Construction engineering and management(CEM)has become increasingly complicated with the increasing size of engineering projects under different construction environments,motivating the digital transformation of CEM.T...Construction engineering and management(CEM)has become increasingly complicated with the increasing size of engineering projects under different construction environments,motivating the digital transformation of CEM.To contribute to a better understanding of the state of the art of smart techniques for engineering projects,this paper provides a comprehensive review of multi-criteria decision-making(MCDM)techniques,intelligent techniques,and their applications in CEM.First,a comprehensive framework detailing smart technologies for construction projects is developed.Next,the characteristics of CEM are summarized.A bibliometric review is then conducted to investigate the keywords,journals,and clusters related to the application of smart techniques in CEM during 2000-2022.Recent advancements in intelligent techniques are also discussed under the following six topics:①big data technology;②computer vision;③speech recognition;④natural language processing;⑤machine learning;and⑥knowledge representation,understanding,and reasoning.The applications of smart techniques are then illustrated via underground space exploitation.Finally,future research directions for the sustainable development of smart construction are highlighted.展开更多
Geotechnical engineering data are usually small-sample and high-dimensional,which brings a lot of challenges in predictive modeling.This paper uses a typical high-dimensional and small-sample swell pressure(P_(s))data...Geotechnical engineering data are usually small-sample and high-dimensional,which brings a lot of challenges in predictive modeling.This paper uses a typical high-dimensional and small-sample swell pressure(P_(s))dataset to explore the possibility of using multi-algorithm hybrid ensemble and dimensionality reduction methods to mitigate the uncertainty of soil parameter prediction.Based on six machine learning(ML)algorithms,the base learner pool is constructed,and four ensemble methods,Stacking(SG),Blending(BG),Voting regression(VR),and Feature weight linear stacking(FWL),are used for the multi-algorithm ensemble.Furthermore,the importance of permutation is used for feature dimensionality reduction to mitigate the impact of weakly correlated variables on predictive modeling.The results show that the proposed methods are superior to traditional prediction models and base ML models,where FWL is more suitable for modeling with small-sample datasets,and dimensionality reduction can simplify the data structure and reduce the adverse impact of the small-sample effect,which points the way to feature selection for predictive modeling.Based on the ensemble methods,the feature importance of the five primary factors affecting P_(s) is the maximum dry density(31.145%),clay fraction(15.876%),swell percent(15.289%),plasticity index(14%),and optimum moisture content(13.69%),the influence of input parameters on P_(s) is also investigated,in line with the findings of the existing literature.展开更多
The study proposes an improved Harris hawks optimization(IHHO) algorithm by integrating the standard Harris hawks optimization(HHO) algorithm and mutation-based search mechanism for developing a high-performance machi...The study proposes an improved Harris hawks optimization(IHHO) algorithm by integrating the standard Harris hawks optimization(HHO) algorithm and mutation-based search mechanism for developing a high-performance machine learning solution for predicting soil compression index. HHO is a newly introduced meta-heuristic optimization algorithm(MOA) used to solve continuous search problems.Compared to the original HHO, the proposed IHHO can evade trapping in local optima, which in turn raises the search capabilities and enhances the search mechanism relying on mutation. Subsequently, a novel meta-heuristic-based soft computing technique called ELM-IHHO was established by integrating IHHO and extreme learning machine(ELM) to estimate soil compression index. A sum of 688 consolidation test data was collected for this purpose from an ongoing dedicated freight corridor railway project. To evaluate the generalization capability of the proposed ELM-IHHO model, a detailed comparison between ELM-IHHO and other well-established MOAs, such as particle swarm optimization,genetic algorithm, and biogeography-based optimization integrated with ELM, was performed. Based on the outcomes, the ELM-IHHO model exhibits superior performance over the other MOAs in predicting soil compression index.展开更多
Uplift of segmental linings in shield tunnels presents considerable challenges,potentially compromising the structural integrity of tunnels.The uplift movement can be physically modelled using a Timoshenko beam on a W...Uplift of segmental linings in shield tunnels presents considerable challenges,potentially compromising the structural integrity of tunnels.The uplift movement can be physically modelled using a Timoshenko beam on a Winkler foundation.This study introduces an innovative method employing a physicsinformed neural network(PINN)to solve the governing differential equations of shield tunnel linings under specifiedboundary conditions,known loads,and foundation parameters.Importantly,the PINN does not rely on empirical data for training;instead,it incorporates physics-based constraints to accurately capture spatial variations in load and foundation stiffness during grouting and construction phases.The PINN model was validated with fielddata from a shield tunnel in the Pazhou branch of the Guangzhou-Dongguan-Shenzhen intercity railway line.The results demonstrate the effectiveness of the model in predicting segment uplift.Furthermore,compared to traditional analytical solutions,the PINN model provides a more realistic representation of fieldconditions by integrating spatial variations in loading and foundation support.展开更多
