Search

Effective functioning of water systems is critical to ensure the quality of human life. Therefore, failure prediction of water mains under climatic variations is necessary to avoid socio-economic and environmental losses. This paper aims to propose a hybrid model named STL-GC-LSTM for an accurate failure prediction of water mains under the impact of climatic variations. Firstly, the seasonal-trend decomposition based on Loess (STL) method is employed to decompose the failure time series. Next, significant climate variables are selected from the Granger causality (GC) test. Lastly, the final predicted failure of water mains is acquired by adding up the predictive results of the three components which are learned by Long Short-Term Memory (LSTM) models. Several evaluation metrics are used to assess the prediction performance. The results from a case study in Hong Kong imply that STL decomposition is promising for fully mining intrinsic properties of failure series. The developed hybrid models are effective in specifically identifying which component climatic variations exert influence on, and the final failure predictions show satisfactory agreement compared with peer models. This paper could provide an accurate estimation for failures of water mains ahead of time and be used as an essential complement to other numerical prediction models. [ABSTRACT FROM AUTHOR]

In the realm of energy infrastructure, ensuring the security of gas transmission pipelines is critical. This research introduces an advanced dynamic risk assessment framework that leverages the predictive capabilities of LSTM networks, presenting an improvement over conventional failure prediction models. Unlike traditional approaches that rely on averaging historical failure records, this framework dynamically processes historical pipeline failure incidents into sequential time series analysis, facilitating and improving the accuracy of the current failure rate. The model refines the failure rate estimation for individual pipelines by incorporating unique characteristics and modification factors, resulting in a highly precise failure likelihood estimation. Additionally, this study introduces a quantifiable linkage between mortality risk and the fatality probit value across various accident scenarios, enhancing consequence evaluation. A sensitivity analysis is then performed to assess the impact of various input parameters on the model's performance. The practical application of the model on a U.S. pipeline confirms its effectiveness. This proposed methodology substantially enhances the understanding of incident causation in gas pipeline systems, paving the way for superior safety management strategies. It is instrumental in enhancing pipeline safety, refining infrastructure planning, and optimizing safety resource allocation. The methodology offers benefits for pipeline operators, industry professionals, and regulatory agencies, contributing to improved operational safety and resource management in the pipeline industry. [ABSTRACT FROM AUTHOR]

Ensuring the safety of gas pipelines is crucial for the reliable and efficient transportation of natural gas. This study introduces a methodology for evaluating the time-varying reliability of corroded gas pipelines. The proposed approach employs both importance sampling and copula theory to effectively address the uncertainties associated with random variables involved and provide efficient estimates of failure probability. Small leak and burst failure modes are specifically investigated within this study. The methodology first establishes a step-by-step procedure for analysis. Subsequently, the study investigates the failure probability of corroded gas pipelines, taking into account both small leak and burst failures, under scenarios involving single and multiple defects. Furthermore, the study examines the influence of correlation strength and dependence structure among the involved random variables using the copula theory. Additionally, the generation of newly formed defects is thoroughly investigated, along with its impact on failure probability. Numerical examples are provided to evaluate the performance of the proposed methodology, comparing it with the benchmark failure probability estimated through Monte Carlo simulation. The results validate the precision and efficiency of the proposed methodology, while offering practical and insightful suggestions for reliability analysis of real-world gas pipelines. • Copula-based method improves time-varying reliability analysis for pipelines. • Importance sampling aligns with MCS and enhances analysis efficiency. • Correlations influence the probabilities of pipeline failures at specific pipe ages. • Field inspection data is essential to conduct a comprehensive reliability analysis. [ABSTRACT FROM AUTHOR]

