相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Materials Science, Multidisciplinary
Jeong Ah Lee et al.
Summary: Recently, there has been development in metal additive manufacturing (MAM) due to its advantages such as complex geometries, waste reduction, design flexibility, and cost-effectiveness. However, the influence of processing parameters on MAM product properties is not well understood or easily predictable. This study applies explainable machine learning (xML) models to predict and understand the geometry and defects of MAM-processed Fe-Ni alloys. Gaussian process regression (GPR) predicts as-printed height and porosity, while a support vector machine (SVM) classifies defect types based on predicted and measured porosities. The Shapley additive explanation (SHAP) approach is used to analyze feature importance. This study provides insights into the use of xML models to link processing with results in MAM.
JOURNAL OF MATERIALS RESEARCH AND TECHNOLOGY-JMR&T
(2023)
Article
Engineering, Civil
Omid Yazdanpanah et al.
Summary: A nonmodel and output-only-based framework is used to compute a robust wavelet-based damage-sensitive feature and estimate engineering demand parameters of buildings with eccentrically braced frames. A large database is recruited for estimation and various regression algorithms are investigated for prediction. Extreme Gradient Boosted Trees are found to have the highest efficiency in predicting the parameters and are selected as the best surrogate algorithm. The predicted parameters can be used for early decision-making in emergency operations.
ENGINEERING STRUCTURES
(2023)
Article
Engineering, Civil
Dade Lai et al.
Summary: A machine-learning model combining several algorithms is developed to predict the maximum displacements of RC beams under impact loads. The model is trained using a comprehensive database of 342 samples and achieves approximately 90% validation accuracy.
ENGINEERING STRUCTURES
(2023)
Article
Engineering, Mechanical
Chang Zhou et al.
Summary: This study compares the dynamic response of reinforced concrete (RC) piers and carbon fiber reinforced polymer (CFRP) grid-reinforced engineered cementitious composites (ECC) confined RC piers under truck collision through numerical simulation. Parametric analysis is conducted to investigate the effect of ECC and CFRP on the dynamic shear capacity of bridge piers. The results show that CFRP and ECC have a significant influence on improving the dynamic shear capacity of bridge piers, while the weight of the engine and initial velocity of the truck are the main factors affecting the dynamic shear demand.
ENGINEERING FAILURE ANALYSIS
(2023)
Article
Engineering, Mechanical
Chang Zhou et al.
Summary: This study examines the feasibility of using carbon fiber reinforced polymer (CFRP) grid-reinforced engineered cementitious composites (ECC) to improve the impact resistance of reinforced concrete (RC) columns. Impact tests were conducted on cantilever RC columns and RC columns confined with CFRP grid-reinforced ECC. The results show that CFRP grid-reinforced ECC significantly limits shear crack development and improves the shear capacity of RC columns.
INTERNATIONAL JOURNAL OF IMPACT ENGINEERING
(2023)
Article
Engineering, Civil
Chang Zhou et al.
Summary: This study explores the performance-based design of CFRP grid-reinforced ECC composite material to improve the impact resistance of RC bridge piers. Finite element analysis and experimental verification are conducted to quantify the different damage modes and states.
ENGINEERING STRUCTURES
(2023)
Article
Engineering, Civil
Chang Zhou et al.
Summary: This study proposes a new corrugated steel fender system to protect bridge piers from truck collisions. The system uses corrugated steel webs to absorb impact energy and has been verified through pendulum impact tests and finite element modeling. Parametric analyses were also performed to optimize the fender design and minimize damage to the bridge pier and truck.
THIN-WALLED STRUCTURES
(2023)
Article
Construction & Building Technology
Lei Zhang et al.
Summary: This study introduces a machine learning model based on chemistry information to estimate the compressive strength of alkali-activated materials (AAMs). By utilizing chemical feature engineering and four applied ML models, accurate predictions were achieved with detailed analysis on the impact of mixture design variables on the compressive strength development of AAMs.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Construction & Building Technology
F. Parisi et al.
Summary: This paper presents a method of automatically analyzing raw monitoring data using machine learning classification tools to detect damage in steel truss railway bridges. The results indicate that the method can achieve high accuracy in damage detection and is suitable for structural health monitoring.
