Pub Date : 2024-10-10DOI: 10.1016/j.advengsoft.2024.103787
Rongbo Zhou , Shuli Sun , Shiyu Fu
Mesh smoothing is a critical technique for enhancing mesh quality. Recently, polyhedral meshes have gained prominence in Computational Fluid Dynamics (CFD), with orthogonality being a common metric for evaluating these meshes. This paper introduces an innovative geometric method for smoothing and untangling polyhedral meshes, leveraging element shape transformation to improve orthogonality. The proposed method involves two primary operations. The first operation enhances individual element quality through geometric shape transformation achieved by node movement. This movement direction is determined by a combination of the node's normal vector and a correction vector. Following this transformation, temporary nodes of each element are established, and the node positions are updated using a weighted average of their corresponding temporary node set, a process referred to as element stitching. These operations can be iteratively applied to progressively enhance overall polyhedral mesh quality. The effectiveness and stability of this method are demonstrated through various examples, showing not only an improvement in mesh quality but also the elimination of inverted elements. CFD simulation results further indicate that the enhanced mesh quality positively impacts simulation accuracy.
{"title":"Smoothing and untangling for polyhedral mesh based on element shape transformation","authors":"Rongbo Zhou , Shuli Sun , Shiyu Fu","doi":"10.1016/j.advengsoft.2024.103787","DOIUrl":"10.1016/j.advengsoft.2024.103787","url":null,"abstract":"<div><div>Mesh smoothing is a critical technique for enhancing mesh quality. Recently, polyhedral meshes have gained prominence in Computational Fluid Dynamics (CFD), with orthogonality being a common metric for evaluating these meshes. This paper introduces an innovative geometric method for smoothing and untangling polyhedral meshes, leveraging element shape transformation to improve orthogonality. The proposed method involves two primary operations. The first operation enhances individual element quality through geometric shape transformation achieved by node movement. This movement direction is determined by a combination of the node's normal vector and a correction vector. Following this transformation, temporary nodes of each element are established, and the node positions are updated using a weighted average of their corresponding temporary node set, a process referred to as element stitching. These operations can be iteratively applied to progressively enhance overall polyhedral mesh quality. The effectiveness and stability of this method are demonstrated through various examples, showing not only an improvement in mesh quality but also the elimination of inverted elements. CFD simulation results further indicate that the enhanced mesh quality positively impacts simulation accuracy.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"198 ","pages":"Article 103787"},"PeriodicalIF":4.0,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142426493","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}
Pub Date : 2024-10-10DOI: 10.1016/j.advengsoft.2024.103791
Bu-Seog Ju , Hoyoung Son , Shinyoung Kwag , Sangwoo Lee
With the introduction of probabilistic safety assessment in nuclear power plants, a fragility analysis is critical to evaluating the probability of a failure of structures. However, such fragility analysis requires a large amount of finite element analyses due to explicit consideration and quantification of all sources of uncertainty. This study aims to present a sequential machining learning-based framework that can sequentially and efficiently estimate the fragility of containment vessels in nuclear power plants while minimizing finite element analyses, and the proposed framework is applied for performing a fragility analysis of a prestressed concrete containment vessel subjected to internal pressure. Within the framework, machine learning models are used to predict the behavior of the containment vessel based on collected analytical data from finite element analyses. The predicted data are used to estimate fragility curves through maximum likelihood estimation within the proposed framework, and the number of analytical data for training machine learning models is sequentially increased until the required convergence index of the estimated fragility curve is reached. In addition, the final fragility curves obtained from the proposed framework are compared with the fragility curves (benchmark) obtained from 1000 analytical data. This proposed framework can significantly reduce computational costs by estimating the fragility curve with the minimum number of finite element analyses.