• A comprehensive analysis of root causes for the accelerated internal corrosion in steel saltwater pipes coated with fusion bonded epoxy. • Cathodic delamination of the epoxy lining is identified as the primary cause of early internal corrosion failure. • Dynamic cyclic load has a greater chance for crack propagation in the epoxy lining compared to static load. • Development of recommendations and precautions based on the results of failure analysis. Effective functioning of saltwater supply system is essential to Hong Kong government agencies. However, it has been frequently observed that steel saltwater pipes suffered from severe internal corrosion and consequently early burst accidents, which may cause high economic loss and safety concerns to the public. Therefore, by taking a sample saltwater pipe made of DN450 mild steel with internal and external walls coated with fusion bonded epoxy in Hong Kong, this paper investigates the root causes and failure mechanism for the internal corrosion of this failed steel saltwater pipe through laboratory experiments and numerical simulation analysis. Two hypotheses are proposed and validated: (1) cathodic delamination of the epoxy lining, and (2) delamination of the epoxy lining due to external mechanical loads. The results verify that the sample saltwater pipe failed due to the cathodic delamination of the epoxy lining, and the electrochemical corrosion of the inner pipe wall. Moreover, it can be concluded that external mechanical load has few significant impacts on the damage of the epoxy lining for this sample pipe. This study exemplifies the importance of an in-depth analysis on the internal corrosion of steel water pipes, especially in a highly-corrosive internal environment. [ABSTRACT FROM AUTHOR]

• An LSTM-GAN generative model is employed for enriching the leak detection dataset. • The model captures the time-series features of leak signals in WDNs. • The performance of LSTM GAN is evaluated through a series of validation approaches. • The method enriches the leak signals and enhances the water leak detection accuracy. Water distribution networks (WDNs) experience significant water loss due to leaks, necessitating advanced water leak detection methods. However, machine learning-based acoustic method heavily relies on signal information and is limited by data scarcity and the limited diversity of available data. To address this challenge and enhance water leak detection in WDNs, this study proposes an LSTM-GAN approach. Acoustic signals are collected from WDNs to train the LSTM-GAN model, which generates synthetic leak signals to enhance the dataset. The validity of the generative method is evaluated through t-SNE and acoustic characteristics analysis. LSTM-based water leak detection models are established and compared using the original and the generated datasets to confirm the efficacy of generated samples in improving water leak detection performances. The capability of LSTM-GAN has been evaluated through different perspectives, including sensitivity analysis and model comparison. The results validate the quality and consistency of the generated acoustic signals under leak conditions. Besides, the optimal number of generated samples should be determined according to the requirements and characteristics of the leak detection task. Furthermore, the comparison between the proposed method and other acoustic generative methods demonstrates the superiority of LSTM-GAN-generated signals in enhancing the performance of leak detection models. The proposed generative method offers an innovative approach to facilitate machine learning-based leak detection models with limited data, thereby enhancing robustness. [Display omitted] [ABSTRACT FROM AUTHOR]

Circular economy (CE) is an emerging concept in the construction industry that focuses on maintaining materials in a continuous cycle to maximize their value. Although previous studies have explored CE in different contexts, there is a lack of studies investigating the relationship between CE barriers and drivers in developing countries. To address this gap, this study aims to identify a list of barriers and drivers of CE adoption and investigate their relationship. The literature review classifies 21 barriers into four constructs, including market policy and technology-related, legal and institutional, supply chain-related, and product design and waste management barriers. Through a questionnaire-based survey with respondents mainly from the Ghanaian construction industry, the research uncovers the most critical barriers within each construct and identifies 13 out of 16 drivers to be critical for CE implementation. The relationship between CE barriers and drivers is found to be significant and substantial, as demonstrated by the path coefficient (β = 0.723) and the p-value (< 0.05). This study's outcomes offer both theoretical and practical implications for academic and industry practitioners, empowering them to craft evidence-based strategies that facilitate successful CE adoption in developing nations. • Comprehensive understandings of the critical barriers and drivers are outlined. • Relationships between barriers and drivers are found to be significant. • Insights may inform data-driven strategies for CE adoption. • Focus on GCI study reveals CE adoption awareness in emerging economies. [ABSTRACT FROM AUTHOR]