AUTOMATION IN CONSTRUCTION
(2022)
Article
Mechanics
Zilan Zhang et al.
Summary: This study proposes a data-driven strategy to accelerate the simulation process of composite structures, using a novel family of composite laminates called double-double. Multiple machine learning methods are applied to accurately predict the displacement field of the double-double composite model under different loading conditions, with a speed three orders of magnitude faster than numerical simulations. This method can simplify the optimization process of composite structures.
COMPOSITE STRUCTURES
(2022)
Article
Construction & Building Technology
Ziyue Zeng et al.
Summary: This study proposes a deep-learning based approach for predicting concrete strength, considering multiple explainable features and utilizing job-site proportioning information. The model achieves high accuracy and generalization ability, revealing the interplay between different explainable features in determining concrete strength.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Engineering, Civil
Ji-Gang Xu et al.
Summary: This paper investigates the application of machine learning for predicting the seismic failure mode and maximum bearing capacity of corroded reinforced concrete columns. A comprehensive database of corroded RC columns is collected, and six machine learning algorithms are used to develop predictive models. The results show that the Random forest and CatBoost models have the best performance for predicting the seismic failure mode, while the CatBoost model outperforms traditional code models for bearing capacity prediction.
ENGINEERING STRUCTURES
(2022)
Article
Engineering, Civil
Kai Heng et al.
Summary: This study aims to clarify the collapse mechanism and evaluate the damage level of an entire bridge under vehicle-pier collision. The research reveals that the overall collapse process of the bridge structure is impact-successive and damage-accumulative, which is not completely coincident with the failure of the impacted pier.
JOURNAL OF BRIDGE ENGINEERING
(2022)
Article
Multidisciplinary Sciences
Weihua Lei et al.
Summary: The authors propose a machine learning framework for predicting connections removal in transportation networks and investigate the dynamics of edge removal in the Brazilian domestic bus transportation network and the U.S. domestic air transportation network. They find that machine learning models can accurately predict edge removals on a monthly time scale and even in the presence of external shocks. The authors also demonstrate the usefulness of their approach by forecasting the impact of a hypothetical reduction in the scale of the U.S. air transportation network due to CO2 emissions reduction policies. This forecasting approach could be valuable for future infrastructure planning.
NATURE COMMUNICATIONS
(2022)
Article
Mechanics
Chen Zhang et al.
Summary: A method combining finite element analysis (FEA) and machine learning is studied to predict mechanical properties of composite laminates, by establishing FEA models and using artificial neural network (ANN) and random forest (RF) models to learn virtual samples, predicting mechanical properties. The predicted results are consistent with FEA values, demonstrating the effectiveness of this method.
COMPOSITE STRUCTURES
(2022)
Article
Computer Science, Interdisciplinary Applications
Duc-Kien Thai et al.
Summary: This paper proposes a new approach using machine learning to predict local damage of RC panels under impact loading, providing a new pathway for predicting structural behavior despite lower accuracy than expected.
ENGINEERING WITH COMPUTERS
(2021)
Article
Geosciences, Multidisciplinary
Wengang Zhang et al.
Summary: This study applies XGBoost and RF methods to predict the USS of soft clays, showing that these approaches outperform traditional methods. Bayesian optimization is used to determine model hyperparameters, leading to more accurate and robust models.
GEOSCIENCE FRONTIERS
(2021)
Article
Engineering, Mechanical
Wuchao Zhao et al.
Summary: This study investigates the dynamic behavior and damage mechanisms of reinforced concrete piers subjected to truck impact using finite-element simulations. High-fidelity models were established and verified, revealing significant differences in impact force, failure modes, and energy absorption among different truck types. The findings highlight the importance of structural stiffness, mass distribution, and material properties in determining the response of RC piers to truck impact.