{"title":"Sequential machine learning based fragility analysis: Sequential ML-FA for reactor containment vessel subjected to internal pressure","authors":"Bu-Seog Ju , Hoyoung Son , Shinyoung Kwag , Sangwoo Lee","doi":"10.1016/j.advengsoft.2024.103791","DOIUrl":"10.1016/j.advengsoft.2024.103791","url":null,"abstract":"<div><div>With the introduction of probabilistic safety assessment in nuclear power plants, a fragility analysis is critical to evaluating the probability of a failure of structures. However, such fragility analysis requires a large amount of finite element analyses due to explicit consideration and quantification of all sources of uncertainty. This study aims to present a sequential machining learning-based framework that can sequentially and efficiently estimate the fragility of containment vessels in nuclear power plants while minimizing finite element analyses, and the proposed framework is applied for performing a fragility analysis of a prestressed concrete containment vessel subjected to internal pressure. Within the framework, machine learning models are used to predict the behavior of the containment vessel based on collected analytical data from finite element analyses. The predicted data are used to estimate fragility curves through maximum likelihood estimation within the proposed framework, and the number of analytical data for training machine learning models is sequentially increased until the required convergence index of the estimated fragility curve is reached. In addition, the final fragility curves obtained from the proposed framework are compared with the fragility curves (benchmark) obtained from 1000 analytical data. This proposed framework can significantly reduce computational costs by estimating the fragility curve with the minimum number of finite element analyses.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"198 ","pages":"Article 103791"},"PeriodicalIF":4.0,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142426492","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}
Pub Date : 2024-10-09DOI: 10.1016/j.advengsoft.2024.103790
Osezua Ibhadode , Yun-Fei Fu , Ahmed Qureshi
Topology optimization has revolutionized the design of structures for various applications, particularly with the advancement of additive manufacturing. However, existing open-source codes for topology optimization have limitations, such as restricted domain initialization and lack of a CAD output after optimization. A novel open-source Matlab code, FreeTO, is presented, and it addresses these limitations by enabling the initialization of 3D arbitrary geometries and providing an STL file post-optimization. FreeTO utilizes a structured mesh and a smooth-edge (boundary) algorithm to generate smooth topological boundaries. The code is demonstrated through six practical design cases, showcasing its effectiveness in compliance minimization, compliant mechanisms, and self-supporting problems. FreeTO offers a user-friendly, all-in-one topology optimization package, making it an invaluable tool for educators, researchers, and practitioners. Future developments will focus on eliminating a few geometrical deviations in the optimized topologies, incorporating speedups, and extending the code to apply to more applications.
{"title":"FreeTO - Freeform 3D topology optimization using a structured mesh with smooth boundaries in Matlab","authors":"Osezua Ibhadode , Yun-Fei Fu , Ahmed Qureshi","doi":"10.1016/j.advengsoft.2024.103790","DOIUrl":"10.1016/j.advengsoft.2024.103790","url":null,"abstract":"<div><div>Topology optimization has revolutionized the design of structures for various applications, particularly with the advancement of additive manufacturing. However, existing open-source codes for topology optimization have limitations, such as restricted domain initialization and lack of a CAD output after optimization. A novel open-source Matlab code, FreeTO, is presented, and it addresses these limitations by enabling the initialization of 3D arbitrary geometries and providing an STL file post-optimization. FreeTO utilizes a structured mesh and a smooth-edge (boundary) algorithm to generate smooth topological boundaries. The code is demonstrated through six practical design cases, showcasing its effectiveness in compliance minimization, compliant mechanisms, and self-supporting problems. FreeTO offers a user-friendly, all-in-one topology optimization package, making it an invaluable tool for educators, researchers, and practitioners. Future developments will focus on eliminating a few geometrical deviations in the optimized topologies, incorporating speedups, and extending the code to apply to more applications.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"198 ","pages":"Article 103790"},"PeriodicalIF":4.0,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142426491","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-08DOI: 10.1016/j.advengsoft.2024.103789
Shiran Zhu , Ruiwen Guo , Xin Jin , Xiaofei Ma , Jinxiong Zhou , Ning An
Deployable rib-mesh reflector antennas, known for their ultralight nature and high deployment-to-stowage ratio, have been attracting attention from both the aerospace industry and academia. Form finding is a critical step in determining the equilibrium shape of the reflector under a specific internal stress distribution, which is a prerequisite in evaluating the surface accuracy of these antennas. This paper presents a comprehensive methodology for iteratively implementing the nonlinear finite element method for form finding of cable-membrane structures supported by flexible frames. The method is integrated into the commercial finite element code ABAQUS with Python scripts, and its accuracy and efficiency are validated through a few benchmark examples. Subsequently, the proposed method is applied to analyze the surface accuracy of umbrella-like rib-mesh reflector antennas. The effect of key design parameters such as the number and rigidity of ribs, the magnitude and anisotropy of membrane stress, and the amount of pretension force in boundary cables on the antenna’s surface accuracy has been highlighted. The effort not only establishes a robust and user-friendly strategy for form finding of cable-membrane structures supported by flexible frames but also provides valuable insights into the surface accuracy of umbrella-like rib-mesh reflector antennas. To facilitate the application of the FEM-based form-finding method, the source code for this paper is publicly available via a permanent link on GitHub https://github.com/SCU-An-Group/FEM-based-Form-Finding.