[Display omitted] • A reliable blockage detection system is realized by incorporating low-power level sensors and 4G telemetry for real-time monitoring and a smart alarming system. • The blockage detection system employs a set of decision rules and time series analysis to distinguish blockage events from normal behavior. • The proposed system achieved a high success rate in detecting blockage events during a field test, with a low false alarm rate. • The system can help reduce the economic and environmental impacts of Sanitary sewer overflows (SSOs) and improve the overall performance of the wastewater network. Sewer blockages and overflows have significant economic and environmental repercussions on communities. Thus, it is crucial to detect and remove sewer blockages prior to the occurrence of overflows. With the improvement in mobile networks and the development of high-quality and low-power sensors and loggers, wastewater network operators can now adopt monitoring devices enabled by the "Internet of Things" (IoT) technology for real-time monitoring. To this end, this paper studies the current state-of-the-art in sewer blockage management and introduces a novel methodology to monitor sanitary sewer blockages to prevent sanitary sewer overflows (SSO) with the least human interaction. The proposed system incorporates low-power level sensors and 4G telemetry for real-time monitoring of the manhole's sewage level to detect sewer blockages. The blockage detection methodology encompasses a set of decision rules and time series analysis to identify blockage events. The final blockage detection model offers a versatile capability to be implemented on sanitary sewer networks of different types with minimum computational costs. [ABSTRACT FROM AUTHOR]

Hong Kong, among the world's most densely populated cities, has witnessed rapid growth in traffic volume, resulting in increased traffic density and vehicle loads. Regular bridge inspections are imperative to ensure human safety and safeguard property. However, conventional visual inspection methods are highly criticized for their critical limitations such as inaccuracy, subjectivity, labor-intensiveness, tediousness, and hazardousness. Cracks are regarded as the most prevalent type of defects encountered during inspection of reinforced concrete bridges. Automated detection of bridge surface cracks is a quite challenging and hectic task due to their random characteristics and usual in complex and non-uniform background textures. Presence. In light of foregoing, this paper proposes a novel computer vision model for concrete bridge crack detection in an attempt to circumvent the critical deficiencies of manual visual inspection. The developed model is envisioned on the use of you only look once version 8 (YOLOv8) architecture, which is cited as one of the most advanced convolutional neural networks structures for multi-scale object detection. Comprising three fundamental components - the backbone, neck, and head, this model introduces the concept of a decoupled head, segregating it into a detection head and a classification head. This design empowers the model with greater flexibility in handling diverse tasks. Moreover, the incorporation of the global attention module (GAM) and the wise intersection over union (IoU) loss function serves to further boost detection correctness of the developed model and amplify its generalization ability. The developed YOLOv8-GAM-Wise-IoU is compared against some of the widely acknowledged one-stage and two-stage deep learning models using the evaluation metrics of precision, recall, F1-score, mean average precision (mAP) and IoU. It outperformed them accomplishing testing precision, recall, F1-score, mAP50, mAP50–95 and mAP75 of 97.4%, 94.9%, 0.96, 98.1%, 76.2%, and 97.8%, respectively. It is also observed that developed model maintains a modest size of 93.20 M resulting in diminishing the computational cost of training and inference processes. This makes it highly deployable in various crack detection pertaining applications. It can be argued that the developed model can contribute notably to the preservation of safety and integrity of reinforced concrete bridges in Hong Kong environment. • Previously developed bridge crack detection models are reviewed. • A Novel YOLOv8-GAM-Wise-IoU Model is proposed for bridge crack detection. • GAM and Wise-IOU are introduced to enhance detection correctness. • One-stage and two-stage deep learning models are used for validation. • Efficiency of the developed model is extensively scrutinized and exemplified. [ABSTRACT FROM AUTHOR]

