Advances in Engineering Software最新文献_第9页

An improved YOLOv10-based lightweight multi-scale feature fusion model for road defect detection and its applications 基于yolov10改进的轻型多尺度特征融合道路缺陷检测模型及其应用

IF 4 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Advances in Engineering Software

Pub Date : 2025-06-13 DOI: 10.1016/j.advengsoft.2025.103976

Jianxi Ou , Jianqin Zhang , Haoyu Li , Bin Duan

Intelligent road damage detection is critical for ensuring traffic safety and extending the lifespan of roads. However, existing methods struggle to balance high accuracy and real-time performance in complex detection scenarios and resource-constrained environments. To address this issue, this study proposes a lightweight multi-scale feature fusion model based on an improved YOLOv10—GAS-YOLO. The model utilizes a novel lightweight architecture (GSF-ST) designed through a combination of feature generation, asymmetric convolution, and grouped channel shuffling optimization strategies, significantly reducing computational complexity and parameter count while enhancing both global and local feature representation. To improve multi-scale damage detection performance, GAS-YOLO incorporates an improved bidirectional feature pyramid network (BiFPN) and Swin Transformer module. A resolution halving and channel doubling strategy enhances the detection ability of small targets. Moreover, the WiOU loss function further optimizes bounding box regression accuracy, mitigating errors caused by sample imbalance. Channel pruning techniques are applied to achieve secondary lightweight compression of the model, resulting in significant resource savings. Through comparative experiments and ablation analysis with several advanced damage detection models, this study demonstrates a significant performance improvement of GAS-YOLO. Experimental results show that GAS-YOLO exhibits outstanding performance in multi-scale damage detection tasks, with 5.6 M parameters, 8.4GFLOPs of computational complexity, and a model size of only 5.8 MB. Compared to baseline models, detection accuracy improves by 10.8 %, computational complexity is reduced by 2.57 times, and parameter count is reduced by 1.29 times, with an average detection accuracy of 86.5 % and a single image processing time of 6.1 ms. Validation on both public datasets and self-constructed datasets further proves its real-time processing capability while maintaining high accuracy. The GAS-YOLO model proposed in this study not only provides a practical solution for road damage detection in resource-constrained environments but also offers new insights for intelligent management of intelligent transportation and urban infrastructure, with broad application prospects.

智能道路损伤检测对于确保交通安全和延长道路寿命至关重要。然而，在复杂的检测场景和资源受限的环境中，现有的方法难以平衡高精度和实时性。为了解决这一问题，本研究提出了一种基于改进的YOLOv10-GAS-YOLO的轻量级多尺度特征融合模型。该模型采用了一种新型的轻量级架构（GSF-ST），通过结合特征生成、非对称卷积和分组信道变换优化策略设计，显著降低了计算复杂度和参数数量，同时增强了全局和局部特征表示。为了提高多尺度损伤检测性能，GAS-YOLO结合了改进的双向特征金字塔网络（BiFPN）和Swin Transformer模块。分辨率减半和信道加倍策略提高了小目标的检测能力。此外，WiOU损失函数进一步优化了边界盒回归的精度，减轻了样本不平衡带来的误差。通道修剪技术用于实现模型的二次轻量级压缩，从而显著节省资源。通过与几种先进的损伤检测模型的对比实验和烧蚀分析，本研究证明了GAS-YOLO的性能有显著提高。实验结果表明，GAS-YOLO在多尺度损伤检测任务中表现优异，参数为5.6 M，计算复杂度为4.4 gflops，模型大小仅为5.8 MB，检测精度比基线模型提高10.8%，计算复杂度降低2.57倍，参数数量减少1.29倍，平均检测精度达到86.5%，单幅图像处理时间为6.1 ms。通过对公共数据集和自构建数据集的验证，进一步证明了该方法在保持较高精度的同时具有实时性。本研究提出的GAS-YOLO模型不仅为资源受限环境下的道路损伤检测提供了切实可行的解决方案，也为智能交通和城市基础设施的智能管理提供了新的见解，具有广阔的应用前景。

{"title":"An improved YOLOv10-based lightweight multi-scale feature fusion model for road defect detection and its applications","authors":"Jianxi Ou , Jianqin Zhang , Haoyu Li , Bin Duan","doi":"10.1016/j.advengsoft.2025.103976","DOIUrl":"10.1016/j.advengsoft.2025.103976","url":null,"abstract":"<div><div>Intelligent road damage detection is critical for ensuring traffic safety and extending the lifespan of roads. However, existing methods struggle to balance high accuracy and real-time performance in complex detection scenarios and resource-constrained environments. To address this issue, this study proposes a lightweight multi-scale feature fusion model based on an improved YOLOv10—GAS-YOLO. The model utilizes a novel lightweight architecture (GSF-ST) designed through a combination of feature generation, asymmetric convolution, and grouped channel shuffling optimization strategies, significantly reducing computational complexity and parameter count while enhancing both global and local feature representation. To improve multi-scale damage detection performance, GAS-YOLO incorporates an improved bidirectional feature pyramid network (BiFPN) and Swin Transformer module. A resolution halving and channel doubling strategy enhances the detection ability of small targets. Moreover, the WiOU loss function further optimizes bounding box regression accuracy, mitigating errors caused by sample imbalance. Channel pruning techniques are applied to achieve secondary lightweight compression of the model, resulting in significant resource savings. Through comparative experiments and ablation analysis with several advanced damage detection models, this study demonstrates a significant performance improvement of GAS-YOLO. Experimental results show that GAS-YOLO exhibits outstanding performance in multi-scale damage detection tasks, with 5.6 M parameters, 8.4GFLOPs of computational complexity, and a model size of only 5.8 MB. Compared to baseline models, detection accuracy improves by 10.8 %, computational complexity is reduced by 2.57 times, and parameter count is reduced by 1.29 times, with an average detection accuracy of 86.5 % and a single image processing time of 6.1 ms. Validation on both public datasets and self-constructed datasets further proves its real-time processing capability while maintaining high accuracy. The GAS-YOLO model proposed in this study not only provides a practical solution for road damage detection in resource-constrained environments but also offers new insights for intelligent management of intelligent transportation and urban infrastructure, with broad application prospects.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"208 ","pages":"Article 103976"},"PeriodicalIF":4.0,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144270709","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

