.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"134 ","pages":"Pages 542-555"},"PeriodicalIF":6.8,"publicationDate":"2025-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145837445","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}

引用次数: 0

A Müntz spectral method for solving fractional Fredholm integro–differential equations with convergence analysis 求解分数阶Fredholm积分微分方程的<s:1> ntz谱法及其收敛性分析

IF 6.8 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

alexandria engineering journal

Pub Date : 2025-12-24 DOI: 10.1016/j.aej.2025.12.040

Jabbar Mahdy Hadaad , Masoud Allame , Habeeb Abed Kadhim Aal-Rkhais , Majid Tavassoli-Kajani

The solutions of fractional order equations might involve certain fractional-power terms that classical orthogonal polynomials connot match. Consequently, the advancement of effective numerical methods using generalized orthogonal polynomials such as fractional Jacobi, Müntz and fractional Chelyshkov functions enhances the precision of approximate solutions. This paper proposes a novel Müntz–Legendre spectral approach for a class of fractional Fredholm integro–differential equations with Caputo or Caputo–Fabrizio (CF) derivative. We first construct a matrix method that transforms the given linear problem to a system of linear algebraic equations. Then, we give a comprehensive convergence analysis of the proposed method. As opposed to the Caputo definition, the derivative of CF has no singularity at the end point, so it is expected that it is more convenient for numerical studies. Nonetheless, we propose a new approach to deal with the singularity in the definition of the Caputo derivative, efficiently. Some numerical examples are given and comparisons with other existing methods are provided to demonstrate the efficiency and accuracy of the proposed method. The extension of the proposed method to nonlinear problems via the linearization technique is also illustrated in an example.

分数阶方程的解可能涉及某些经典正交多项式无法匹配的分数次项。因此，利用分数阶Jacobi、m ntz和分数阶Chelyshkov函数等广义正交多项式的有效数值方法的进步提高了近似解的精度。针对一类具有Caputo或Caputo - fabrizio （CF）导数的分数阶Fredholm积分微分方程，提出了一种新的m ntz - legendre谱方法。我们首先构造一个矩阵方法，将给定的线性问题转化为线性代数方程组。然后，对该方法进行了全面的收敛性分析。与Caputo定义相反，CF的导数在端点处没有奇点，因此有望更方便于数值研究。尽管如此，我们还是提出了一种新的方法来有效地处理卡普托导数定义中的奇点。最后给出了数值算例，并与现有方法进行了比较，验证了该方法的有效性和准确性。通过实例说明了该方法通过线性化技术推广到非线性问题。

{"title":"A Müntz spectral method for solving fractional Fredholm integro–differential equations with convergence analysis","authors":"Jabbar Mahdy Hadaad , Masoud Allame , Habeeb Abed Kadhim Aal-Rkhais , Majid Tavassoli-Kajani","doi":"10.1016/j.aej.2025.12.040","DOIUrl":"10.1016/j.aej.2025.12.040","url":null,"abstract":"<div><div>The solutions of fractional order equations might involve certain fractional-power terms that classical orthogonal polynomials connot match. Consequently, the advancement of effective numerical methods using generalized orthogonal polynomials such as fractional Jacobi, Müntz and fractional Chelyshkov functions enhances the precision of approximate solutions. This paper proposes a novel Müntz–Legendre spectral approach for a class of fractional Fredholm integro–differential equations with Caputo or Caputo–Fabrizio (CF) derivative. We first construct a matrix method that transforms the given linear problem to a system of linear algebraic equations. Then, we give a comprehensive convergence analysis of the proposed method. As opposed to the Caputo definition, the derivative of CF has no singularity at the end point, so it is expected that it is more convenient for numerical studies. Nonetheless, we propose a new approach to deal with the singularity in the definition of the Caputo derivative, efficiently. Some numerical examples are given and comparisons with other existing methods are provided to demonstrate the efficiency and accuracy of the proposed method. The extension of the proposed method to nonlinear problems via the linearization technique is also illustrated in an example.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"134 ","pages":"Pages 585-595"},"PeriodicalIF":6.8,"publicationDate":"2025-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145837446","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}