An efficient determination of the geological characteristics and soil-rock type ahead of a tunnel face is critical for adjusting construction parameters during shield tunnelling.In general,operational engineers rely o...An efficient determination of the geological characteristics and soil-rock type ahead of a tunnel face is critical for adjusting construction parameters during shield tunnelling.In general,operational engineers rely on visual observations of mucky soil types from belt conveyors.This results in shield halting and involves both time and cost implications.This paper proposes a deep learning approach designed to identify mucky soil by monitoring a video installed on the strut of a belt conveyer.The proposed approach comprises four steps:(1)image acquisition,(2)enhanced you-only-look-once(YOLO)modelling,(3)model performance evaluation,and(4)soil identification based on an optimal analysis.The enhanced YOLO model is a deep image detection algorithm.It was introduced by integrating two innovative strategies:data augmentation and imbalance learning.This enhancement accelerates the speed of image identification and improves the overall classification performance.A case study of shield tunnelling in the soil-rock mixed strata of the GuangzhoueFoshan intercity railway line was conducted to validate the proposed approach.The results indicate that the enhanced YOLO model achieves a classification performance comparable to that of the highly optimised AlexNet and GoogleNet.Additionally,the proposed approach more effectively detects the muck soil content than manual observation.This demonstrates its potential for real-time applications in shield tunnelling operations.展开更多
The efficiency of gas hydrate production depends on the success of gas exploration and occurrence evaluation.The existing evaluation models are generally univariate and only applicable to certain geological settings.T...The efficiency of gas hydrate production depends on the success of gas exploration and occurrence evaluation.The existing evaluation models are generally univariate and only applicable to certain geological settings.This study presents a holistic approach to evaluate the likelihood of gas hydrate occurrence by supplying an index for mapping gas hydrate levels with depth.The approach integrates a generalised TOPSIS method with the fuzzy set theory.An expedition of gas hydrate conducted in the Shenhu area of the South China Sea was adopted as a case study to assess the reliability of the proposed index.As a multivariate model,the proposed approach enables the capture of non-linearity associated with gas hydrates in its entirety.The magnitude of the strength of the influential factor varies substantially from one site to another across the Shenhu area.The results also show that no site achieves the highest likelihood‘Level V’.These results are consistent with the gas saturation values obtained using Archie’s relationship.For example,at SH4 and SH7,the values of the likelihood index are the highest between 170–185 m and 150–165 m,respectively,and the observed saturation at these locations varies from 20%(SH4)to 43%(SH7).The proposed likelihood index yields a prominent ability to quantify the level of occurrence of gas hydrates with depth at different sites.It appears to be an efficient multicriteria system bound to improve the management of the gas production trial stage.展开更多
This paper presents an analysis of a tunnel failure accident during shield tunnel construction on Foshan Metro Line 2 in China.The failure is caused by the leakage of the multilayer seal system,which consists of sever...This paper presents an analysis of a tunnel failure accident during shield tunnel construction on Foshan Metro Line 2 in China.The failure is caused by the leakage of the multilayer seal system,which consists of several brush seals at the tail of the shield.Four different failure modes for the multilayer seal system are discussed.A simple structural analysis of the brush seals is then conducted,and failure mode 4(failure due to brush seal deformation)is identified as a major reason for the Foshan tunnel accident.A finite element method(FEM)analysis is employed to validate the conclusions drawn from the simple structural analysis of the brush seals.展开更多
This paper proposed a framework for muck types identification based on data augmentation-assisted image recognition during shield tunnelling.The muck pictures were collected from the shield monitoring system above the...This paper proposed a framework for muck types identification based on data augmentation-assisted image recognition during shield tunnelling.The muck pictures were collected from the shield monitoring system above the conveyor belt.The data augmentation operations were then used to increase the quality of the original images.Furthermore,the Bayesian optimisation algorithm was employed to adjust the parameters of augmenters and highlight the features of the photos.The deep image recognition algorithms(AlexNet and GoogLeNet)were trained and enhanced by the augmentation images,which were used to establish the muck types identification models and assessed by the evaluation indices.Model efficiency was analysed through the performance and time cost of training and validation processes to select the optimal model for muck types identification.Results showed that the performance of identification models could be highly increased by data augmentation with Bayesian optimisation,and the enhanced GoogLeNet performed the highest efficiency for muck types identification.展开更多
基金funded by the project of Guangdong Provincial Basic and Applied Basic Research Fund Committee(2022A1515240073)the Pearl River Talent Recruitment Program(2019CX01G338),Guangdong Province.