Advanced numerical modeling for nonlinear responses of sandwich multiphase composite plates with viscoelastic damping core 粘弹性阻尼芯夹层多相复合材料板非线性响应的先进数值模拟

IF 4 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Advances in Engineering Software

Pub Date : 2025-06-13 DOI: 10.1016/j.advengsoft.2025.103958

Ho-Nam Vu , Duy-Khuong Ly , Umut Topal , Tan Nguyen , T. Nguyen-Thoi

This study introduces an advanced numerical model for the nonlinear dynamic analysis of sandwich multiphase composite plates composed of carbon nanotubes (CNT), carbon fibers, and epoxy, featuring a viscoelastic core modeled using the Golla–Hughes–McTavish (GHM) method. The proposed framework uniquely combines the Cell-Based Smoothed Discrete Shear Gap Method (CS-DSG3) with the sinusoidal–zigzag shear deformation theory, pioneering their integration to improve layerwise modeling and viscoelastic damping analysis. The sinusoidal–zigzag theory effectively captures the continuous in-plane displacement distributions, yielding superior predictions of the layered structure’s mechanical response compared to classical theories. By incorporating the von Kármán displacement–strain relationship, the model effectively captures the passive damped dynamic behavior of viscoelastic core plate under large deformations. The Newmark time integration scheme and Picard’s methods are employed to efficiently solve the resulting nonlinear equations of motion at each time step. Validation against benchmark studies demonstrates the model’s accuracy and reliability in capturing the complex dynamic responses of laminated systems. A comprehensive parametric investigation further explores the impact of material properties, including the volume fractions and configurations of CNTs and carbon fibers, on the nonlinear dynamic behavior. These advancements position the model as a computationally efficient and high-fidelity tool for analyzing the nonlinear dynamics of complex laminated composite structures.

本文引入了一种先进的数值模型，用于碳纳米管（CNT）、碳纤维和环氧树脂组成的夹层多相复合材料板的非线性动力学分析，该模型采用了Golla-Hughes-McTavish （GHM）方法建模。提出的框架独特地将基于单元的平滑离散剪切间隙方法（CS-DSG3）与正弦之字形剪切变形理论相结合，开创了它们的集成，以改进分层建模和粘弹性阻尼分析。与经典理论相比，正弦之字形理论有效地捕获了连续的平面内位移分布，对层状结构的力学响应做出了更好的预测。该模型通过引入von Kármán位移-应变关系，有效地捕捉了粘弹性芯板在大变形下的被动阻尼动力行为。采用Newmark时间积分格式和Picard方法有效地求解每个时间步长的非线性运动方程。对基准研究的验证表明，该模型在捕获层压系统的复杂动态响应方面具有准确性和可靠性。全面的参数研究进一步探讨了材料性能，包括碳纳米管和碳纤维的体积分数和结构，对非线性动态行为的影响。这些进步使该模型成为一种计算效率高、保真度高的工具，用于分析复杂层压复合材料结构的非线性动力学。

{"title":"Advanced numerical modeling for nonlinear responses of sandwich multiphase composite plates with viscoelastic damping core","authors":"Ho-Nam Vu , Duy-Khuong Ly , Umut Topal , Tan Nguyen , T. Nguyen-Thoi","doi":"10.1016/j.advengsoft.2025.103958","DOIUrl":"10.1016/j.advengsoft.2025.103958","url":null,"abstract":"<div><div>This study introduces an advanced numerical model for the nonlinear dynamic analysis of sandwich multiphase composite plates composed of carbon nanotubes (CNT), carbon fibers, and epoxy, featuring a viscoelastic core modeled using the Golla–Hughes–McTavish (GHM) method. The proposed framework uniquely combines the Cell-Based Smoothed Discrete Shear Gap Method (CS-DSG3) with the sinusoidal–zigzag shear deformation theory, pioneering their integration to improve layerwise modeling and viscoelastic damping analysis. The sinusoidal–zigzag theory effectively captures the continuous in-plane displacement distributions, yielding superior predictions of the layered structure’s mechanical response compared to classical theories. By incorporating the von Kármán displacement–strain relationship, the model effectively captures the passive damped dynamic behavior of viscoelastic core plate under large deformations. The Newmark time integration scheme and Picard’s methods are employed to efficiently solve the resulting nonlinear equations of motion at each time step. Validation against benchmark studies demonstrates the model’s accuracy and reliability in capturing the complex dynamic responses of laminated systems. A comprehensive parametric investigation further explores the impact of material properties, including the volume fractions and configurations of CNTs and carbon fibers, on the nonlinear dynamic behavior. These advancements position the model as a computationally efficient and high-fidelity tool for analyzing the nonlinear dynamics of complex laminated composite structures.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"208 ","pages":"Article 103958"},"PeriodicalIF":4.0,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144270708","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