引用次数: 0

Intelligent fault detection of zero-sample rotating machinery with embedded physical knowledge of vibration envelope and time-frequency analysis 基于振动包络物理知识和时频分析的零样本旋转机械故障智能检测

IF 6.8 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

alexandria engineering journal

Pub Date : 2025-12-24 DOI: 10.1016/j.aej.2025.12.030

Guoqiang Li , Cheng Chen , Qijun Liu , Yiwei Cheng , Meirong Wei , Defeng Wu

Data-driven fault detection methods for rotating machinery have achieved impressive performance. Nevertheless, their practical deployment faces substantial challenges, including the high cost of acquiring fault data and inherent difficulties in constructing accurate models. This paper integrates domain knowledge of vibration signal analysis and proposes a physical knowledge-driven modeling method for rotating machinery fault detection with zero fault sample. First, Hilbert envelope analysis is introduced to attenuate the impact of fundamental frequency components. Subsequently, multi-dimensional evaluation metrics are used to select and filter multiple time-frequency analysis methods, thereby constructing a robust time-frequency knowledgebase. Then, three novel loss function driven by zero-fault samples is designed based on the differences between the selected time-frequency analysis methods and physical knowledge regarding the similarity among sliding window samples in monitoring signals. Finally, an end-to-end intelligent fault detection algorithm is developed based on the trained feature encoder and the introduced physical knowledge. The effectiveness of the proposed method is validated on both the rolling bearing experimental platform and the turbine experimental platform. The validation results demonstrate that the proposed method can achieve intelligent fault detection modelling without any fault samples, attaining fault detection test accuracies of 98.97 % and 96.19 % in the two respective case studies.

数据驱动的旋转机械故障检测方法已经取得了令人瞩目的成绩。然而，它们的实际部署面临着巨大的挑战，包括获取故障数据的高成本和构建准确模型的固有困难。结合振动信号分析的领域知识，提出了一种零故障样本下旋转机械故障检测的物理知识驱动建模方法。首先，引入希尔伯特包络分析来减弱基频分量的影响。然后，利用多维评价指标对多种时频分析方法进行选择和过滤，构建鲁棒的时频知识库。然后，基于所选时频分析方法与监测信号滑动窗样本相似性物理知识的差异，设计了三种新的零故障样本驱动的损失函数。最后，基于训练好的特征编码器和引入的物理知识，开发了端到端的智能故障检测算法。在滚动轴承实验平台和涡轮实验平台上验证了该方法的有效性。验证结果表明，该方法可以在不需要任何故障样本的情况下实现智能故障检测建模，在两个案例中分别获得了98.97 %和96.19 %的故障检测测试准确率。

{"title":"Intelligent fault detection of zero-sample rotating machinery with embedded physical knowledge of vibration envelope and time-frequency analysis","authors":"Guoqiang Li , Cheng Chen , Qijun Liu , Yiwei Cheng , Meirong Wei , Defeng Wu","doi":"10.1016/j.aej.2025.12.030","DOIUrl":"10.1016/j.aej.2025.12.030","url":null,"abstract":"<div><div>Data-driven fault detection methods for rotating machinery have achieved impressive performance. Nevertheless, their practical deployment faces substantial challenges, including the high cost of acquiring fault data and inherent difficulties in constructing accurate models. This paper integrates domain knowledge of vibration signal analysis and proposes a physical knowledge-driven modeling method for rotating machinery fault detection with zero fault sample. First, Hilbert envelope analysis is introduced to attenuate the impact of fundamental frequency components. Subsequently, multi-dimensional evaluation metrics are used to select and filter multiple time-frequency analysis methods, thereby constructing a robust time-frequency knowledgebase. Then, three novel loss function driven by zero-fault samples is designed based on the differences between the selected time-frequency analysis methods and physical knowledge regarding the similarity among sliding window samples in monitoring signals. Finally, an end-to-end intelligent fault detection algorithm is developed based on the trained feature encoder and the introduced physical knowledge. The effectiveness of the proposed method is validated on both the rolling bearing experimental platform and the turbine experimental platform. The validation results demonstrate that the proposed method can achieve intelligent fault detection modelling without any fault samples, attaining fault detection test accuracies of 98.97 % and 96.19 % in the two respective case studies.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"134 ","pages":"Pages 570-584"},"PeriodicalIF":6.8,"publicationDate":"2025-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145837039","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}

