Computer-Aided Civil and Infrastructure Engineering最新文献

英文中文

Cover Image, Volume 40, Issue 8

IF 8.5 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2025-03-09 DOI: 10.1111/mice.13455

The cover image is based on the article Hidden structural information reconstruction and seismic response analysis of high-rise residential shear wall buildings with limited structural data by Chenyu Zhang et al., https://doi.org/10.1111/mice.13320.

引用次数: 0

Cover Image, Volume 40, Issue 8

IF 8.5 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2025-03-09 DOI: 10.1111/mice.13456

The cover image is based on the article An interactive cross-multi-feature fusion approach for salient object detection in crack segmentation by Jian Liu et al., https://doi.org/10.1111/mice.13437.

引用次数: 0

A flexible road network partitioning framework for traffic management via graph contrastive learning and multi-objective optimization

IF 11.775 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2025-03-08 DOI: 10.1111/mice.13454

Cheng Hu, Jinjun Tang, Yaopeng Wang, Zhitao Li, Guowen Dai

The partitioning of a heterogeneously loaded road network into homogeneous, compact subregions is a fundamental prerequisite for the implementation of network-level traffic management and control based on the network macroscopic fundamental diagram. This study proposes a flexible road network partitioning framework that leverages the powerful feature extraction capabilities of self-supervised graph neural networks and employs a multi-objective optimization approach to balance regional homogeneity and compactness. A graph contrastive learning model is proposed to extract meaningful node embeddings that incorporate topology and attribute similarity information. Based on the learned node embeddings, the partition is determined by a parameter-free hierarchical clustering method and a subregion identification algorithm. Boundary tuning is then modeled as a bi-objective optimization problem to maximize regional homogeneity and compactness. A Pareto local search algorithm is developed to approximate the Pareto front. This study further demonstrates the extension of the proposed methods to scenarios with missing data. Finally, the methods are validated on real road networks with automatic license plate recognition data.

{"title":"A flexible road network partitioning framework for traffic management via graph contrastive learning and multi-objective optimization","authors":"Cheng Hu, Jinjun Tang, Yaopeng Wang, Zhitao Li, Guowen Dai","doi":"10.1111/mice.13454","DOIUrl":"https://doi.org/10.1111/mice.13454","url":null,"abstract":"The partitioning of a heterogeneously loaded road network into homogeneous, compact subregions is a fundamental prerequisite for the implementation of network-level traffic management and control based on the network macroscopic fundamental diagram. This study proposes a flexible road network partitioning framework that leverages the powerful feature extraction capabilities of self-supervised graph neural networks and employs a multi-objective optimization approach to balance regional homogeneity and compactness. A graph contrastive learning model is proposed to extract meaningful node embeddings that incorporate topology and attribute similarity information. Based on the learned node embeddings, the partition is determined by a parameter-free hierarchical clustering method and a subregion identification algorithm. Boundary tuning is then modeled as a bi-objective optimization problem to maximize regional homogeneity and compactness. A Pareto local search algorithm is developed to approximate the Pareto front. This study further demonstrates the extension of the proposed methods to scenarios with missing data. Finally, the methods are validated on real road networks with automatic license plate recognition data.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"53 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143575376","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Sewer image super-resolution with depth priors and its lightweight network

IF 11.775 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2025-03-08 DOI: 10.1111/mice.13453

Gang Pan, Chen Wang, Zhijie Sui, Shuai Guo, Yaozhi Lv, Honglie Li, Di Sun, Zixia Xia

The quick-view (QV) technique serves as a primary method for detecting defects within sewerage systems. However, the effectiveness of QV is impeded by the limited visual range of its hardware, resulting in suboptimal image quality for distant portions of the sewer network. Image super-resolution is an effective way to improve image quality and has been applied in a variety of scenes. However, research on super-resolution for sewer images remains considerably unexplored. In response, this study leverages the inherent depth relationships present within QV images and introduces a novel Depth-guided, Reference-based Super-Resolution framework denoted as DSRNet. It comprises two core components: a depth extraction module and a depth information matching module (DMM). DSRNet utilizes the adjacent frames of the low-resolution image as reference images and helps them recover texture information based on the correlation. By combining these modules, the integration of depth priors significantly enhances both visual quality and performance benchmarks. Besides, in pursuit of computational efficiency and compactness, a super-resolution knowledge distillation model based on an attention mechanism is introduced. This mechanism facilitates the acquisition of feature similarity between a more complex teacher model and a streamlined student model, with the latter being a lightweight version of DSRNet. Experimental results demonstrate that DSRNet significantly improves peak signal-to-noise ratio (PSNR) and and Structural Similarity index (SSIM) compared with other methods. This study also conducts experiments on sewer defect semantic segmentation, object detection, and classification on the Pipe data set and Sewer-ML data set. Experiments show that the method can improve the performance of low-resolution sewer images in these tasks.