Probabilistic slope stability analysis based on the Hermite-logistic regression approach 基于Hermite-logistic回归方法的概率边坡稳定性分析

IF 4 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Advances in Engineering Software

Pub Date : 2025-06-11 DOI: 10.1016/j.advengsoft.2025.103973

Yi Liang , Zhengpeng Jia , Qinglong Wu , Kefeng Xiao , Ran Yuan , Haizuo Zhou , Yi He

In slope reliability analysis, conventional surrogate model-based analysis methods, such as response surface method, Kriging method, and neural networks method, often rely on the safety factor of slopes for analysis. However, the calculation of safety factors requires repeated iterations using strength reduction, leading to low efficiency in reliability analysis. Addressing this challenge, this manuscript proposes an improved slope reliability analysis method to improve analysis efficiency. This method, which considers the spatial variability of soil parameters, is based on the principles of binary classification concept. It employs the Karhunen-Loève (K-L) expansion to discretize the soil of the slope and generate a random field. By combining Hermite polynomials with logistic regression approach, a surrogate model is established. Using the intrinsic program in FLAC^3D for convergency determination, the stability classification (stable or unstable) for each slope is carried out without reducing the soil strength parameters (using original soil strength parameters). The classification results serve as response values for the Hermite-logistic regression surrogate model, establishing an implicit relationship between random variables and slope stability. The effectiveness of this Hermite-logistic regression method is verified through examples of undrained saturated clay slopes and c-φ soil slopes. The findings indicate that the Hermite-logistic regression model demonstrates remarkable computational efficiency when compared to conventional random finite element calculations, all while maintaining high computational accuracy. Specifically, the proposed method reduces the computational cost by at least a factor of ten while ensuring the attainment of precise results. In addition, a sensitivity analysis is performed to investigate the influence of slope geometric parameters and spatial variability parameters on slope stability and reliability.

在边坡可靠度分析中，传统的基于代理模型的分析方法，如响应面法、Kriging法、神经网络法等，往往依赖于边坡的安全系数进行分析。然而，安全系数的计算需要使用强度折减法进行反复迭代，导致可靠性分析效率较低。针对这一挑战，本文提出了一种改进的边坡可靠度分析方法，以提高分析效率。该方法基于二元分类概念，考虑了土壤参数的空间变异性。采用karhunen - lo (K-L)展开对边坡土体进行离散化，生成随机场。将Hermite多项式与logistic回归方法相结合，建立了一个代理模型。利用FLAC3D中的固有程序进行收敛判定，在不降低土强度参数（使用原土强度参数）的情况下，对每个边坡进行稳定性分类（稳定或不稳定）。分类结果作为Hermite-logistic回归代理模型的响应值，建立了随机变量与边坡稳定性之间的隐式关系。通过不排水饱和粘土边坡和c-φ土边坡实例验证了该方法的有效性。研究结果表明，与传统的随机有限元计算相比，Hermite-logistic回归模型具有显著的计算效率，同时保持了较高的计算精度。具体而言，该方法在确保获得精确结果的同时，将计算成本降低了至少十倍。此外，还对边坡几何参数和空间变异性参数对边坡稳定性和可靠度的影响进行了敏感性分析。

{"title":"Probabilistic slope stability analysis based on the Hermite-logistic regression approach","authors":"Yi Liang , Zhengpeng Jia , Qinglong Wu , Kefeng Xiao , Ran Yuan , Haizuo Zhou , Yi He","doi":"10.1016/j.advengsoft.2025.103973","DOIUrl":"10.1016/j.advengsoft.2025.103973","url":null,"abstract":"<div><div>In slope reliability analysis, conventional surrogate model-based analysis methods, such as response surface method, Kriging method, and neural networks method, often rely on the safety factor of slopes for analysis. However, the calculation of safety factors requires repeated iterations using strength reduction, leading to low efficiency in reliability analysis. Addressing this challenge, this manuscript proposes an improved slope reliability analysis method to improve analysis efficiency. This method, which considers the spatial variability of soil parameters, is based on the principles of binary classification concept. It employs the Karhunen-Loève (K-L) expansion to discretize the soil of the slope and generate a random field. By combining Hermite polynomials with logistic regression approach, a surrogate model is established. Using the intrinsic program in FLAC<sup>3D</sup> for convergency determination, the stability classification (stable or unstable) for each slope is carried out without reducing the soil strength parameters (using original soil strength parameters). The classification results serve as response values for the Hermite-logistic regression surrogate model, establishing an implicit relationship between random variables and slope stability. The effectiveness of this Hermite-logistic regression method is verified through examples of undrained saturated clay slopes and <em>c</em>-<em>φ</em> soil slopes. The findings indicate that the Hermite-logistic regression model demonstrates remarkable computational efficiency when compared to conventional random finite element calculations, all while maintaining high computational accuracy. Specifically, the proposed method reduces the computational cost by at least a factor of ten while ensuring the attainment of precise results. In addition, a sensitivity analysis is performed to investigate the influence of slope geometric parameters and spatial variability parameters on slope stability and reliability.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"208 ","pages":"Article 103973"},"PeriodicalIF":4.0,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144253653","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

Metaheuristic algorithms-optimized machine learning models for FRP-concrete interfacial bond strength prediction 基于元启发式算法优化的frp -混凝土界面粘结强度预测机器学习模型

IF 4 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Advances in Engineering Software