Sewer overflow (SO) is becoming a concerning issue since discharged wastewater contains toxic substances and debris resulting in hazardous pollution to the surrounding environment and water quality degradation; and spilled stormwater may cause localized flooding and even back-up into buildings. Therefore, it is necessary to predict the occurrence of SO in advance, which enables the utilities to post warnings, prioritize the resource allocation and take proactive measures to minimize negative effects on environment and society. This paper aims to provide a state-of-the-art review for the prediction of sewer overflow which is lacking in literature, including bibliometric survey, scientometric analysis, in-depth systematic review, and elucidation of the existing research gaps and the potential future research directions. The findings reveal that the majority focuses on combined sewer overflow (CSO), and artificial intelligence-based models are the most popular ones. The input factors vary widely among three model categories. Volume , likelihood of occurrence and water level are the three mostly adopted output factors. Further research directions are recommended to fill these gaps (e.g., consider socio-economic factors and pipe properties, deploy IoT facilities to reduce false alarms, distinguish between regular and extreme weather conditions). This state-of-the-art review fills the gap of few endeavors focusing on SO prediction, and could provide the scholars and engineers with inclusive hindsight in dealing with harmful incidents. [ABSTRACT FROM AUTHOR]

• Propose an integrated methodology for failure modeling of gas pipelines. • Identity the importance of physical covariates and handling censoring in modeling. • RSF model outperforms Cox model and other machine learning models. • Provide valuable insights for safety and risk management for gas pipelines. This study proposes a methodology to model gas transmission pipeline failures using historical pipeline failure data. Censoring occurs frequently in the dataset, and overlooking it may lead to biased predictions. To address this issue, the statistical Cox model, a survival analysis and machine learning integrated model, i.e., RSF, are introduced in this study, along with other machine learning models (ANN, SVR, RF, and XGBoost), primarily for comparison. The Cox and RSF models provide insights into the influence of covariates on pipeline failure, informing decisions regarding pipeline construction, inspection, and maintenance activities. The findings indicate that the statistical Cox model overestimates failure age due to its limited ability to capture failure nonlinearity, while other machine learning models underestimate failure age because they cannot handle dataset censoring. In contrast, the survival analysis integrated machine learning method, RSF, outperforms other methods for modeling gas pipeline failures. The findings have practical implications for effectively managing reliability and mitigating risks associated with gas transmission pipelines to ensure safety. Moreover, the proposed methodology can potentially be applied to other pipeline systems and various types of systems, provided certain requirements are met. [ABSTRACT FROM AUTHOR]

• The DT Implementation barriers are categorized under six categories. • The PLS-SEM technique was developed to prioritize DT implementation barriers. • There is a strong relationship between overcoming DT implementation barriers and OSS. • Overcoming DT implementation barriers can enhance construction sustainability by 23 %. A Digital Twin (DT) is a digital copy of a real-world object or process. Although DT has gained traction in construction, its relationship with sustainable success remains insufficiently studied. This research addresses this gap by investigating barriers to implementing DT in sustainable construction. The study employs a hybrid approach involving literature review, expert interviews, and modeling techniques, with data collected from 108 construction experts based on a number of criteria, including the experience, degree, and familiarity of the experts about the Hong Kong building and construction sector Hong Kong. The findings reveal 45 barriers categorized into six clusters, including notable obstacles such as "legacy systems," "data uncertainties," and "connectivity." The key clusters identified are "performance" and "security," while the "social" aspect of sustainable success is least supported. Recognizing these challenges assists decision-makers in navigating obstacles and utilizing DT for environmentally conscious construction, streamlined processes, and positive societal impacts. Future research could delve into integrating sustainability throughout the project lifecycle using technology adoption theories. [ABSTRACT FROM AUTHOR]