文摘Construction engineering and management(CEM)has become increasingly complicated with the increasing size of engineering projects under different construction environments,motivating the digital transformation of CEM.To contribute to a better understanding of the state of the art of smart techniques for engineering projects,this paper provides a comprehensive review of multi-criteria decision-making(MCDM)techniques,intelligent techniques,and their applications in CEM.First,a comprehensive framework detailing smart technologies for construction projects is developed.Next,the characteristics of CEM are summarized.A bibliometric review is then conducted to investigate the keywords,journals,and clusters related to the application of smart techniques in CEM during 2000-2022.Recent advancements in intelligent techniques are also discussed under the following six topics:①big data technology;②computer vision;③speech recognition;④natural language processing;⑤machine learning;and⑥knowledge representation,understanding,and reasoning.The applications of smart techniques are then illustrated via underground space exploitation.Finally,future research directions for the sustainable development of smart construction are highlighted.
基金great gratitude to National Key Research and Development Project(Grant No.2019YFC1509800)for their financial supportNational Nature Science Foundation of China(Grant No.12172211)for their financial support.
文摘Geotechnical engineering data are usually small-sample and high-dimensional,which brings a lot of challenges in predictive modeling.This paper uses a typical high-dimensional and small-sample swell pressure(P_(s))dataset to explore the possibility of using multi-algorithm hybrid ensemble and dimensionality reduction methods to mitigate the uncertainty of soil parameter prediction.Based on six machine learning(ML)algorithms,the base learner pool is constructed,and four ensemble methods,Stacking(SG),Blending(BG),Voting regression(VR),and Feature weight linear stacking(FWL),are used for the multi-algorithm ensemble.Furthermore,the importance of permutation is used for feature dimensionality reduction to mitigate the impact of weakly correlated variables on predictive modeling.The results show that the proposed methods are superior to traditional prediction models and base ML models,where FWL is more suitable for modeling with small-sample datasets,and dimensionality reduction can simplify the data structure and reduce the adverse impact of the small-sample effect,which points the way to feature selection for predictive modeling.Based on the ensemble methods,the feature importance of the five primary factors affecting P_(s) is the maximum dry density(31.145%),clay fraction(15.876%),swell percent(15.289%),plasticity index(14%),and optimum moisture content(13.69%),the influence of input parameters on P_(s) is also investigated,in line with the findings of the existing literature.
文摘The study proposes an improved Harris hawks optimization(IHHO) algorithm by integrating the standard Harris hawks optimization(HHO) algorithm and mutation-based search mechanism for developing a high-performance machine learning solution for predicting soil compression index. HHO is a newly introduced meta-heuristic optimization algorithm(MOA) used to solve continuous search problems.Compared to the original HHO, the proposed IHHO can evade trapping in local optima, which in turn raises the search capabilities and enhances the search mechanism relying on mutation. Subsequently, a novel meta-heuristic-based soft computing technique called ELM-IHHO was established by integrating IHHO and extreme learning machine(ELM) to estimate soil compression index. A sum of 688 consolidation test data was collected for this purpose from an ongoing dedicated freight corridor railway project. To evaluate the generalization capability of the proposed ELM-IHHO model, a detailed comparison between ELM-IHHO and other well-established MOAs, such as particle swarm optimization,genetic algorithm, and biogeography-based optimization integrated with ELM, was performed. Based on the outcomes, the ELM-IHHO model exhibits superior performance over the other MOAs in predicting soil compression index.
基金funded by“The Pearl River Talent Recruitment Program”in 2019(Grant No.2019CX01G338)Guangdong Province and Guangdong Provincial Basic and Applied Basic Research Fund Committee(2022A1515240073).
文摘Uplift of segmental linings in shield tunnels presents considerable challenges,potentially compromising the structural integrity of tunnels.The uplift movement can be physically modelled using a Timoshenko beam on a Winkler foundation.This study introduces an innovative method employing a physicsinformed neural network(PINN)to solve the governing differential equations of shield tunnel linings under specifiedboundary conditions,known loads,and foundation parameters.Importantly,the PINN does not rely on empirical data for training;instead,it incorporates physics-based constraints to accurately capture spatial variations in load and foundation stiffness during grouting and construction phases.The PINN model was validated with fielddata from a shield tunnel in the Pazhou branch of the Guangzhou-Dongguan-Shenzhen intercity railway line.The results demonstrate the effectiveness of the model in predicting segment uplift.Furthermore,compared to traditional analytical solutions,the PINN model provides a more realistic representation of fieldconditions by integrating spatial variations in loading and foundation support.