Pub Date : 2025-06-07 DOI: 10.1016/j.advengsoft.2025.103971

Peng Ge , Ou Yang , Jia He , Zhiyu Liu , Hao Chen

Globally, the technique of reinforcing concrete structures with bonded fiber-reinforced polymers (FRP) has become widely adopted. The integrity of the interface between concrete and FRP significantly influences the behavior of the reinforced structure. Consequently, precise prediction of the bond strength at the concrete and FRP interface is crucial for the logical design and assessment of structures that are repaired and reinforced using FRP. This paper utilizes two emerging metaheuristic algorithms, the Slime Mould Algorithm (SMA) and the Dung Beetle Optimization Algorithm (DBO), to improve the performance of machine learning (ML) techniques, including KNN, SVR, GBDT, and XGBoost. Optimizing the ML models with metaheuristic algorithms significantly enhanced the prediction accuracy compared to the non-optimized models. The SMA-GBDT performed better than other ML models, achieving an R² of 0.9492, an MAE of 1.5294, an MSE of 6.4159, an RMSE of 2.5329, and a MAPE of 8.6916, based on the testing dataset. Specifically, the SMA-GBDT model exhibited improvements of 5.83%, 39.04%, 50.75%, 29.82%, and 43.84% in R², MAE, MSE, RMSE, and MAPE, respectively, compared to the non-optimized GBDT. The predictions made by the SMA-GBDT model were higher precision than those provided by the current design codes and existing models.

在全球范围内，结合纤维增强聚合物（FRP）加固混凝土结构的技术已被广泛采用。混凝土与FRP之间界面的完整性对加筋结构的性能有重要影响。因此，精确预测混凝土和FRP界面的粘结强度对于使用FRP修复和加固的结构的逻辑设计和评估至关重要。本文利用两种新兴的元启发式算法——黏菌算法（SMA）和屎壳郎优化算法（DBO）来提高机器学习（ML）技术的性能，包括KNN、SVR、GBDT和XGBoost。与未优化的模型相比，用元启发式算法优化ML模型显著提高了预测精度。基于测试数据，SMA-GBDT比其他ML模型表现更好，R²为0.9492，MAE为1.5294，MSE为6.4159，RMSE为2.5329，MAPE为8.6916。其中，与未优化的GBDT模型相比，SMA-GBDT模型在R²、MAE、MSE、RMSE和MAPE上分别提高了5.83%、39.04%、50.75%、29.82%和43.84%。SMA-GBDT模型的预测精度高于现行设计规范和现有模型的预测精度。

{"title":"Metaheuristic algorithms-optimized machine learning models for FRP-concrete interfacial bond strength prediction","authors":"Peng Ge , Ou Yang , Jia He , Zhiyu Liu , Hao Chen","doi":"10.1016/j.advengsoft.2025.103971","DOIUrl":"10.1016/j.advengsoft.2025.103971","url":null,"abstract":"<div><div>Globally, the technique of reinforcing concrete structures with bonded fiber-reinforced polymers (FRP) has become widely adopted. The integrity of the interface between concrete and FRP significantly influences the behavior of the reinforced structure. Consequently, precise prediction of the bond strength at the concrete and FRP interface is crucial for the logical design and assessment of structures that are repaired and reinforced using FRP. This paper utilizes two emerging metaheuristic algorithms, the Slime Mould Algorithm (SMA) and the Dung Beetle Optimization Algorithm (DBO), to improve the performance of machine learning (ML) techniques, including KNN, SVR, GBDT, and XGBoost. Optimizing the ML models with metaheuristic algorithms significantly enhanced the prediction accuracy compared to the non-optimized models. The SMA-GBDT performed better than other ML models, achieving an <em>R</em>² of 0.9492, an MAE of 1.5294, an MSE of 6.4159, an RMSE of 2.5329, and a MAPE of 8.6916, based on the testing dataset. Specifically, the SMA-GBDT model exhibited improvements of 5.83%, 39.04%, 50.75%, 29.82%, and 43.84% in <em>R</em>², MAE, MSE, RMSE, and MAPE, respectively, compared to the non-optimized GBDT. The predictions made by the SMA-GBDT model were higher precision than those provided by the current design codes and existing models.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"208 ","pages":"Article 103971"},"PeriodicalIF":4.0,"publicationDate":"2025-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144229745","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

Layout optimization design method for thermo-elastic thin-walled structures with lattices and stiffeners 带有加劲肋的热弹性薄壁结构布局优化设计方法

IF 4 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Advances in Engineering Software

Pub Date : 2025-06-07 DOI: 10.1016/j.advengsoft.2025.103962

Yang Li , Tong Gao , Yongbin Huang , Longlong Song , Weihong Zhang

This work proposes a layout optimization design method for thermo-elastic thin-walled structures with lattices and stiffeners in the framework of multi-material topology optimization, in which both the steady-state temperature field and mechanical loads are considered. Firstly, taking into account the design requirements, suitable lattice unit cells are chosen and their equivalent mechanical properties are obtained by the homogenization method. Thus, the candidate lattice unit cells are represented as corresponding virtual homogeneous materials. Meanwhile, the stiffeners are modelled with solid material. Afterwards, a multi-material thermo-elastic structural optimization formulation is established and solved iteratively through gradient-driven optimization algorithms to obtain the optimized layouts of the lattices and stiffeners. In addition, the maximum size constraint and the overall volume constraint with a lower bound are introduced. The former ensures that the solid material takes the form of 'ribs' in the optimization results and the latter could meet the requirement that the design space is filled with lattice or solid material. Finally, numerical tests are conducted to demonstrate the detailed application process and validate the effectiveness of the proposed design method. This work provides an effective design tool for the application of additively manufactured lattice structures in thermo-elastic coupled load-bearing structures.