• The incident records of gas transmission pipelines in the U.S. are investigated. • Effects of physical, environmental and operational factors are investigated. • The link between background, causal factors and incident consequences is explored. • Enhance a better understanding of pipeline failures and aid in development of predictive models. The contemporary world is confronted with a significant and pressing challenge in the form of the energy crisis. Natural gas represents a potential solution to the crisis, and its transportation relies heavily on transmission and distribution pipelines. Regrettably, these pipelines have witnessed a significant number of severe incidents in recent years due to various reasons. This study aims to investigate the influence of different background factors on pipeline incidents triggered by distinct causal factors, using incident records from the PHMSA in the United States. This study reveals that outside force damage is the most frequent causal factor, responsible for 41.21% of total incidents. The failure rate of gas transmission pipelines is notably affected by the operational pressure ratio and the laying location class. Moreover, this study explores the relationship between various factors and each causal factor leading to the incident, assessing the incident's consequences in terms of type, injury, fatality, and total cost. Generally, incidents involving larger-diameter pipelines with higher operational pressure ratios and deployed in higher location classes have more severe consequences, with the highest injury rate, fatality rate, and cost rate being 1.728 × 10−4, 1.043 × 10−4, and 1953.36 $ per incident per kilometer, respectively. These findings contribute to a better understanding of pipeline failures and can aid in the development of accurate and effective predictive models for gas pipelines. [ABSTRACT FROM AUTHOR]

[Display omitted] • Application of machine intelligence to water leak detection. • Identification of controlling parameters governing the leakage phenomenon. • The derived GEP expressions achieved a reasonable accuracy in leakage prediction. Globally, the loss of potable water through buried and service water distribution networks (WDNs) is one of the persistent challenges confronted by water utilities. Most of the WDNs inspection methods are ad-hoc and typically provide the current status of the pipes. Despite the significant research efforts, a reliable prediction method of the water leak of buried and service water distribution pipes is rare. To overcome this challenge, gene expression programming (GEP) models – that uses extracted features of acoustic signals collected from noise loggers attached to pipeline valves at the chamber – are developed and validated in the current study. To develop these models, extensive fieldwork hitherto unavailable was undertaken in this study to record the flow-induced acoustic signal of WDNs. The GEP models are developed using a step function – that returns a binary output – which is leveraged to exhibit the proposed detection and prediction methods using the acoustic signal collected from the buried WDNs. The models only consider the highly correlated features with the leakage. The models are found to be able to predict leakages on metal and nonmetal pipes with about 95% accuracy. These models were developed to reduce the time and cost of deployment of equipment for leakage detection of pipes. The proposed method presented in this study highlights the prospect and advantage of using the GEP in infrastructural management given the amazing capability of the machine intelligence technique to recognize multi-dimensional circumstances with ease, high prediction accuracy, and potential for unceasing improvement. [ABSTRACT FROM AUTHOR]

Sewer overflow contains several hazardous contaminants causing adverse health effects and annoyance to the public. Despite this importance, few studies has hitherto been undertaken on examining the odor nuisance and risk of diseases due to contact with untreated overflow. However, quantitative investigation of odor emission from the sanitary sewage overflows has not been addressed. As such, this study aims to scrupulously investigate the deleterious impact of such phenomenon on public health in terms of the aforesaid matters. To this end, a multi-stage methodological approach was employed. Firstly, field data was collected from the vicinity of a wastewater treatment plant for three years, and then the concentrations of H 2 S in the aqueous phase and gaseous phase were estimated based on the environmental parameters. Afterward, the Gaussian aerial dispersion model and Quantitative Microbial Risk Assessment (QMRA) were employed. In parallel, the impact of the exposure to the malodorous H 2 S emitted from overflow cases was assessed. Furthermore, the results obtained from impact assessment were validated using the developed questionnaire survey. From the results obtained, the following major conclusions are drawn: (1) levels of H 2 S (g) near the overflow were high enough to be perceived by individuals, (2) concentrations of NH 3(g) in the ambient air were estimated lower than the perception threshold, (3) the sulfide concentration in the overflow was the most influential parameter with positive linear correlation with the concentration of H 2 S (g) , (4) the concentration of odor causes high annoyance, according to the questioning from the residents near the overflow events (5) exponential dose-response indicated 89–95% infection risk and (6) the good correlation between the estimated values of annoyance and the real annoyance level perceived by the residents proved accuracy of the methodology for estimation of H 2 S concentration and annoyance level. The unique findings obtained from this study guide the environmental decision-makers to take pre-emptive actions, preventing risk of infection and complaints from the residents. • A dispersion model is developed based on the wastewater and climate data. • A predictive-based model is developed to evaluate the annoyance of the odor from the sanitary overflows. • Initial sulfide concentration is the most significant parameter affecting the odor from an overflow. • The infection risk from the exposure to the sanitary overflows is assessed. [ABSTRACT FROM AUTHOR]

