Search results

Accurate prediction of the structural condition of urban critical infrastructure is crucial for predictive maintenance. However, the existing prediction methods lack precision due to limitations in utilizing heterogeneous sensing data and domain knowledge as well as insufficient generalizability resulting from limited data samples. This paper integrates implicit and qualitative expert knowledge into quantifiable values in tunnel condition assessment and proposes a tunnel structure prediction algorithm that augments a state-of-the-art attention-based long short-term memory (LSTM) model with expert rating knowledge to achieve robust prediction results to reasonably allocate maintenance resources.

Through formalizing domain experts' knowledge into quantitative tunnel condition index (TCI) with analytic hierarchy process (AHP), a fusion approach using sequence smoothing and sliding time window techniques is applied to the TCI and time-series sensing data. By incorporating both sensing data and expert ratings, an attention-based LSTM model is developed to improve prediction accuracy and reduce the uncertainty of structural influencing factors.

The empirical experiment in Dalian Road Tunnel in Shanghai, China showcases the effectiveness of the proposed method, which can comprehensively evaluate the tunnel structure condition and significantly improve prediction performance.

This study proposes a novel structure condition prediction algorithm that augments a state-of-the-art attention-based LSTM model with expert rating knowledge for robust prediction of structure condition of complex projects.

This paper aims to investigate the responses of single piles and pile groups due to tunneling-induced ground movements in a two-layered soil system. The analyses mainly focus on the additional single pile responses in terms of bending moment, lateral deflection, axial force, shaft resistance and pile settlement. Subsequently, a series of parametric studies were carried out to better understand the responses of single piles induced by tunneling. To give further understanding regarding the pile groups, a 2 × 2 pile group with two different pile head conditions, namely, free and capped, was considered.

Using the PLAXIS three-dimensional (3D) software, a full 3D numerical modeling is performed to investigate the effects of ground movements caused by tunneling on adjacent pile foundations. The numerical model was validated using centrifuge test data found in the literature. The relevance of the 3D model is also judged by comparison with the 2D plane strain model using the PLAXIS 2D code.

The numerical test results reveal that tunneling induces significant displacements and internal forces in nearby piles. The magnitude and distribution of internal forces depend mainly on the position of the pile toe relative to the tunnel depth and the distance between the pile and the vertical axis of the tunnel. As the volume loss increases from 1% to 3%, the apparent loss of pile capacity increases from 11% to 20%. By increasing the pile length from 0.5 to 1.5 times, the tunnel depth, the maximum pile settlement and lateral deflection decrease by about 63% and 18%, respectively. On the other hand, the maximum bending moment and axial load increase by about 7 and 13 times, respectively. When the pile is located at a distance of 2.5 times the tunnel diameter (Dt), the additional pile responses become insignificant. It was found that an increase in tunnel depth from 1.5Dt to 2.5Dt (with a pile length of 3Dt) increases the maximum lateral deflection by about 420%. Regarding the interaction between tunneling and group of piles, a positive group effect was observed with a significant reduction of the internal forces in rear piles. The maximum bending moment of the front piles was found to be higher than that of the rear piles by about 47%.

Soil is a complex material that shows differently in primary loading, unloading and reloading with stress-dependent stiffness. This general behavior was not possibly being accounted for in simple elastic perfectly plastic Mohr–Coulomb model which is often used to predict the behavior of soils. Thus, in the present study, the more advanced hardening soil model with small-strain stiffness (HSsmall) is used to model the non-linear stress–strain soil behavior. Moreover, unlike previous studies THAT are usually based on the assumption that the soil is homogeneous and using numerical methods by decoupled loadings under plane strain conditions; in this study, the pile responses have been exhaustively investigated in a two-layered soil system using a fully coupled 3D numerical analysis that takes into account the real interactions between tunneling and pile foundations. The paper presents a distinctive set of findings and insights that provide valuable guidance for the design and construction of shield tunnels passing through pile foundations.

Prefabricated technology is gradually being applied to the construction of subway stations due to its characteristic of mechanization. However, the prefabricated subway station in China is in the initial stage of development, which is prone to construction safety issues. This study aims to evaluate the construction safety risks of prefabricated subway stations in China and formulate corresponding countermeasures to ensure construction safety.

A construction safety risk evaluation index system for the prefabricated subway station was established through literature research and the Delphi method. Furthermore, based on the structure entropy weight method, matter-element theory and evidence theory, a hybrid evaluation model is developed to evaluate the construction safety risks of prefabricated subway stations. The basic probability assignment (BPA) function is obtained using the matter-element theory, the index weight is calculated using the structure entropy weight method to modify the BPA function and the risk evaluation level is determined using the evidence theory. Finally, the reliability and applicability of the evaluation model are verified with a case study of a prefabricated subway station project in China.

The results indicate that the level of construction safety risks in the prefabricated subway station project is relatively low. Man risk, machine risk and method risk are the key factors affecting the overall risk of the project. The evaluation results of the first-level indexes are discussed, and targeted countermeasures are proposed. Therefore, management personnel can deeply understand the construction safety risks of prefabricated subway stations.