{"title":"Form finding of cable-membrane structures with flexible frames: Finite element implementation and application to surface accuracy analysis of umbrella-like rib-mesh reflectors","authors":"Shiran Zhu , Ruiwen Guo , Xin Jin , Xiaofei Ma , Jinxiong Zhou , Ning An","doi":"10.1016/j.advengsoft.2024.103789","DOIUrl":"10.1016/j.advengsoft.2024.103789","url":null,"abstract":"<div><div>Deployable rib-mesh reflector antennas, known for their ultralight nature and high deployment-to-stowage ratio, have been attracting attention from both the aerospace industry and academia. Form finding is a critical step in determining the equilibrium shape of the reflector under a specific internal stress distribution, which is a prerequisite in evaluating the surface accuracy of these antennas. This paper presents a comprehensive methodology for iteratively implementing the nonlinear finite element method for form finding of cable-membrane structures supported by flexible frames. The method is integrated into the commercial finite element code ABAQUS with Python scripts, and its accuracy and efficiency are validated through a few benchmark examples. Subsequently, the proposed method is applied to analyze the surface accuracy of umbrella-like rib-mesh reflector antennas. The effect of key design parameters such as the number and rigidity of ribs, the magnitude and anisotropy of membrane stress, and the amount of pretension force in boundary cables on the antenna’s surface accuracy has been highlighted. The effort not only establishes a robust and user-friendly strategy for form finding of cable-membrane structures supported by flexible frames but also provides valuable insights into the surface accuracy of umbrella-like rib-mesh reflector antennas. To facilitate the application of the FEM-based form-finding method, the source code for this paper is publicly available via a permanent link on GitHub <span><span>https://github.com/SCU-An-Group/FEM-based-Form-Finding</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"198 ","pages":"Article 103789"},"PeriodicalIF":4.0,"publicationDate":"2024-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142426490","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}
Pub Date : 2024-10-05DOI: 10.1016/j.advengsoft.2024.103788
Yeqi Liu , Deping Yu , Wu Zhao , Kai Zhang
Detecting weld defects in battery trays is crucial for the safety of new energy vehicles. Existing methods for weld surface defect detection, relying on traditional computer vision algorithms and convolutional neural networks with substantial image-level labeled data, face challenges in accurately identifying small defects, especially with limited samples. To address these issues, we developed an innovative Segmentation-Assisted Classification with Convolutional Neural Networks (SACNN) model. SACNN integrates a common feature extraction subnet, a segmentation subnet enhanced by a multi-scale feature fusion module, and a classification subnet specifically designed for precise defect detection. A joint loss function co-trains the segmentation and classification subnets using both image-level and pixel-level labels, enhancing the model’s ability to accurately detect small defect regions. Our model demonstrates notable improvement, achieving accuracy gains ranging from 2% to 18% compared to existing state-of-the-art methods, with an overall accuracy of 94.09% on an industrial dataset of battery tray welds. To further evaluate the generalization capability of our model, we evaluated it on the publicly available Magnetic Tile dataset, achieving state-of-the-art results in this challenging context. Additionally, we conducted comprehensive ablation studies to validate the contribution of each component in our approach and utilized visualization techniques to enhance the interpretability of our model. These advancements represent a significant contribution to the state of the art in aluminum alloy weld defect detection.