The deterioration of water pipes causes significant socio-economic and environmental burdens. Many predictors/factors are used to mitigate such problems by modelling the water pipe deterioration. However, these predictors have not been thoroughly investigated in the literature. This study adopts mixed systematic and scientometric analyses to review the predictors used in modelling water pipe deterioration. Within the study context, the predictors are categorised into pipe-related, soil and corrosion-induced, operational, and environmental. The results reveal that the pipe-related predictors have received the most attention in the reviewed studies, whereas further investigations are required to study long-term changes in the environmental-induced predictors. Accordingly, future research directions are recommended to fill these gaps (e.g., considering sustainability issues, and deploying real-time monitoring, and IoT facilities to enhance data availability. These directions greatly benefit practitioners and researchers from multidisciplinary backgrounds in research directions related to water pipes. [Display omitted] • The article reviews the predictors of the water pipe deterioration models. • A three-tier methodology is used to perform the review process. • Binary response statistic is used to extract the predictors and analysis them. • The fault tree diagram captures the logic behind the effect of the predictors on the water pipe deterioration. • Research gaps are discussed, and future direction are recommended. [ABSTRACT FROM AUTHOR]

The need for sustainable water infrastructure systems continues to grow as clean water is essential for daily life. Despite efforts to sustain water distribution networks (WDNs), they often experience frequent failures, leading to several environmental, social, and economic consequences. Previous studies have investigated the causes of water pipe failure in different contexts. However, a comprehensive and holistic understanding of these causes is lacking in the literature. Therefore, this study contributes to the existing knowledge by presenting 1) a scientometric analysis of the previous literature, 2) a systematic discussion of the causes, 3) an Analytical Hierarchy Process model and fault tree logic to prioritize and map the causes, respectively, and 4) an overview of techniques used in developing failure prediction models. The scientometric analysis reveals that little attention has been paid generally to the operational causes of water pipe failure. The same trend was supported by the systematic review, which divides a total of 33 causes into three main categories: pipe-related, environment-related, and operation-related causes. This study gives insights to academics and practitioners working in this domain on the contributions of various factors to the failure of water pipes, which would be useful in designing a sustainable and resilient WDN. [ABSTRACT FROM AUTHOR]