基金funded by Guangdong Province Scientific Research Project for Young Innovation Talent(Grant No.2022KQNCX239)The Pearl River Talent Recruitment Program(Grant No.2019CX01G338),Guangdong Province.
文摘An efficient determination of the geological characteristics and soil-rock type ahead of a tunnel face is critical for adjusting construction parameters during shield tunnelling.In general,operational engineers rely on visual observations of mucky soil types from belt conveyors.This results in shield halting and involves both time and cost implications.This paper proposes a deep learning approach designed to identify mucky soil by monitoring a video installed on the strut of a belt conveyer.The proposed approach comprises four steps:(1)image acquisition,(2)enhanced you-only-look-once(YOLO)modelling,(3)model performance evaluation,and(4)soil identification based on an optimal analysis.The enhanced YOLO model is a deep image detection algorithm.It was introduced by integrating two innovative strategies:data augmentation and imbalance learning.This enhancement accelerates the speed of image identification and improves the overall classification performance.A case study of shield tunnelling in the soil-rock mixed strata of the GuangzhoueFoshan intercity railway line was conducted to validate the proposed approach.The results indicate that the enhanced YOLO model achieves a classification performance comparable to that of the highly optimised AlexNet and GoogleNet.Additionally,the proposed approach more effectively detects the muck soil content than manual observation.This demonstrates its potential for real-time applications in shield tunnelling operations.
基金funded by“The Pearl River Talent Recruitment Program”in 2019(Grant No.2019CX01G338)Guangdong Province and the Scientific Research Initiation Grant of Shantou University for New Faculty Member(Grant No.NTF19024-2019).
文摘The efficiency of gas hydrate production depends on the success of gas exploration and occurrence evaluation.The existing evaluation models are generally univariate and only applicable to certain geological settings.This study presents a holistic approach to evaluate the likelihood of gas hydrate occurrence by supplying an index for mapping gas hydrate levels with depth.The approach integrates a generalised TOPSIS method with the fuzzy set theory.An expedition of gas hydrate conducted in the Shenhu area of the South China Sea was adopted as a case study to assess the reliability of the proposed index.As a multivariate model,the proposed approach enables the capture of non-linearity associated with gas hydrates in its entirety.The magnitude of the strength of the influential factor varies substantially from one site to another across the Shenhu area.The results also show that no site achieves the highest likelihood‘Level V’.These results are consistent with the gas saturation values obtained using Archie’s relationship.For example,at SH4 and SH7,the values of the likelihood index are the highest between 170–185 m and 150–165 m,respectively,and the observed saturation at these locations varies from 20%(SH4)to 43%(SH7).The proposed likelihood index yields a prominent ability to quantify the level of occurrence of gas hydrates with depth at different sites.It appears to be an efficient multicriteria system bound to improve the management of the gas production trial stage.
基金The research work described herein was funded by the National Basic Research Program of China(973 Program:2015CB057806).This financial support is gratefully acknowledged.
文摘This paper presents an analysis of a tunnel failure accident during shield tunnel construction on Foshan Metro Line 2 in China.The failure is caused by the leakage of the multilayer seal system,which consists of several brush seals at the tail of the shield.Four different failure modes for the multilayer seal system are discussed.A simple structural analysis of the brush seals is then conducted,and failure mode 4(failure due to brush seal deformation)is identified as a major reason for the Foshan tunnel accident.A finite element method(FEM)analysis is employed to validate the conclusions drawn from the simple structural analysis of the brush seals.
基金funded by the Guangdong Provincial Basic and Applied Basic Research Fund Committee(2022A1515240073)“The Pearl River Talent Recruitment Program”in 2019(Grant No.2019CX01G338),Guangdong Province,China.
文摘This paper proposed a framework for muck types identification based on data augmentation-assisted image recognition during shield tunnelling.The muck pictures were collected from the shield monitoring system above the conveyor belt.The data augmentation operations were then used to increase the quality of the original images.Furthermore,the Bayesian optimisation algorithm was employed to adjust the parameters of augmenters and highlight the features of the photos.The deep image recognition algorithms(AlexNet and GoogLeNet)were trained and enhanced by the augmentation images,which were used to establish the muck types identification models and assessed by the evaluation indices.Model efficiency was analysed through the performance and time cost of training and validation processes to select the optimal model for muck types identification.Results showed that the performance of identification models could be highly increased by data augmentation with Bayesian optimisation,and the enhanced GoogLeNet performed the highest efficiency for muck types identification.