本文提出了一种在多材料拓扑优化框架下兼顾稳态温度场和机械载荷的格筋热弹性薄壁结构布局优化设计方法。首先，根据设计要求，选择合适的点阵单元，并采用均匀化方法获得其等效力学性能；因此，候选晶格单元被表示为相应的虚拟均质材料。同时，用固体材料对加强筋进行建模。然后，建立了多材料热弹性结构优化公式，并通过梯度驱动优化算法进行迭代求解，得到了优化的格和加强筋布局。此外，还引入了最大尺寸约束和带下界的总体体积约束。前者确保固体材料在优化结果中以“肋”的形式存在，后者可以满足设计空间以晶格或固体材料填充的要求。最后，通过数值试验验证了该方法的具体应用过程，验证了该设计方法的有效性。本工作为增材制造晶格结构在热弹性耦合承重结构中的应用提供了有效的设计工具。

{"title":"Layout optimization design method for thermo-elastic thin-walled structures with lattices and stiffeners","authors":"Yang Li , Tong Gao , Yongbin Huang , Longlong Song , Weihong Zhang","doi":"10.1016/j.advengsoft.2025.103962","DOIUrl":"10.1016/j.advengsoft.2025.103962","url":null,"abstract":"<div><div>This work proposes a layout optimization design method for thermo-elastic thin-walled structures with lattices and stiffeners in the framework of multi-material topology optimization, in which both the steady-state temperature field and mechanical loads are considered. Firstly, taking into account the design requirements, suitable lattice unit cells are chosen and their equivalent mechanical properties are obtained by the homogenization method. Thus, the candidate lattice unit cells are represented as corresponding virtual homogeneous materials. Meanwhile, the stiffeners are modelled with solid material. Afterwards, a multi-material thermo-elastic structural optimization formulation is established and solved iteratively through gradient-driven optimization algorithms to obtain the optimized layouts of the lattices and stiffeners. In addition, the maximum size constraint and the overall volume constraint with a lower bound are introduced. The former ensures that the solid material takes the form of 'ribs' in the optimization results and the latter could meet the requirement that the design space is filled with lattice or solid material. Finally, numerical tests are conducted to demonstrate the detailed application process and validate the effectiveness of the proposed design method. This work provides an effective design tool for the application of additively manufactured lattice structures in thermo-elastic coupled load-bearing structures.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"208 ","pages":"Article 103962"},"PeriodicalIF":4.0,"publicationDate":"2025-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144243458","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 lightweight convolutional neural network-based model and system for defect detection and navigation on bridge road surface 基于轻量级卷积神经网络的桥梁路面缺陷检测与导航模型与系统

IF 4 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Advances in Engineering Software

Pub Date : 2025-06-07 DOI: 10.1016/j.advengsoft.2025.103972

Ronghua Fu , Yufeng Zhang , Drahomír Novák , Alfred Strauss , Maosen Cao

The Faster Region-based Convolutional Neural Network (Faster R-CNN) is widely used for detecting defects on road surface. However, its effectiveness in this task is limited by its large model size and slow detection speed. To address these challenges, two versions of the Faster R-CNN model—small and large—were developed. First, the models were structurally optimized by integrating inverted residual blocks, depthwise separable convolutions, and attention mechanisms to improve efficiency and performance. The large version also incorporated multi-scale feature extraction for enhanced detection capabilities. Second, model pruning was applied to further compress the networks. Extensive ablation experiments were conducted to investigate the relationship between the model's internal structure and its impact on crack detection accuracy and efficiency. The experimental results demonstrate that the proposed models outperform general CNN-based models in bridge surface defect detection, achieving superior detection speed while maintaining high accuracy. The large version exhibits better performance but at the cost of increased model complexity. Testing was conducted on a real-life bridge in Nanjing, China. Additionally, a software application, integrated with a laptop and a smartphone, was deployed to identify defects and map their locations on the bridge, streamlining the detection process. The source code of this software is freely available at https://github.com/DUYA686686/detection-software.git

基于更快区域的卷积神经网络（Faster R-CNN）被广泛应用于路面缺陷检测。然而，由于模型规模大，检测速度慢，限制了该方法在该任务中的有效性。为了应对这些挑战，我们开发了两个版本的Faster R-CNN模型——小型和大型。首先，通过整合倒立残差块、深度可分卷积和注意机制对模型进行结构优化，以提高效率和性能。大型版本还集成了多尺度特征提取，以增强检测能力。其次，采用模型剪枝进一步压缩网络；通过广泛的烧蚀实验来研究模型内部结构及其对裂纹检测精度和效率的影响。实验结果表明，该模型在桥梁表面缺陷检测方面优于一般基于cnn的模型，在保持较高精度的同时，检测速度更快。大版本表现出更好的性能，但代价是增加了模型的复杂性。测试是在中国南京一座真实的桥梁上进行的。此外，还部署了一个集成了笔记本电脑和智能手机的软件应用程序来识别缺陷，并绘制出它们在桥上的位置，简化了检测过程。该软件的源代码可在https://github.com/DUYA686686/detection-software.git免费获得