This research fills the research gap in the field of construction safety risk assessment of prefabricated subway stations. The methods for construction safety risk assessment are summarized to establish a reliable hybrid evaluation model, laying the foundation for future research. Moreover, the construction safety risk evaluation index system for prefabricated subway stations is proposed, which can be adopted to guide construction safety management.

Completing construction projects within the planned schedule has widely been considered as one of the major project success factors. This study investigates the use of technologies to address delays in construction projects and aims to address three research questions (1) to identify the adopted technologies and proposed solutions in the literature, (2) to explore the reasons why the delays cannot be prevented despite disruptive technologies and (3) to determine the major strategies to prevent delays in construction projects.

In total, 208 research articles that used innovative technologies, methods, or tools to avoid delays in construction projects were investigated by conducting a comprehensive literature review. An elaborative content analysis was performed to cover the implemented technologies and their transformation, highlighted research fields in relation to selected technologies, focused delay causes and corresponding delay mitigation strategies and emphasized project types with specific delay causes. According to the analysis results, a typological framework with appropriate technological means was proposed.

The findings revealed that several tools such as planning, imaging, geo-spatial data collection, machine learning and optimization have widely been adopted to address specific delay causes. It was also observed that strategies to address various delay causes throughout the life cycle of construction projects have been overlooked in the literature. The findings of the present research underpin the trends and technological advances to address significant delay causes.

Despite the technological advancements in the digitalization era of Industry 4.0, many construction projects still suffer from poor schedule performance. However, the reason of this is questionable and has not been investigated thoroughly.

The purpose of this paper is to identify and analyze the interdependence of project complexity factors (PCFs) in metro rail projects using the Decision-Making Trial and Evaluation Laboratory (DEMATEL). The study provides qualitative and quantitative analysis of project complexities factors and their relationships. The results of the study facilitate effective project planning, proactive risk management and informed decision-making by stakeholders.

This study employs a case-based method for identifying PCFs and a DEMATEL method for analyzing the interdependence of complexity factors in metro rail projects. Initially, PCFs were identified through an extensive literature review. To validate and refine these factors, semi-structured interviews were conducted with thirty experienced professionals, each having 5–20 years of experience in roles such as project management, engineering, and planning. Further, elevated and underground metro rail projects were purposefully selected as cases, for identifying the similarities and differences in PCFs. A questionnaire survey was conducted with various technical experts in metro rail projects. These experts rated the impact of PCFs on a five-point Likert scale, for the evaluation of the interdependence of PCFs. The DEMATEL technique was used to analyze the interdependencies of the PCFs.

Metro rail projects are influenced by project complexity, which significantly impacts their performance. The analysis reveals that “design problems with existing structures,” “change in design or construction” and “land acquisition” are the key factors contributing to project complexity.

The study of project complexity in metro rail projects is limited because most of the studies have studies on examining complexity in mega projects. The existing literature lacks adequate attention in identifying project complexity and its effects on metro rail project performance. This research aims to bridge this gap by examining project complexity and interdependencies in metro rail projects.

The study is aimed to compare the prediction success of basic machine learning and ensemble machine learning models and accordingly create novel prediction models by combining machine learning models to increase the prediction success in construction labor productivity prediction models.

Categorical and numerical data used in prediction models in many studies in the literature for the prediction of construction labor productivity were made ready for analysis by preprocessing. The Python programming language was used to develop machine learning models. As a result of many variation trials, the models were combined and the proposed novel voting and stacking meta-ensemble machine learning models were constituted. Finally, the models were compared to Target and Taylor diagram.

Meta-ensemble models have been developed for labor productivity prediction by combining machine learning models. Voting ensemble by combining et, gbm, xgboost, lightgbm, catboost and mlp models and stacking ensemble by combining et, gbm, xgboost, catboost and mlp models were created and finally the Et model as meta-learner was selected. Considering the prediction success, it has been determined that the voting and stacking meta-ensemble algorithms have higher prediction success than other machine learning algorithms. Model evaluation metrics, namely MAE, MSE, RMSE and R², were selected to measure the prediction success. For the voting meta-ensemble algorithm, the values of the model evaluation metrics MAE, MSE, RMSE and R² are 0.0499, 0.0045, 0.0671 and 0.7886, respectively. For the stacking meta-ensemble algorithm, the values of the model evaluation metrics MAE, MSE, RMSE and R² are 0.0469, 0.0043, 0.0658 and 0.7967, respectively.

The study shows the comparison between machine learning algorithms and created novel meta-ensemble machine learning algorithms to predict the labor productivity of construction formwork activity. The practitioners and project planners can use this model as reliable and accurate tool for predicting the labor productivity of construction formwork activity prior to construction planning.

The study provides insight into the application of ensemble machine learning algorithms in predicting construction labor productivity. Additionally, novel meta-ensemble algorithms have been used and proposed. Therefore, it is hoped that predicting the labor productivity of construction formwork activity with high accuracy will make a great contribution to construction project management.

This study aimed to address a gap in subcontractor management by focusing on previously unexplored complexities surrounding subcontractor management in developing countries. While past studies concentrated on selection and relationships, this study delved into how effective subcontractor management impacts project success.