{"title":"Sewer image super-resolution with depth priors and its lightweight network","authors":"Gang Pan, Chen Wang, Zhijie Sui, Shuai Guo, Yaozhi Lv, Honglie Li, Di Sun, Zixia Xia","doi":"10.1111/mice.13453","DOIUrl":"https://doi.org/10.1111/mice.13453","url":null,"abstract":"The quick-view (QV) technique serves as a primary method for detecting defects within sewerage systems. However, the effectiveness of QV is impeded by the limited visual range of its hardware, resulting in suboptimal image quality for distant portions of the sewer network. Image super-resolution is an effective way to improve image quality and has been applied in a variety of scenes. However, research on super-resolution for sewer images remains considerably unexplored. In response, this study leverages the inherent depth relationships present within QV images and introduces a novel Depth-guided, Reference-based Super-Resolution framework denoted as DSRNet. It comprises two core components: a depth extraction module and a depth information matching module (DMM). DSRNet utilizes the adjacent frames of the low-resolution image as reference images and helps them recover texture information based on the correlation. By combining these modules, the integration of depth priors significantly enhances both visual quality and performance benchmarks. Besides, in pursuit of computational efficiency and compactness, a super-resolution knowledge distillation model based on an attention mechanism is introduced. This mechanism facilitates the acquisition of feature similarity between a more complex teacher model and a streamlined student model, with the latter being a lightweight version of DSRNet. Experimental results demonstrate that DSRNet significantly improves peak signal-to-noise ratio (PSNR) and and Structural Similarity index (SSIM) compared with other methods. This study also conducts experiments on sewer defect semantic segmentation, object detection, and classification on the Pipe data set and Sewer-ML data set. Experiments show that the method can improve the performance of low-resolution sewer images in these tasks.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"48 9 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143575368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Automated indoor 3D scene reconstruction with decoupled mapping using quadruped robot and LiDAR sensor

IF 11.775 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2025-03-04 DOI: 10.1111/mice.13450

Vincent J. L. Gan, Difeng Hu, Yushuo Wang, Ruoming Zhai

Advancements in automated 3D scene reconstruction are essential for accurately capturing and documenting the current state of buildings and infrastructure. Traditional 3D reconstruction relies on laser scanning to obtain as-built conditions, but this process is often labor-intensive and time-consuming. This study introduces an optimization algorithm incorporating methods for viewpoint generation, occlusion detection and culling, and robot-moving trajectory identification. Additionally, the research investigates 3D reconstruction methods, comparing coupled and decoupled approaches to identify the most practical configuration for robotic scanning. Automation strategies for collision avoidance in human-centric environments are also explored, with adaptive control methods tested and validated for efficient point cloud data capture in indoor environments. This research advances the state-of-the-art in robotic scanning by providing a more precise and adaptive framework for 3D scene reconstruction. The results demonstrate the effectiveness of the proposed method in achieving high scan completeness and sufficient density in point cloud data, offering solutions for efficient robotic scanning.

{"title":"Automated indoor 3D scene reconstruction with decoupled mapping using quadruped robot and LiDAR sensor","authors":"Vincent J. L. Gan, Difeng Hu, Yushuo Wang, Ruoming Zhai","doi":"10.1111/mice.13450","DOIUrl":"https://doi.org/10.1111/mice.13450","url":null,"abstract":"Advancements in automated 3D scene reconstruction are essential for accurately capturing and documenting the current state of buildings and infrastructure. Traditional 3D reconstruction relies on laser scanning to obtain as-built conditions, but this process is often labor-intensive and time-consuming. This study introduces an optimization algorithm incorporating methods for viewpoint generation, occlusion detection and culling, and robot-moving trajectory identification. Additionally, the research investigates 3D reconstruction methods, comparing coupled and decoupled approaches to identify the most practical configuration for robotic scanning. Automation strategies for collision avoidance in human-centric environments are also explored, with adaptive control methods tested and validated for efficient point cloud data capture in indoor environments. This research advances the state-of-the-art in robotic scanning by providing a more precise and adaptive framework for 3D scene reconstruction. The results demonstrate the effectiveness of the proposed method in achieving high scan completeness and sufficient density in point cloud data, offering solutions for efficient robotic scanning.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"18 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143546037","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Development of a portable device for structural visual inspection