{"title":"A lightweight convolutional neural network-based model and system for defect detection and navigation on bridge road surface","authors":"Ronghua Fu , Yufeng Zhang , Drahomír Novák , Alfred Strauss , Maosen Cao","doi":"10.1016/j.advengsoft.2025.103972","DOIUrl":"10.1016/j.advengsoft.2025.103972","url":null,"abstract":"<div><div>The Faster Region-based Convolutional Neural Network (Faster R-CNN) is widely used for detecting defects on road surface. However, its effectiveness in this task is limited by its large model size and slow detection speed. To address these challenges, two versions of the Faster R-CNN model—small and large—were developed. First, the models were structurally optimized by integrating inverted residual blocks, depthwise separable convolutions, and attention mechanisms to improve efficiency and performance. The large version also incorporated multi-scale feature extraction for enhanced detection capabilities. Second, model pruning was applied to further compress the networks. Extensive ablation experiments were conducted to investigate the relationship between the model's internal structure and its impact on crack detection accuracy and efficiency. The experimental results demonstrate that the proposed models outperform general CNN-based models in bridge surface defect detection, achieving superior detection speed while maintaining high accuracy. The large version exhibits better performance but at the cost of increased model complexity. Testing was conducted on a real-life bridge in Nanjing, China. Additionally, a software application, integrated with a laptop and a smartphone, was deployed to identify defects and map their locations on the bridge, streamlining the detection process. The source code of this software is freely available at <span><span>https://github.com/DUYA686686/detection-software.git</span><svg><path></path></svg></span></div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"208 ","pages":"Article 103972"},"PeriodicalIF":4.0,"publicationDate":"2025-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144229744","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

An isogeometric approach to supersonic flutter analysis of lightweight-designed plates with graphene reinforcement 石墨烯配筋轻量化板的超音速颤振分析等几何方法

IF 4 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Advances in Engineering Software

Pub Date : 2025-06-06 DOI: 10.1016/j.advengsoft.2025.103955

Nam V. Nguyen, Thoai N. Tran

In recent years, there has been an increasing emphasis on implementing high-performance, lightweight designs in a wide range of contemporary interdisciplinary applications. The primary objective of this paper, therefore, is to present a NURBS-based isogeometric approach for a comprehensive investigation into the supersonic flutter characteristics of graphene-reinforced functionally graded (FG) metal foam plates. The lightweight structures are designed using a combination of two porosity distributions and two graphene dispersion patterns, featuring both uniform and non-uniform configurations. The mathematical equations governing the dynamic behavior of the porous plates are derived using a computational approach based on generalized higher-order shear deformation theory (HSDT) within a NURBS-based isogeometric analysis (IGA). A first-order approximation of piston theory is employed to model the fluid–structure interaction by estimating the aerodynamic forces induced by high-speed airflow. The accuracy of the current approach is assessed and validated against the analytical approach and other existing benchmark results. Several extensive parametric investigations are subsequently conducted to fulfill the primary goal of this research: to clarify the influence of internal porosity and graphene nanofiller on the flutter boundaries and associated vibrational modes of lightweight-designed plate structures. The obtained results demonstrate that graphene-reinforced FG cellular plates possess exceptional properties, such as high stiffness and reduced weight, making them well-suited for advanced technological applications. Furthermore, the present findings offer valuable insights that can assist in the design and fabrication, with the goal of improving the robustness and efficacy of future practical engineering structures.

近年来，人们越来越重视在广泛的当代跨学科应用中实现高性能、轻量化设计。因此，本文的主要目标是提出一种基于nurbs的等几何方法来全面研究石墨烯增强功能梯度（FG）金属泡沫板的超音速颤振特性。轻质结构的设计结合了两种孔隙率分布和两种石墨烯分散模式，具有均匀和非均匀的配置。在基于nurbs的等高几何分析（IGA）中，使用基于广义高阶剪切变形理论（HSDT）的计算方法推导了控制多孔板动态行为的数学方程。采用一阶近似活塞理论，通过估计高速气流引起的气动力来模拟流固耦合。根据分析方法和其他现有基准结果评估和验证当前方法的准确性。随后进行了几项广泛的参数研究，以实现本研究的主要目标：阐明内部孔隙率和石墨烯纳米填料对轻量化板结构颤振边界和相关振动模式的影响。结果表明，石墨烯增强FG细胞板具有优异的性能，如高刚度和减轻重量，使其非常适合于先进的技术应用。此外，目前的研究结果提供了有价值的见解，可以帮助设计和制造，以提高未来实际工程结构的稳健性和有效性。

{"title":"An isogeometric approach to supersonic flutter analysis of lightweight-designed plates with graphene reinforcement","authors":"Nam V. Nguyen, Thoai N. Tran","doi":"10.1016/j.advengsoft.2025.103955","DOIUrl":"10.1016/j.advengsoft.2025.103955","url":null,"abstract":"<div><div>In recent years, there has been an increasing emphasis on implementing high-performance, lightweight designs in a wide range of contemporary interdisciplinary applications. The primary objective of this paper, therefore, is to present a NURBS-based isogeometric approach for a comprehensive investigation into the supersonic flutter characteristics of graphene-reinforced functionally graded (FG) metal foam plates. The lightweight structures are designed using a combination of two porosity distributions and two graphene dispersion patterns, featuring both uniform and non-uniform configurations. The mathematical equations governing the dynamic behavior of the porous plates are derived using a computational approach based on generalized higher-order shear deformation theory (HSDT) within a NURBS-based isogeometric analysis (IGA). A first-order approximation of piston theory is employed to model the fluid–structure interaction by estimating the aerodynamic forces induced by high-speed airflow. The accuracy of the current approach is assessed and validated against the analytical approach and other existing benchmark results. Several extensive parametric investigations are subsequently conducted to fulfill the primary goal of this research: to clarify the influence of internal porosity and graphene nanofiller on the flutter boundaries and associated vibrational modes of lightweight-designed plate structures. The obtained results demonstrate that graphene-reinforced FG cellular plates possess exceptional properties, such as high stiffness and reduced weight, making them well-suited for advanced technological applications. Furthermore, the present findings offer valuable insights that can assist in the design and fabrication, with the goal of improving the robustness and efficacy of future practical engineering structures.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"208 ","pages":"Article 103955"},"PeriodicalIF":4.0,"publicationDate":"2025-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144221978","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