{"title":"Segmentation-assisted classification model with convolutional neural network for weld defect detection","authors":"Yeqi Liu , Deping Yu , Wu Zhao , Kai Zhang","doi":"10.1016/j.advengsoft.2024.103788","DOIUrl":"10.1016/j.advengsoft.2024.103788","url":null,"abstract":"<div><div>Detecting weld defects in battery trays is crucial for the safety of new energy vehicles. Existing methods for weld surface defect detection, relying on traditional computer vision algorithms and convolutional neural networks with substantial image-level labeled data, face challenges in accurately identifying small defects, especially with limited samples. To address these issues, we developed an innovative Segmentation-Assisted Classification with Convolutional Neural Networks (SACNN) model. SACNN integrates a common feature extraction subnet, a segmentation subnet enhanced by a multi-scale feature fusion module, and a classification subnet specifically designed for precise defect detection. A joint loss function co-trains the segmentation and classification subnets using both image-level and pixel-level labels, enhancing the model’s ability to accurately detect small defect regions. Our model demonstrates notable improvement, achieving accuracy gains ranging from 2% to 18% compared to existing state-of-the-art methods, with an overall accuracy of 94.09% on an industrial dataset of battery tray welds. To further evaluate the generalization capability of our model, we evaluated it on the publicly available Magnetic Tile dataset, achieving state-of-the-art results in this challenging context. Additionally, we conducted comprehensive ablation studies to validate the contribution of each component in our approach and utilized visualization techniques to enhance the interpretability of our model. These advancements represent a significant contribution to the state of the art in aluminum alloy weld defect detection.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"198 ","pages":"Article 103788"},"PeriodicalIF":4.0,"publicationDate":"2024-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142426489","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}
Pub Date : 2024-10-03DOI: 10.1016/j.advengsoft.2024.103785
Tiendung Vu , Son H. Nguyen
This paper investigates the performance of a recently proposed polygonal plate element with alpha (α)-assumed rotations and shear strains, referred to as αARS-Poly, in free vibration analysis. The αARS-Poly element utilizes a simple and efficient approach involving a scaling factor (α) to enhance the accuracy of assumed rotations and shear strains. To fully explore the advantages of this element, we undertake a comprehensive analysis of free vibration in plate structures using a range of models with complex geometries. Numerical results demonstrate that the αARS-Poly element offers stability and reliability within smooth mode shapes. Furthermore, it significantly outperforms the previous polygonal Reissner-Mindlin plate element with piecewise-linear shape functions (PRMn-PL), achieving frequencies that closely match reference solutions, thereby validating its accuracy and robustness for dynamic applications.
{"title":"Polygonal plate element method for free vibration analysis using an efficient alpha (α)-assumed rotations and shear strains","authors":"Tiendung Vu , Son H. Nguyen","doi":"10.1016/j.advengsoft.2024.103785","DOIUrl":"10.1016/j.advengsoft.2024.103785","url":null,"abstract":"<div><div>This paper investigates the performance of a recently proposed polygonal plate element with alpha (<em>α</em>)-assumed rotations and shear strains, referred to as <em>α</em>ARS-Poly, in free vibration analysis. The <em>α</em>ARS-Poly element utilizes a simple and efficient approach involving a scaling factor (<em>α</em>) to enhance the accuracy of assumed rotations and shear strains. To fully explore the advantages of this element, we undertake a comprehensive analysis of free vibration in plate structures using a range of models with complex geometries. Numerical results demonstrate that the <em>α</em>ARS-Poly element offers stability and reliability within smooth mode shapes. Furthermore, it significantly outperforms the previous polygonal Reissner-Mindlin plate element with piecewise-linear shape functions (PRM<em>n</em>-PL), achieving frequencies that closely match reference solutions, thereby validating its accuracy and robustness for dynamic applications.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"198 ","pages":"Article 103785"},"PeriodicalIF":4.0,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142426488","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}
Pub Date : 2024-10-02DOI: 10.1016/j.advengsoft.2024.103786
Kairen Shen, Hao Wang
To develop digital twin (DT) of road infrastructure, one critical element is computation of pavement responses (strains, stresses, and deflections) under traffic and environmental loading. This study aims to develop high-efficient asphalt pavement modeling software based on semi-analytical finite element method (SAFEM) for DT application. The algorithms address important aspects in vehicle-tire-pavement interaction modeling, such as dynamic vehicular loading, three-dimensional (3-D) non-uniform tire contact stress, viscoelastic behavior of asphalt material, and interface bonding condition. The simulation accuracy is verified by comparison with full-scale test and field measurements, and the relative differences are around 5 % to 20 %. Techniques including optimized discrete Fourier transform, parallel computing, graphics processing unit (GPU) acceleration, and sparse matrices are implemented for computation efficiency. As compared to the traditional 3-D FEM, SAFEM shows significant savings in computation time and storage usage. The high efficiency and accuracy make the software full of potential to be applied for DT of roadway infrastructure.