• Comprehensive scientometric and systematic reviews of corrosion protection methods for metallic pipelines are detailed. • 122 research articles are used to divide, classify, and discuss external and internal corrosion protection methods. • The functions, limitations, and requirements of corrosion protection methods are reported and discussed. • The purpose of this review is to assist researchers in filling research gaps and focusing on future directions. Metallic pipelines carrying water and/or oil/gas are exposed to deterioration, leaks/bursts, and failures due to corrosion. A suitable corrosion protection technique can prevent corrosion of these metallic pipelines, particularly in hostile environments, and corrosive soils. It can also reduce pipe deterioration, leaks/breaks, and failure, prolong service life, and improve the transportation process. Based on prior studies, this comprehensive review is regarded as an early attempt to cover both external and internal corrosion protection techniques for metallic pipelines in depth. The external corrosion protection techniques are classified into passive, active and hybrid corrosion protection techniques. The passive techniques include coatings, linings, barriers, material design, electrical isolation, inhibitors, and multi-passive techniques. Whereas active corrosion protection techniques include sacrificial anode and impressed current cathodic protections. Active and passive techniques are frequently combined to provide a more comprehensive corrosion protection system against newly discovered corrosion causes or coating degradations. On the other hand, internal corrosion protection techniques include internal coatings/linings/barriers, corrosion allowance, inhibitors/chemical treatments, dehydration, pigging, pipe material selection and flow control. The functions, merits, demerits, limitations/shortcomings, and requirements of corrosion protection techniques, as well as the various considerations that control their use have been covered and discussed. This comprehensive review will assist researchers, practitioners, and the industrial sector in prioritizing their policies in order not only to select the appropriate external and internal corrosion protection technique but also to fill current research gaps and focus on the future directions. [ABSTRACT FROM AUTHOR]

• Mechanical properties in centrifugal casting ductile iron pipes vary across thickness. • Equations are proposed to evaluate tube properties in ring hoop tension test. • Casting defects cause material inhomogeneity in ductile iron pipe walls. • Round bars in pipeline standards tend to overestimate actual pipe behaviour. Ductile iron pipes are widely used in pipe manufacturing for water and sewage transmission and distribution. In pipeline standards such as EN545, the pipe material is assumed isotropic and its mechanical properties are determined by tensile testing of round bars extracted along the longitudinal direction. This study experimentally examined the mechanical properties of centrifugal casting ductile iron pipes, focusing on the effects of sampling orientation, location, preparation, and test methodology. A ring hoop tension test (RHTT) was designed to evaluate circumferential properties. Force analysis of RHTT was performed and theoretical equation was derived to quantify the friction coefficient that existed between the coupon specimen and the loading fixture. A numerical study was conducted to further validate the effectiveness of the proposed theory. The test results indicated that the pipe mechanical property was inhomogeneous across the wall thickness, being inferior in the internal section and superior in the middle and external sections. This inferior layer would develop crack first and lead to subsequent outward propagation. This phenomenon led to a substantial degradation in the overall mechanical performance of the entire specimens, in comparison to the material in the middle portion. The material exhibited better performance in the circumferential direction compared to the longitudinal direction in terms of its mechanical properties, such as tensile strength and ductility. Flattened specimens showed enhanced strength and reduced ductility compared to the base pipe material. Fractographic and metallographic analyses revealed the existence of casting defects of porosity and agglomerated graphite in the internal section, which were the primary cause of material inhomogeneity. The round bars suggested per EN545 tended to overestimate the actual mechanical behaviour of ductile iron pipes, and may not be a true representation of the finished product of pipes. Flattened specimens as per ASTM E8/E8M were not recommended for ductile iron pipe material assessment, as the flattening process altered the stress–strain characteristics significantly. [ABSTRACT FROM AUTHOR]

• Data of multiple machine intelligent systems were fused to assess the subway condition. • Image processing and machine learning detected and quantified various surface defects. • Monte Carlo simulation was leveraged to estimate the defects' condition indices. • Artificial neural networks and regression analysis attained 0.928 and 0.957 validation performance. • Monte Carlo simulation forecast precision was recorded as 95% percentile. Water intrusion through soil is considered the most significant structural issue and the major cause of concrete degradation in subway networks. An enormous amount of water infiltration may expedite the deterioration mechanisms, such as moisture marks, spalling, scaling, and cracks. These mechanisms can compromise the structural durability and jeopardize people's safety. The condition assessment of concrete infrastructure is predominantly conducted based of visual inspection techniques, which are costly, time-consuming, and error prone. In this research, two main models for the condition assessment of subway networks are proposed. First, image processing techniques and machine intelligent systems are streamlined through successive operations to detect and quantify multiple surface defects automatically. Spatial and frequency domain filters are used to enhance the image clues, in tandem with artificial neural networks (ANNs) and regression analysis (RA) for defect recognition. The Monte Carlo simulation (MCS) is then leveraged to deliver advanced optimization and accurate estimation for each defect's condition index in the subway element. The developed method was implemented on four stations in Montréal subway systems, whereby the performance of ANNs and RA was validated through R2 as 0.928 and 0.957, respectively. Moreover, the MCS forecast precision was recorded as 95% percentile, which proves the efficacy of the developed models. This research provides insights for infrastructure managers about maintenance and intervention plans in order to prioritize their spending policies. [ABSTRACT FROM AUTHOR]