Machine learning-based two-stage damage prediction method for RC slabs under blast loads 基于机器学习的两阶段爆炸荷载下RC板损伤预测方法

IF 4 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Advances in Engineering Software

Pub Date : 2025-06-04 DOI: 10.1016/j.advengsoft.2025.103959

Chunfeng Zhao , Jian Su , Yufu Zhu , Xiaojie Li

Reinforced concrete (RC) slabs are extremely vulnerable to damage in explosions and terrorist attacks as the force members of building structures. It is necessary to evaluate and predict the damage of the RC slabs to improve the explosion protection of building structures. In this study, a two-stage damage prediction method for RC slabs under blast loads is developed using machine learning method. In the first stage, the parameters related to the RC slab and the explosion are used as input feature variables, and a machine learning algorithm is adopted to establish a displacement prediction model for the RC slab under explosion loading. In the second stage, the prediction of the maximum displacement of the RC slab under blast loads is carried out using the proposed model, and the damage of the RC slab is evaluated following the damage assessment criteria. Finally, the accuracy and reliability of the two-stage prediction method is validated by the present empirical methods. The results show that the two-stage prediction method under the damage assessment criterion of the support rotation has the best damage identification results with an accuracy of 93.1 %. Furthermore, the two-stage prediction method has better generalization performance with an accuracy of 90 % compared with the present empirical prediction methods.

钢筋混凝土板作为建筑物结构的受力构件，在爆炸和恐怖袭击中极易受到破坏。为了提高建筑结构的防爆性能，对钢筋混凝土板的损伤进行评估和预测是十分必要的。本文采用机器学习方法，提出了一种两阶段爆炸荷载作用下RC板损伤预测方法。第一阶段将RC板与爆炸相关参数作为输入特征变量，采用机器学习算法建立爆炸荷载作用下RC板位移预测模型。第二阶段，利用本文提出的模型预测爆炸荷载作用下RC板的最大位移，并根据损伤评估准则对RC板进行损伤评估。最后，通过本文的经验方法验证了两阶段预测方法的准确性和可靠性。结果表明，基于支架旋转损伤评估准则的两阶段预测方法损伤识别效果最好，准确率为93.1%。此外，与现有的经验预测方法相比，两阶段预测方法具有更好的泛化性能，准确率达到90%。

{"title":"Machine learning-based two-stage damage prediction method for RC slabs under blast loads","authors":"Chunfeng Zhao , Jian Su , Yufu Zhu , Xiaojie Li","doi":"10.1016/j.advengsoft.2025.103959","DOIUrl":"10.1016/j.advengsoft.2025.103959","url":null,"abstract":"<div><div>Reinforced concrete (RC) slabs are extremely vulnerable to damage in explosions and terrorist attacks as the force members of building structures. It is necessary to evaluate and predict the damage of the RC slabs to improve the explosion protection of building structures. In this study, a two-stage damage prediction method for RC slabs under blast loads is developed using machine learning method. In the first stage, the parameters related to the RC slab and the explosion are used as input feature variables, and a machine learning algorithm is adopted to establish a displacement prediction model for the RC slab under explosion loading. In the second stage, the prediction of the maximum displacement of the RC slab under blast loads is carried out using the proposed model, and the damage of the RC slab is evaluated following the damage assessment criteria. Finally, the accuracy and reliability of the two-stage prediction method is validated by the present empirical methods. The results show that the two-stage prediction method under the damage assessment criterion of the support rotation has the best damage identification results with an accuracy of 93.1 %. Furthermore, the two-stage prediction method has better generalization performance with an accuracy of 90 % compared with the present empirical prediction methods.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"208 ","pages":"Article 103959"},"PeriodicalIF":4.0,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144203553","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

Hybrid material topology optimization of solid-lattice structures for natural frequency maximization 基于固有频率最大化的混合材料固体晶格结构拓扑优化

IF 4 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Advances in Engineering Software

Pub Date : 2025-06-02 DOI: 10.1016/j.advengsoft.2025.103961

Yuhan Liu, Zhen Liu, Yedan Li, Wei-Zhi Luo, Liang Xia

This paper presents a topology optimization design approach for hybrid materials used to generate solid-lattice structures. Specifically, the approach aims to maximize the natural frequencies of hybrid structures by optimizing the topological distribution of solid and lattice materials, as well as the lattice relative density. For this purpose, a hybrid material interpolation model is developed. In this approach, the modal assurance criterion (MAC) is applied to optimize the target-order natural frequency accurately. Additionally, a hybrid structure post-processing framework based on the signed distance field (SDF) is proposed. This framework adaptively refines the lattice resolution at model boundaries, ensuring geometric integrity. Moreover, a circular geometry transition strategy is employed to improve structural connectivity, which significantly reduces model errors in non-transition regions. 2D and 3D numerical examples demonstrate the proposed method’s effectiveness in maximizing the natural frequency of hybrid structures. In particular, the dynamic performance of hybrid structures surpasses that of pure solid structures under multiple mass loading cases.