{"title":"Development of high-efficient asphalt pavement modeling software for digital twin of road infrastructure","authors":"Kairen Shen, Hao Wang","doi":"10.1016/j.advengsoft.2024.103786","DOIUrl":"10.1016/j.advengsoft.2024.103786","url":null,"abstract":"<div><div>To develop digital twin (DT) of road infrastructure, one critical element is computation of pavement responses (strains, stresses, and deflections) under traffic and environmental loading. This study aims to develop high-efficient asphalt pavement modeling software based on semi-analytical finite element method (SAFEM) for DT application. The algorithms address important aspects in vehicle-tire-pavement interaction modeling, such as dynamic vehicular loading, three-dimensional (3-D) non-uniform tire contact stress, viscoelastic behavior of asphalt material, and interface bonding condition. The simulation accuracy is verified by comparison with full-scale test and field measurements, and the relative differences are around 5 % to 20 %. Techniques including optimized discrete Fourier transform, parallel computing, graphics processing unit (GPU) acceleration, and sparse matrices are implemented for computation efficiency. As compared to the traditional 3-D FEM, SAFEM shows significant savings in computation time and storage usage. The high efficiency and accuracy make the software full of potential to be applied for DT of roadway infrastructure.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"198 ","pages":"Article 103786"},"PeriodicalIF":4.0,"publicationDate":"2024-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142426495","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The self-developed Finite Element Limit Analysis (FELA) code was utilized to examine the ultimate bearing capacity of strip footings positioned above tunnels affected by inclined loads. Bearing capacity factors were predicted using both upper bound (UB) and lower bound (LB) solutions, with a variance of less than 3 %. The primary focus of this study lies in assessing the influences of underlying tunnels and inclined loads on potential failure modes. In particular, the concept of failure envelopes was introduced, by which the load properties (inclination angle), the tunnel location (relative lateral distance and longitudinal distance from the footing) and the material properties of rock masses (GSI, mi, sci, g) were involved in to facilitate preliminary designs. In addition to envelopes, the transition among failure patterns was summarized, resting with any possible factors.
{"title":"Effects of inclined loads on strip footings with an underlying tunnel","authors":"Gaoqiao Wu , Jiayu Zeng , Rui Zhang , Yongjie Tan , Shiping Zhang","doi":"10.1016/j.advengsoft.2024.103783","DOIUrl":"10.1016/j.advengsoft.2024.103783","url":null,"abstract":"<div><div>The self-developed Finite Element Limit Analysis (FELA) code was utilized to examine the ultimate bearing capacity of strip footings positioned above tunnels affected by inclined loads. Bearing capacity factors were predicted using both upper bound (UB) and lower bound (LB) solutions, with a variance of less than 3 %. The primary focus of this study lies in assessing the influences of underlying tunnels and inclined loads on potential failure modes. In particular, the concept of failure envelopes was introduced, by which the load properties (inclination angle), the tunnel location (relative lateral distance and longitudinal distance from the footing) and the material properties of rock masses (<em>GSI, m</em><sub>i</sub>, <em>s</em><sub>ci</sub>, <em>g</em>) were involved in to facilitate preliminary designs. In addition to envelopes, the transition among failure patterns was summarized, resting with any possible factors.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"198 ","pages":"Article 103783"},"PeriodicalIF":4.0,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142426487","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}
Pub Date : 2024-10-01DOI: 10.1016/j.advengsoft.2024.103779
Shihao Wen , Minsoo Park , Dai Quoc Tran , Seungsoo Lee , Seunghee Park
The construction sector is globally acknowledged as one of the most hazardous industries, owing to the vulnerability of its workers to accidents, injuries, and even loss of life. Effective precautionary measures are necessary and ensuring the use of personal protective equipment (PPE) by workers is crucial for protecting them from accidents. Existing deep learning-based PPE detection systems mainly use simple vision-based target detection methods for tasks such as the identification of helmets or vests, and they tend to be task-specific. However, the identification of specific PPE based on respective job types and maintaining detailed safety records, requires further innovative approaches. In this paper, we propose an innovative intelligent system that not only accurately recognizes specific PPE according to the needs of different work types but also automatically generates safety inspection reports and establishes complete safety records, thus providing critical data to support accident investigations. The proposed system integrates a target detection model, visual question answering model, and text-based analysis of the relevant regulations to realize real-time detection of PPE and automatic generation of safety inspection reports. The experimental results show that the proposed YOLOv8n-DCA network strikes a good balance between performance and computational cost—, with a mAP value of 86%. Compared to the original YOLOv8n network, the mAP value is improved by 5.1%, while the model parameters and size are significantly reduced. Further, the visual question answering model exhibited a precision is 95.9. Finally, the automatic generation of safety inspection reports was successfully realized, verifying the feasibility of the developed system. This innovative system promises a comprehensive and efficient PPE management solution for the construction industry to ensure worker safety and provide strong data support.