This study used the Bayesian Network analysis approach, through a meticulously developed questionnaire survey refined through a piloting stage involving experienced industry professionals. The survey was ultimately distributed among participants based in Accra, Ghana, resulting in a response rate of approximately 63%.

The research identified diverse components contributing to subcontractor disruptions, highlighted the necessity of a clear regulatory framework, emphasized the impact of financial and leadership assessments on performance, and underscored the crucial role of main contractors in Integrated Project and Labour Cost Management with Subcontractor Oversight and Coordination.

Previous studies have not considered the challenges subcontractors face in projects. This investigation bridges this gap from multiple perspectives, using Bayesian network analysis to enhance subcontractor management, thereby contributing to the successful completion of construction projects.

The Government’s investment in infrastructure projects is considerably high, especially in bridge construction projects. Government authorities must establish an initial forecasted budget to have transparency in transactions. Early cost estimating is challenging for Quantity Surveyors due to incomplete project details at the initial stage and the unavailability of standard cost estimating techniques for bridge projects. To mitigate the difficulties in the traditional preliminary cost estimating methods, there is a requirement to develop a new initial cost estimating model which is accurate, user friendly and straightforward. The research was carried out in Sri Lanka, and this paper aims to develop the artificial neural network (ANN) model for an early cost estimate of concrete bridge systems.

The construction cost data of 30 concrete bridge projects which are in Sri Lanka constructed within the past ten years were trained and tested to develop an ANN cost model. Backpropagation technique was used to identify the number of hidden layers, iteration and momentum for optimum neural network architectures.

An ANN cost model was developed, furnishing the best result since it succeeded with around 90% validation accuracy. It created a cost estimation model for the public sector as an accurate, heuristic, flexible and efficient technique.

The research contributes to the current body of knowledge by providing the most accurate early-stage cost estimate for the concrete bridge systems in Sri Lanka. In addition, the research findings would be helpful for stakeholders and policymakers to propose policy recommendations that positively influence the prediction of the most accurate cost estimate for concrete bridge construction projects in Sri Lanka and other developing countries.

The purpose of this paper is to review cases of artificial reefs built through additive manufacturing (AM) technologies and analyse their ecological goals, fabrication process, materials, structural design features and implementation location to determine predominant parameters, environmental impacts, advantages, and limitations.

The review analysed 16 cases of artificial reefs from both temperate and tropical regions. These were categorised based on the AM process used, the mortar material used (crucial for biological applications), the structural design features and the location of implementation. These parameters are assessed to determine how effectively the designs meet the stipulated ecological goals, how AM technologies demonstrate their potential in comparison to conventional methods and the preference locations of these implementations.

The overview revealed that the dominant artificial reef implementation occurs in the Mediterranean and Atlantic Seas, both accounting for 24%. The remaining cases were in the Australian Sea (20%), the South Asia Sea (12%), the Persian Gulf and the Pacific Ocean, both with 8%, and the Indian Sea with 4% of all the cases studied. It was concluded that fused filament fabrication, binder jetting and material extrusion represent the main AM processes used to build artificial reefs. Cementitious materials, ceramics, polymers and geopolymer formulations were used, incorporating aggregates from mineral residues, biological wastes and pozzolan materials, to reduce environmental impacts, promote the circular economy and be more beneficial for marine ecosystems. The evaluation ranking assessed how well their design and materials align with their ecological goals, demonstrating that five cases were ranked with high effectiveness, ten projects with moderate effectiveness and one case with low effectiveness.

AM represents an innovative method for marine restoration and management. It offers a rapid prototyping technique for design validation and enables the creation of highly complex shapes for habitat diversification while incorporating a diverse range of materials to benefit environmental and marine species’ habitats.

The booming social media attracts construction professionals (CPs) to express emotions caused by work pressure (WP) through online behaviors. Previous works focus on the analysis of WP and emotions but do not adequately consider how WP can be reflected through online emotions. Thus, this study aims to attempt to explore the quantitative relationship between online emotional intensity and WP.

This study developed a linguistic-sticker (LS) model to quantitatively evaluate the sentiment intensity of posts published on social media. Moreover, the authors designed two econometric models of ordinary least squares regression and negative binomial regression to test the hypothesis.

The research found that posts with stronger negative sentiment (or positive sentiment) indicate that CPs face higher (or lower) WP. Besides, there is a negative bias between the sentiment intensity of posts and the comment quantity.

The positive correlation between sentiment intensity of posts and WP has been confirmed, which indicates that construction managers should pay more attention to CPs' behavior on social media, and take a more direct way to analyze work-related online behavior (e.g. posting, commenting). The dynamic monitoring of emotion-related posts also provides a direct basis for the management team to learn about CP's pressure status and propose measures to reduce their negative emotions. Furthermore, the emotional posts published by CPs on social media provide a direct basis for team managers to obtain their psychological state.

The research contributes to incorporating CPs' emotions into the LS model and to providing information systems artifacts and new findings on the analysis of WP and online emotions.