本文提出了一种用于生成固体晶格结构的杂化材料的拓扑优化设计方法。具体来说，该方法旨在通过优化固体和晶格材料的拓扑分布以及晶格相对密度来最大化混合结构的固有频率。为此，建立了一种混合材料插值模型。该方法采用模态保证准则（MAC）对目标阶固有频率进行精确优化。此外，提出了一种基于符号距离域（SDF）的混合结构后处理框架。该框架自适应细化模型边界的格分辨率，保证几何完整性。此外，采用圆形几何过渡策略提高了结构连通性，显著降低了非过渡区域的模型误差。二维和三维数值算例验证了该方法在最大化混合结构固有频率方面的有效性。特别是混合动力结构在多重质量荷载作用下的动力性能优于纯实体结构。

{"title":"Hybrid material topology optimization of solid-lattice structures for natural frequency maximization","authors":"Yuhan Liu, Zhen Liu, Yedan Li, Wei-Zhi Luo, Liang Xia","doi":"10.1016/j.advengsoft.2025.103961","DOIUrl":"10.1016/j.advengsoft.2025.103961","url":null,"abstract":"<div><div>This paper presents a topology optimization design approach for hybrid materials used to generate solid-lattice structures. Specifically, the approach aims to maximize the natural frequencies of hybrid structures by optimizing the topological distribution of solid and lattice materials, as well as the lattice relative density. For this purpose, a hybrid material interpolation model is developed. In this approach, the modal assurance criterion (MAC) is applied to optimize the target-order natural frequency accurately. Additionally, a hybrid structure post-processing framework based on the signed distance field (SDF) is proposed. This framework adaptively refines the lattice resolution at model boundaries, ensuring geometric integrity. Moreover, a circular geometry transition strategy is employed to improve structural connectivity, which significantly reduces model errors in non-transition regions. 2D and 3D numerical examples demonstrate the proposed method’s effectiveness in maximizing the natural frequency of hybrid structures. In particular, the dynamic performance of hybrid structures surpasses that of pure solid structures under multiple mass loading cases.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"208 ","pages":"Article 103961"},"PeriodicalIF":4.0,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144190150","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

An improved newton metaheuristic algorithm for design optimization of steel moment-resisting frames 钢质抗弯矩框架设计优化的改进牛顿元启发式算法

IF 4 2区工程技术 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Advances in Engineering Software

Pub Date : 2025-05-28 DOI: 10.1016/j.advengsoft.2025.103960

Ataollah Zaerreza, Saeed Gholizadeh, Mirali Mohammadi

This paper proposes an improved Newton metaheuristic algorithm (INMA) for solving steel moment resisting frame optimization problems. The proposed INMA uses a novel initialization scheme that produces an efficient initial population that is significantly better than a randomly generated initial population for structural optimization problems. The efficiency of the algorithm is further improved by the implementation of a statistical regeneration mechanism. The effectiveness of the INMA is initially demonstrated through two benchmark optimization problems involving steel moment-resisting frames. Furthermore, the performance of the INMA is evaluated to address the performance-based design optimization problem of steel moment-resisting frames. Due to the potentially extensive computational time of the performance-based design optimization process, a nonlinear static pushover analysis is performed to determine structural responses at various seismic performance levels. The numerical results indicate that the INMA outperforms other algorithms in the literature.

本文提出了一种改进的牛顿元启发式算法（INMA），用于求解钢抗弯矩框架优化问题。对于结构优化问题，所提出的INMA采用了一种新的初始化方案，该方案产生的初始种群比随机生成的初始种群明显更好。通过统计再生机制的实现，进一步提高了算法的效率。通过两个涉及钢抗弯矩框架的基准优化问题，初步证明了该方法的有效性。此外，还对INMA的性能进行了评价，以解决钢抗弯矩框架的基于性能的设计优化问题。由于基于性能的设计优化过程的计算时间可能很长，因此进行非线性静态推覆分析以确定不同抗震性能水平下的结构响应。数值结果表明，该算法优于文献中的其他算法。

{"title":"An improved newton metaheuristic algorithm for design optimization of steel moment-resisting frames","authors":"Ataollah Zaerreza, Saeed Gholizadeh, Mirali Mohammadi","doi":"10.1016/j.advengsoft.2025.103960","DOIUrl":"10.1016/j.advengsoft.2025.103960","url":null,"abstract":"<div><div>This paper proposes an improved Newton metaheuristic algorithm (INMA) for solving steel moment resisting frame optimization problems. The proposed INMA uses a novel initialization scheme that produces an efficient initial population that is significantly better than a randomly generated initial population for structural optimization problems. The efficiency of the algorithm is further improved by the implementation of a statistical regeneration mechanism. The effectiveness of the INMA is initially demonstrated through two benchmark optimization problems involving steel moment-resisting frames. Furthermore, the performance of the INMA is evaluated to address the performance-based design optimization problem of steel moment-resisting frames. Due to the potentially extensive computational time of the performance-based design optimization process, a nonlinear static pushover analysis is performed to determine structural responses at various seismic performance levels. The numerical results indicate that the INMA outperforms other algorithms in the literature.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"207 ","pages":"Article 103960"},"PeriodicalIF":4.0,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144147885","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