引用次数: 0

Decoupled feature extraction and correspondence modeling for deformable medical image registration using large kernel attention 基于大核关注的可变形医学图像配准解耦特征提取与对应建模

IF 6.8 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

alexandria engineering journal

Pub Date : 2025-12-24 DOI: 10.1016/j.aej.2025.12.033

Zhou Zhou , Chenglong Fu , Chuang Wang , Ping Zhu , Kaijian Xia , Pengjiang Qian

Medical image registration aims to align images acquired at different times, perspectives, or modalities. Traditional deep learning approaches typically combine moving and fixed images as joint inputs, limiting the model’s ability to independently process image features and achieve accurate voxel-level correspondences. This paper introduces a novel registration framework, DELCA-Net, which decouples feature extraction from correspondence modeling using a large kernel attention (LKA) mechanism. DELCA-Net utilizes a dual-stream shared encoder that separately processes moving and fixed images, capturing long-range semantic dependencies. Additionally, we propose a Cross-Resolution Attention Refinement Module (CARM) that enhances multi-scale spatial correspondences via a coarse-to-fine fusion strategy, improving anatomical feature alignment across resolutions. Comprehensive experiments conducted on the OASIS and IXI datasets demonstrate that our method consistently improves registration accuracy while offering better interpretability and computational efficiency. On the IXI dataset, our model achieves a 1.2% increase in the DICE coefficient while requiring only 1.9% of the parameters of TransMorph. Additionally, the implementation of our method is publicly available at https://github.com/windandink/DELCA-NET.

医学图像配准的目的是对齐在不同时间、视角或模式下获得的图像。传统的深度学习方法通常将运动和固定图像作为联合输入，限制了模型独立处理图像特征和实现精确体素级对应的能力。本文介绍了一种新的配准框架DELCA-Net，该框架利用大核注意（large kernel attention， LKA）机制将特征提取与对应建模解耦。DELCA-Net采用双流共享编码器，分别处理移动和固定图像，捕获远程语义依赖。此外，我们提出了一个跨分辨率注意力细化模块（CARM），该模块通过粗到细的融合策略增强了多尺度空间对应，改善了跨分辨率的解剖特征对齐。在OASIS和IXI数据集上进行的综合实验表明，该方法在提高配准精度的同时具有更好的可解释性和计算效率。在IXI数据集上，我们的模型实现了DICE系数增加1.2%，而只需要1.9%的TransMorph参数。此外，我们的方法的实现可以在https://github.com/windandink/DELCA-NET上公开获得。

{"title":"Decoupled feature extraction and correspondence modeling for deformable medical image registration using large kernel attention","authors":"Zhou Zhou , Chenglong Fu , Chuang Wang , Ping Zhu , Kaijian Xia , Pengjiang Qian","doi":"10.1016/j.aej.2025.12.033","DOIUrl":"10.1016/j.aej.2025.12.033","url":null,"abstract":"<div><div>Medical image registration aims to align images acquired at different times, perspectives, or modalities. Traditional deep learning approaches typically combine moving and fixed images as joint inputs, limiting the model’s ability to independently process image features and achieve accurate voxel-level correspondences. This paper introduces a novel registration framework, DELCA-Net, which decouples feature extraction from correspondence modeling using a large kernel attention (LKA) mechanism. DELCA-Net utilizes a dual-stream shared encoder that separately processes moving and fixed images, capturing long-range semantic dependencies. Additionally, we propose a Cross-Resolution Attention Refinement Module (CARM) that enhances multi-scale spatial correspondences via a coarse-to-fine fusion strategy, improving anatomical feature alignment across resolutions. Comprehensive experiments conducted on the OASIS and IXI datasets demonstrate that our method consistently improves registration accuracy while offering better interpretability and computational efficiency. On the IXI dataset, our model achieves a 1.2% increase in the DICE coefficient while requiring only 1.9% of the parameters of TransMorph. Additionally, the implementation of our method is publicly available at <span><span>https://github.com/windandink/DELCA-NET</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"134 ","pages":"Pages 556-569"},"PeriodicalIF":6.8,"publicationDate":"2025-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145837443","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}