ENGINEERING FAILURE ANALYSIS
(2021)
Article
Computer Science, Artificial Intelligence
Quoc Hoan Doan et al.
Summary: This study aims to classify damage modes of RC panel under impact loading by building an ANN model and optimizing hyperparameters, with a novel optimization strategy proposed to enhance performance on a small dataset.
APPLIED SOFT COMPUTING
(2021)
Article
Engineering, Civil
R. W. Li et al.
Summary: This study aims to establish a performance-based design procedure for double-pier reinforced concrete bridge in vehicle collision scenarios, deriving factors evaluating bridge failure, defining damage indexes, and establishing damage-performance correlations under impact. The study also proposes impact-resistant performance objectives and detailed design procedures based on roadway importance levels.
Article
Engineering, Civil
R. W. Li et al.
Summary: This study focuses on the collapse process and damage levels of bridges collided by medium and heavy trucks, revealing that engine impact-induced shear failure on the reinforced concrete bridge pier is the main cause of bridge collapse. Numerical simulations of 35 truck-bridge collision cases were conducted, proposing a new quantitative damage evaluation approach.
Review
Computer Science, Artificial Intelligence
Andrea Apicella et al.
Summary: In recent years, there has been a renewed interest in trainable activation functions, which can be trained during the learning process to improve neural network performance. Various models of trainable activation functions have been proposed in the literature, many of which are equivalent to adding neuron layers with fixed activation functions and simple local rules.
Article
Computer Science, Artificial Intelligence
Shichao Zhang
Article
Construction & Building Technology
Lin Chen et al.
JOURNAL OF STRUCTURAL ENGINEERING
(2020)
Review
Engineering, Civil
Yazhou Xie et al.
EARTHQUAKE SPECTRA
(2020)
Article
Computer Science, Artificial Intelligence
Alejandro Barredo Arrieta et al.
INFORMATION FUSION
(2020)
Article
Engineering, Civil
R. W. Li et al.
ENGINEERING STRUCTURES
(2020)
Article
Construction & Building Technology
Debaditya Chakraborty et al.
JOURNAL OF BUILDING PERFORMANCE SIMULATION
(2019)
Article
Computer Science, Artificial Intelligence
Tim Miller
ARTIFICIAL INTELLIGENCE
(2019)
Article
Engineering, Civil
Steven Auyeung et al.
ENGINEERING STRUCTURES
(2019)
Article
Engineering, Civil
Ran Cao et al.
JOURNAL OF BRIDGE ENGINEERING
(2019)
Article
Engineering, Civil
Ran Cao et al.
JOURNAL OF BRIDGE ENGINEERING
(2019)
Article
Construction & Building Technology
Sujith Mangalathu et al.
JOURNAL OF STRUCTURAL ENGINEERING
(2019)
Article
Construction & Building Technology
Deyuan Zhou et al.
ADVANCES IN STRUCTURAL ENGINEERING
(2018)
Review
Engineering, Civil
Hadi Salehi et al.
ENGINEERING STRUCTURES
(2018)
Article
Computer Science, Artificial Intelligence
Alberto Fernandez et al.
JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH
(2018)
Article
Engineering, Civil
Omar I. Abdelkarim et al.
ENGINEERING STRUCTURES
(2017)
Article
Engineering, Mechanical
C. Demartino et al.
INTERNATIONAL JOURNAL OF IMPACT ENGINEERING
(2017)
Proceedings Paper
Transportation
Bella Nguyen et al.
TRANSPORT RESEARCH ARENA TRA2016
(2016)
Article
Computer Science, Interdisciplinary Applications
Hrishikesh Sharma et al.
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING
(2015)
Review
Multidisciplinary Sciences
Zoubin Ghahramani
Review
Multidisciplinary Sciences
M. I. Jordan et al.
Article
Engineering, Civil
Yanyan Sha et al.
ENGINEERING STRUCTURES
(2013)
Article
Engineering, Civil
Sherif El-Tawil et al.
JOURNAL OF BRIDGE ENGINEERING
(2005)
Article
Automation & Control Systems
B Samanta et al.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2003)