{"title":"Automated construction safety reporting system integrating deep learning-based real-time advanced detection and visual question answering","authors":"Shihao Wen , Minsoo Park , Dai Quoc Tran , Seungsoo Lee , Seunghee Park","doi":"10.1016/j.advengsoft.2024.103779","DOIUrl":"10.1016/j.advengsoft.2024.103779","url":null,"abstract":"<div><div>The construction sector is globally acknowledged as one of the most hazardous industries, owing to the vulnerability of its workers to accidents, injuries, and even loss of life. Effective precautionary measures are necessary and ensuring the use of personal protective equipment (PPE) by workers is crucial for protecting them from accidents. Existing deep learning-based PPE detection systems mainly use simple vision-based target detection methods for tasks such as the identification of helmets or vests, and they tend to be task-specific. However, the identification of specific PPE based on respective job types and maintaining detailed safety records, requires further innovative approaches. In this paper, we propose an innovative intelligent system that not only accurately recognizes specific PPE according to the needs of different work types but also automatically generates safety inspection reports and establishes complete safety records, thus providing critical data to support accident investigations. The proposed system integrates a target detection model, visual question answering model, and text-based analysis of the relevant regulations to realize real-time detection of PPE and automatic generation of safety inspection reports. The experimental results show that the proposed YOLOv8n-DCA network strikes a good balance between performance and computational cost—, with a mAP value of 86%. Compared to the original YOLOv8n network, the mAP value is improved by 5.1%, while the model parameters and size are significantly reduced. Further, the visual question answering model exhibited a precision is 95.9. Finally, the automatic generation of safety inspection reports was successfully realized, verifying the feasibility of the developed system. This innovative system promises a comprehensive and efficient PPE management solution for the construction industry to ensure worker safety and provide strong data support.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"198 ","pages":"Article 103779"},"PeriodicalIF":4.0,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142426496","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}
In industrial numerical simulations, efficiently generating high-quality tetrahedral meshes remains a significant challenge. Advances in high-performance computing have made parallelization a practical approach to improving the quality of large-scale tetrahedral meshes. This study proposes a fine-grained multithreaded parallel method to accelerate tetrahedral mesh improvement. By utilizing atomic operations, we fundamentally address thread safety concerns. Additionally, through the precise use of atomic operations, task decomposition strategies, and a multithreaded memory model, we minimize the probability of task overlap and data races, thereby enhancing overall parallel mesh improvement efficiency. Experimental results demonstrate that our parallel mesh improver is robust and effective for complex industrial models. On a laptop with 16 threads, we achieved a tenfold increase in tetrahedral mesh improvement speed, with the quality of the improved meshes being comparable to that of the sequential process.
{"title":"Multi-threaded parallel tetrahedral mesh improvement by combining atomic operation and graph coloring","authors":"Yifu Wang, Junji Wang, BoHan Wang, Yifei Wang, Jianjun Chen","doi":"10.1016/j.advengsoft.2024.103782","DOIUrl":"10.1016/j.advengsoft.2024.103782","url":null,"abstract":"<div><div>In industrial numerical simulations, efficiently generating high-quality tetrahedral meshes remains a significant challenge. Advances in high-performance computing have made parallelization a practical approach to improving the quality of large-scale tetrahedral meshes. This study proposes a fine-grained multithreaded parallel method to accelerate tetrahedral mesh improvement. By utilizing atomic operations, we fundamentally address thread safety concerns. Additionally, through the precise use of atomic operations, task decomposition strategies, and a multithreaded memory model, we minimize the probability of task overlap and data races, thereby enhancing overall parallel mesh improvement efficiency. Experimental results demonstrate that our parallel mesh improver is robust and effective for complex industrial models. On a laptop with 16 threads, we achieved a tenfold increase in tetrahedral mesh improvement speed, with the quality of the improved meshes being comparable to that of the sequential process.</div></div>","PeriodicalId":50866,"journal":{"name":"Advances in Engineering Software","volume":"198 ","pages":"Article 103782"},"PeriodicalIF":4.0,"publicationDate":"2024-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142359146","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号