引用次数: 0

Precise tunnel lining crack detection using multimodal fusion transformer and metaheuristic-optimized ResNet-50 基于多模态融合变压器和元启发式优化的ResNet-50的隧道衬砌裂纹精确检测

IF 6.8 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

alexandria engineering journal

Pub Date : 2025-12-24 DOI: 10.1016/j.aej.2025.12.022

Zhen Chen , Zhixi Shen

Automated crack detection in tunnel linings is critical for ensuring infrastructure safety and facilitating efficient long-term maintenance. Manual inspection methods are typically slow, labour-intensive, and inconsistent, highlighting the necessity for advanced automated solutions. This research presents a Mathematical Multimodal Fusion Transformer-Based Optimization (MMFTO) framework that integrates multiple tunnel-lining image modalities to enable robust crack identification. The framework utilizes an optimized multimodal fusion transformer encoder to extract and combine complementary features that are often missed by unimodal systems. Hyper-parameter tuning is conducted using an Improved Piranha Foraging Optimization Algorithm (IPFOA) algorithm, followed by feature refinement with a Modified Sunflower Optimization Algorithm (MSFOA). Final classification is performed by a DeepResNet-50 model. The proposed MMFTO–MSFO–DeepResNet50 system is evaluated on a newly curated multimodal tunnel-lining dataset and compared with existing deep-learning and unimodal approaches. The model achieves 95 % accuracy, 92 % precision, 92 % F1-score, 91 % recall, a mean average precision (mAP) of 94.7 %, and a mean intersection over union (mIoU) of 93.6 %. Further evaluation on Crack500, Tunnel200, and DeepCrack datasets demonstrates strong robustness and generalizability. These results indicate that the framework offers significant potential for real-world tunnel monitoring and intelligent infrastructure management.

隧道衬砌的自动裂缝检测对于确保基础设施安全和促进有效的长期维护至关重要。人工检查方法通常是缓慢的，劳动密集型的，并且不一致的，突出了先进的自动化解决方案的必要性。本研究提出了一种基于数学多模态融合变压器的优化（MMFTO）框架，该框架集成了多种隧道衬砌图像模式，以实现鲁棒的裂缝识别。该框架利用优化的多模态融合变压器编码器来提取和组合单模态系统经常错过的互补特征。使用改进的食人鱼觅食优化算法（IPFOA）进行超参数调优，然后使用改进的向日葵优化算法（MSFOA）进行特征细化。最终分类由DeepResNet-50模型进行。提出的MMFTO-MSFO-DeepResNet50系统在新编制的多模式隧道衬里数据集上进行了评估，并与现有的深度学习和单模态方法进行了比较。该模型的准确率为95 %，精密度为92 %，F1-score为92 %，召回率为91 %，平均平均精度（mAP）为94.7 %，平均交联（mIoU）为93.6 %。对Crack500、Tunnel200和DeepCrack数据集的进一步评估显示出较强的鲁棒性和泛化性。这些结果表明，该框架为现实世界的隧道监测和智能基础设施管理提供了巨大的潜力。