IF 8.5 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2025-03-03 DOI: 10.1111/mice.13399

Jongbin Won, Minhyuk Song, Jongwoong Park

Visual inspection is crucial for the maintenance of built infrastructures, facilitating early detection and quantification of damage. Traditional manual methods, however, often require inspectors to access dangerous or inaccessible areas, posing significant safety risks and inefficiencies. In response to these challenges, this paper introduces a portable visual inspection device (VID) integrated with three laser distance meters and a high-resolution camera. The VID enhances the efficiency of visual inspection by incorporating methods that accurately estimate the camera's pose relative to the target surface and determine a scale factor for precise damage quantification. The proposed methods were validated through experimental validations, demonstrating their precision and effectiveness. In lab-scale validation, the angle estimation showed accuracy with less than 3 degrees of error, and the scale factor estimation method showed discrepancies of less than 1 mm, even when the observation angle exceeded 20 degrees. Subsequent field experiments confirmed the VID's capability to detect and measure microcracks as narrow as 0.1 mm. Furthermore, the device successfully quantified non-crack damage with an error margin of 1.84%, even at challenging angles exceeding 45 degrees.

目视检查对于维护已建基础设施至关重要，有助于及早发现和量化损坏情况。然而，传统的人工方法往往要求检测人员进入危险或无法进入的区域，从而带来了巨大的安全风险和低效率。为了应对这些挑战，本文介绍了一种集成了三个激光测距仪和一个高分辨率摄像头的便携式视觉检测设备（VID）。VID 采用了多种方法，可准确估算摄像头相对于目标表面的姿态，并确定比例因子，从而精确量化损坏程度，从而提高了视觉检测的效率。所提出的方法通过实验验证，证明了其精确性和有效性。在实验室规模的验证中，角度估算的精度误差小于 3 度，而比例因子估算方法的误差小于 1 毫米，即使观测角度超过 20 度。随后的现场实验证实，VID 能够检测和测量窄至 0.1 毫米的微裂缝。此外，即使在观察角度超过 45 度的情况下，该设备也能成功量化非裂纹损伤，误差率仅为 1.84%。

{"title":"Development of a portable device for structural visual inspection","authors":"Jongbin Won, Minhyuk Song, Jongwoong Park","doi":"10.1111/mice.13399","DOIUrl":"10.1111/mice.13399","url":null,"abstract":"Visual inspection is crucial for the maintenance of built infrastructures, facilitating early detection and quantification of damage. Traditional manual methods, however, often require inspectors to access dangerous or inaccessible areas, posing significant safety risks and inefficiencies. In response to these challenges, this paper introduces a portable visual inspection device (VID) integrated with three laser distance meters and a high-resolution camera. The VID enhances the efficiency of visual inspection by incorporating methods that accurately estimate the camera's pose relative to the target surface and determine a scale factor for precise damage quantification. The proposed methods were validated through experimental validations, demonstrating their precision and effectiveness. In lab-scale validation, the angle estimation showed accuracy with less than 3 degrees of error, and the scale factor estimation method showed discrepancies of less than 1 mm, even when the observation angle exceeded 20 degrees. Subsequent field experiments confirmed the VID's capability to detect and measure microcracks as narrow as 0.1 mm. Furthermore, the device successfully quantified non-crack damage with an error margin of 1.84%, even at challenging angles exceeding 45 degrees.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"40 8","pages":"1061-1079"},"PeriodicalIF":8.5,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/mice.13399","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143532579","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Crack segmentation-guided measurement with lightweight distillation network on edge device

IF 11.775 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2025-03-03 DOI: 10.1111/mice.13446

Jianqi Zhang, Ling Ding, Wei Wang, Hainian Wang, Ioannis Brilakis, Diana Davletshina, Rauno Heikkilä, Xu Yang