{"title":"Precise tunnel lining crack detection using multimodal fusion transformer and metaheuristic-optimized ResNet-50","authors":"Zhen Chen , Zhixi Shen","doi":"10.1016/j.aej.2025.12.022","DOIUrl":"10.1016/j.aej.2025.12.022","url":null,"abstract":"<div><div>Automated crack detection in tunnel linings is critical for ensuring infrastructure safety and facilitating efficient long-term maintenance. Manual inspection methods are typically slow, labour-intensive, and inconsistent, highlighting the necessity for advanced automated solutions. This research presents a Mathematical Multimodal Fusion Transformer-Based Optimization (MMFTO) framework that integrates multiple tunnel-lining image modalities to enable robust crack identification. The framework utilizes an optimized multimodal fusion transformer encoder to extract and combine complementary features that are often missed by unimodal systems. Hyper-parameter tuning is conducted using an Improved Piranha Foraging Optimization Algorithm (IPFOA) algorithm, followed by feature refinement with a Modified Sunflower Optimization Algorithm (MSFOA). Final classification is performed by a DeepResNet-50 model. The proposed MMFTO–MSFO–DeepResNet50 system is evaluated on a newly curated multimodal tunnel-lining dataset and compared with existing deep-learning and unimodal approaches. The model achieves 95 % accuracy, 92 % precision, 92 % F1-score, 91 % recall, a mean average precision (mAP) of 94.7 %, and a mean intersection over union (mIoU) of 93.6 %. Further evaluation on Crack500, Tunnel200, and DeepCrack datasets demonstrates strong robustness and generalizability. These results indicate that the framework offers significant potential for real-world tunnel monitoring and intelligent infrastructure management.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"134 ","pages":"Pages 527-541"},"PeriodicalIF":6.8,"publicationDate":"2025-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145837444","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}

引用次数: 0

Can Dengue be controlled? Assessing vaccination and insecticide strategies with optimal control 登革热能被控制吗？以最优控制评估疫苗接种和杀虫剂策略

IF 6.8 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

alexandria engineering journal

Pub Date : 2025-12-23 DOI: 10.1016/j.aej.2025.12.039

Kamrunnesa Mayeda , Sadia Akter Lima , Amin Ullah , Md. Kamrujjaman

Dengue fever is an enormous global public health burden, with millions of cases reported annually. In this paper, we have introduced a mathematical model that is capable of describing the transmission of dengue with hospitalization and vaccination and characterizing the infection’s dynamics. We calculate the basic reproduction number,

0 < R_{0} < 1

, that indicates the die-out of this infection. Initially, the fundamental mathematical findings are illustrated. Further, we compare different population dynamics with vaccination and without vaccination, and the results are satisfying and can also control the infection. We examine diverse characteristics’ impact on distinct population dynamics. In addition, the functions that are in charge of controlling this infection are used to come up with the best control strategies, which gives us the best control of characterization. We solve the model of optimal control numerically and do the correlative study between the control strategies: prevention and insecticide, which are the strongest options to rid a community of this disease. The finding suggests that including hospitalization and vaccination in the transmission model and control strategies (prevention and insecticide) can drastically cut down the infection of dengue fever as well as stop it from further spreading in a community.

登革热是一个巨大的全球公共卫生负担，每年报告的病例达数百万例。在本文中，我们介绍了一个数学模型，能够描述登革热的传播与住院和疫苗接种和表征感染的动态。我们计算基本繁殖数0<；R0<1，这表明这种感染的死亡。首先，说明了基本的数学发现。此外，我们比较了接种疫苗和未接种疫苗的不同种群动态，结果令人满意，也可以控制感染。我们研究了不同特征对不同种群动态的影响。此外，控制这种感染的功能被用来提出最好的控制策略，这给了我们最好的特征控制。对最优控制模型进行了数值求解，并对预防和杀虫剂这两种控制策略之间的相关性进行了研究，这两种控制策略是消除该疾病的最强选择。这一发现表明，在传播模式和控制策略（预防和杀虫剂）中纳入住院和疫苗接种可以大大减少登革热的感染，并阻止其在社区中进一步传播。