Pavement crack measurement (PCM) is essential for automated, precise road condition assessment. However, balancing speed and accuracy on edge artificial intelligence (AI) mobile devices remains challenging. This paper proposes a real-time PCM framework for edge deployment, incorporating a lightweight distillation network and a surface feature measurement algorithm. Specifically, the proposed instance-aware hybrid distillation module combines feature-based and relation-based knowledge distillation, leveraging crack instance-related information for efficient knowledge transfer from teacher to student networks, which results in a more accurate and lightweight segmentation model. Additionally, a real-time crack surface feature measurement algorithm, based on distance mapping relationships and crack edge coordinate extraction, addresses issues with crack edge branching and loss, enhancing measurement efficiency. Real-time measurement was performed on actual roads utilizing mobile robot equipped with an edge computing unit. The crack segmentation precision reached 84.37%, with a frame per second of 77.72. Compared to the ground truth, the relative error for average crack width ranged from 6.42% to 40.65%, while the relative error for crack length varied between 1.48% and 3.76%. These findings highlight the feasibility of real-time crack assessment and save road maintenance costs.

{"title":"Crack segmentation-guided measurement with lightweight distillation network on edge device","authors":"Jianqi Zhang, Ling Ding, Wei Wang, Hainian Wang, Ioannis Brilakis, Diana Davletshina, Rauno Heikkilä, Xu Yang","doi":"10.1111/mice.13446","DOIUrl":"https://doi.org/10.1111/mice.13446","url":null,"abstract":"Pavement crack measurement (PCM) is essential for automated, precise road condition assessment. However, balancing speed and accuracy on edge artificial intelligence (AI) mobile devices remains challenging. This paper proposes a real-time PCM framework for edge deployment, incorporating a lightweight distillation network and a surface feature measurement algorithm. Specifically, the proposed instance-aware hybrid distillation module combines feature-based and relation-based knowledge distillation, leveraging crack instance-related information for efficient knowledge transfer from teacher to student networks, which results in a more accurate and lightweight segmentation model. Additionally, a real-time crack surface feature measurement algorithm, based on distance mapping relationships and crack edge coordinate extraction, addresses issues with crack edge branching and loss, enhancing measurement efficiency. Real-time measurement was performed on actual roads utilizing mobile robot equipped with an edge computing unit. The crack segmentation precision reached 84.37%, with a frame per second of 77.72. Compared to the ground truth, the relative error for average crack width ranged from 6.42% to 40.65%, while the relative error for crack length varied between 1.48% and 3.76%. These findings highlight the feasibility of real-time crack assessment and save road maintenance costs.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"46 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143539331","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Generative adversarial network based on domain adaptation for crack segmentation in shadow environments

IF 11.775 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2025-03-02 DOI: 10.1111/mice.13451

Yingchao Zhang, Cheng Liu

Precision segmentation of cracks is important in industrial non-destructive testing, but the presence of shadows in the actual environment can interfere with the segmentation results of cracks. To solve this problem, this study proposes a two-stage domain adaptation framework called GAN-DANet for crack segmentation in shadowed environments. In the first stage, CrackGAN uses adversarial learning to merge features from shadow-free and shadowed datasets, creating a new dataset with more domain-invariant features. In the second stage, the CrackSeg network innovatively integrates enhanced Laplacian filtering (ELF) into high-resolution net to enhance crack edges and texture features while filtering out shadow information. In this model, CrackGAN addresses domain shift by generating a new dataset with domain-invariant features, avoiding direct feature alignment between source and target domains. The ELF module in CrackSeg effectively enhances crack features and suppresses shadow interference, improving the segmentation model's robustness in shadowed environments. Experiments show that GAN-DANet improves the crack segmentation accuracy, with the mean intersection over union value increasing from 57.87 to 75.03, which surpasses the performance of existing state-of-the-art domain adaptation algorithms.