{"title":"Can Dengue be controlled? Assessing vaccination and insecticide strategies with optimal control","authors":"Kamrunnesa Mayeda , Sadia Akter Lima , Amin Ullah , Md. Kamrujjaman","doi":"10.1016/j.aej.2025.12.039","DOIUrl":"10.1016/j.aej.2025.12.039","url":null,"abstract":"<div><div>Dengue fever is an enormous global public health burden, with millions of cases reported annually. In this paper, we have introduced a mathematical model that is capable of describing the transmission of dengue with hospitalization and vaccination and characterizing the infection’s dynamics. We calculate the basic reproduction number, <span><math><mrow><mn>0</mn><mo><</mo><msub><mrow><mi>R</mi></mrow><mrow><mn>0</mn></mrow></msub><mo><</mo><mn>1</mn></mrow></math></span>, that indicates the die-out of this infection. Initially, the fundamental mathematical findings are illustrated. Further, we compare different population dynamics with vaccination and without vaccination, and the results are satisfying and can also control the infection. We examine diverse characteristics’ impact on distinct population dynamics. In addition, the functions that are in charge of controlling this infection are used to come up with the best control strategies, which gives us the best control of characterization. We solve the model of optimal control numerically and do the correlative study between the control strategies: prevention and insecticide, which are the strongest options to rid a community of this disease. The finding suggests that including hospitalization and vaccination in the transmission model and control strategies (prevention and insecticide) can drastically cut down the infection of dengue fever as well as stop it from further spreading in a community.</div></div>","PeriodicalId":7484,"journal":{"name":"alexandria engineering journal","volume":"134 ","pages":"Pages 508-525"},"PeriodicalIF":6.8,"publicationDate":"2025-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145837784","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}

引用次数: 0

Corrigendum to "Provide personalized programming learning for individuals based on large language models'" [Alex. Eng. J., 132 (2025) 396–406] “基于大型语言模型为个人提供个性化编程学习”的勘误表[Alex]。Eng。J., 132 (2025) 396-406]

IF 6.8 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

alexandria engineering journal

Pub Date : 2025-12-23 DOI: 10.1016/j.aej.2025.12.045

Chong Li , Xin Lee , Xiaojin Wu

引用次数: 0

Modeling predator-prey dynamics with stochastic differential equations: Patterns of collective hunting and nonlinear predation effects 用随机微分方程模拟捕食者-猎物动力学：集体狩猎模式和非线性捕食效应

IF 6.8 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

alexandria engineering journal

Pub Date : 2025-12-22 DOI: 10.1016/j.aej.2025.12.038

Junyi Qi, Tôn Việt Tạ

We investigate predator–prey school interactions in aquatic environments using a stochastic differential equation (SDE)-based, particle-level model that incorporates attraction, repulsion, alignment, and environmental noise. Two predation strategies — center attack and nearest attack — are examined to assess their effects on prey survival, predator efficiency, and group dynamics. Simulations reveal diverse emergent behaviors such as prey dispersal and regrouping, oscillatory predation with collective defense, and predator encirclement. Results show that collective hunting enhances capture efficiency compared to solitary attacks, but benefits diminish beyond a critical predator group size due to intra-predator competition. This work provides new insights into cooperative predation and introduces a generalizable SDE framework for analyzing predator–prey interactions.

研究人员利用基于随机微分方程（SDE）的粒子级模型研究了水生环境中捕食者-猎物群体的相互作用，该模型包含了吸引力、排斥力、对齐和环境噪声。研究了两种捕食策略——中心攻击和最近攻击——以评估它们对猎物生存、捕食者效率和群体动力学的影响。模拟结果揭示了多种突发性行为，如猎物分散和重组，振荡捕食和集体防御，以及捕食者包围。结果表明，与单独攻击相比，集体狩猎提高了捕获效率，但由于捕食者之间的竞争，超过了关键的捕食者群体规模，收益就会减少。这项工作为合作捕食提供了新的见解，并为分析捕食者-猎物相互作用引入了一个可推广的SDE框架。

引用次数: 0