{"title":"Generative adversarial network based on domain adaptation for crack segmentation in shadow environments","authors":"Yingchao Zhang, Cheng Liu","doi":"10.1111/mice.13451","DOIUrl":"https://doi.org/10.1111/mice.13451","url":null,"abstract":"Precision segmentation of cracks is important in industrial non-destructive testing, but the presence of shadows in the actual environment can interfere with the segmentation results of cracks. To solve this problem, this study proposes a two-stage domain adaptation framework called GAN-DANet for crack segmentation in shadowed environments. In the first stage, CrackGAN uses adversarial learning to merge features from shadow-free and shadowed datasets, creating a new dataset with more domain-invariant features. In the second stage, the CrackSeg network innovatively integrates enhanced Laplacian filtering (ELF) into high-resolution net to enhance crack edges and texture features while filtering out shadow information. In this model, CrackGAN addresses domain shift by generating a new dataset with domain-invariant features, avoiding direct feature alignment between source and target domains. The ELF module in CrackSeg effectively enhances crack features and suppresses shadow interference, improving the segmentation model's robustness in shadowed environments. Experiments show that GAN-DANet improves the crack segmentation accuracy, with the mean intersection over union value increasing from 57.87 to 75.03, which surpasses the performance of existing state-of-the-art domain adaptation algorithms.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"2 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2025-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143532414","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cover Image, Volume 40, Issue 7

IF 8.5 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2025-03-02 DOI: 10.1111/mice.13449

The cover image is based on the article Multifidelity graph neural networks for efficient and accurate mesh-based partial differential equations surrogate modeling by Negin Alemazkoor et al., https://doi.org/10.1111/mice.13312.

引用次数: 0

Multivariate engineering formulas discovery with knowledge-based neural network

IF 11.775 1区工程技术 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computer-Aided Civil and Infrastructure Engineering

Pub Date : 2025-02-26 DOI: 10.1111/mice.13448

Pei-Yao Chen, Chen Wang, Jian-Sheng Fan

Multivariate engineering formulas are the foundation of various engineering standards worldwide for constructing complex systems. Traditional formula discovery methods suffer from low efficiency, the curse of dimensionality, and low physical interpretability. To address these limitations, this study proposes a knowledge-based method for efficiently generating multivariate engineering formulas directly from data. The method consists of four components: (1) a deep generative model considering dimensional homogeneity, (2) a physics-adaptive normalization method for multiple engineering variables with different units, (3) a feature merging algorithm grounded in dimensionality theory, and (4) a machine learning-based data segmentation method for piecewise formulas. Experiments on two ground-truth datasets demonstrate that our proposed method improves the accuracy of the generated formulas by 35.6% (measured by mean absolute error), compared to the Eureqa program. Additionally, it enhances the mechanistic interpretability of the results, compared to both Eureqa and the emerging physics-informed neural network-based equation discovery methods. The piecewise formulas successfully capture the implicit mechanisms in the experimental data, consistent with theoretical analysis. Overall, our knowledge-based method holds great promise for improving the efficiency of discovering interpretable and generalizable multivariate engineering formulas, facilitating the transformation of new techniques from testing to applications.

{"title":"Multivariate engineering formulas discovery with knowledge-based neural network","authors":"Pei-Yao Chen, Chen Wang, Jian-Sheng Fan","doi":"10.1111/mice.13448","DOIUrl":"https://doi.org/10.1111/mice.13448","url":null,"abstract":"Multivariate engineering formulas are the foundation of various engineering standards worldwide for constructing complex systems. Traditional formula discovery methods suffer from low efficiency, the curse of dimensionality, and low physical interpretability. To address these limitations, this study proposes a knowledge-based method for efficiently generating multivariate engineering formulas directly from data. The method consists of four components: (1) a deep generative model considering dimensional homogeneity, (2) a physics-adaptive normalization method for multiple engineering variables with different units, (3) a feature merging algorithm grounded in dimensionality theory, and (4) a machine learning-based data segmentation method for piecewise formulas. Experiments on two ground-truth datasets demonstrate that our proposed method improves the accuracy of the generated formulas by 35.6% (measured by mean absolute error), compared to the Eureqa program. Additionally, it enhances the mechanistic interpretability of the results, compared to both Eureqa and the emerging physics-informed neural network-based equation discovery methods. The piecewise formulas successfully capture the implicit mechanisms in the experimental data, consistent with theoretical analysis. Overall, our knowledge-based method holds great promise for improving the efficiency of discovering interpretable and generalizable multivariate engineering formulas, facilitating the transformation of new techniques from testing to applications.","PeriodicalId":156,"journal":{"name":"Computer-Aided Civil and Infrastructure Engineering","volume":"210 1","pages":""},"PeriodicalIF":11.775,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143495838","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

首页上一页

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Computer-Aided Civil and Infrastructure Engineering

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