● Essential factors are discovered for the deterioration modeling of water distribution pipelines. ● A new machine learning approach is proposed to predict the failure risk of water pipelines. ● The proposed method can accommodate limited, high-dimensional, and highly censored data. ● The advantages and drawbacks of the proposed method and other state-of-the-art machine learning paradigms are discussed. Population growth and urbanization worldwide entail the need for continuous renewal plans for urban water distribution networks. Hence, understanding the long-term performance and predicting the service life of water pipelines are essential for facilitating early replacement, avoiding economic losses, and ensuring safe transportation of drinking water from treatment plants to consumers. However, developing a suitable model that can be used for cases where data are insufficient or incomplete remains challenging. Herein, a new advanced meta-learning paradigm based on deep neural networks is introduced. The developed model is used to predict the risk index of pipe failure. The effects of different factors that are considered essential for the deterioration modeling of water pipelines are first examined. The factors include seasonal climatic variation, chlorine content, traffic conditions, pipe material, and the spatial characteristics of water pipes. The results suggest that these factors contribute to estimating the likelihood of failure in water distribution pipelines. The presence of chlorine residual and the number of traffic lanes are the most critical factors, followed by road type, spatial characteristics, month index, traffic type, precipitation, temperature, number of breaks, and pipe depth. The proposed approach can accommodate limited, high-dimensional, and partially observed data and can be applied to any water distribution system. [Display omitted] [ABSTRACT FROM AUTHOR]

• A four-point bending technique for measuring interface fracture toughness between a soft thin-film and a stiff substrate is developed. • The applicability of the technique is verified numerically. • The requirement for the specimen dimensions is proposed. • The technique is successfully applied to characterize the interface fracture toughness between a soft epoxy coating on a steel substrate. Interface fracture toughness, also called work of adhesion or adhesion energy, is a quantity characterizing the resistance of an interface between two adhered solids against interfacial delamination. Determining the interface fracture toughness should be of great value to the studies on the related adhesion and delamination problems. Four-point bending test is an experimental approach that was originally used to measure the flexural stiffness and fracture toughness of monolithic materials. It was also used to characterize the fracture toughness of the interface when a bi-layered notched composite beam specimen is adopted (Int. J. Frac. 1989; 40: 235). However, this method does not work very well when a thin and soft material is encountered because the interface delamination cannot be triggered easily. To address this problem, in this paper, we revise the configuration of the four-point bending specimen from bi-layer to tri-layer by imposing an additional stiffer layer on the top of the thin and soft layer. The analytical solution to the energy release rate of the preexisting interfacial crack is revisited. Finite element analysis is carried out to assess the applicability and limitations of the analytical solution. With the modified four-point bending specimen, the interface fracture toughness between an epoxy coating and a steel substrate is successfully measured from the critical load that leads to the delamination of the preexisting interfacial crack. [ABSTRACT FROM AUTHOR]

• A novel Exfiltration Severity Index (ESI) is proposed to assess sewer pipelines. • A two-tiered model is applied to predict the exfiltration occurrence and severity. • GridSearchCV is employed to optimize the accuracy of the prediction models. • Shapley analysis is utilized to assess the factors affecting sewer exfiltration. Effective management of aging sewer pipelines requires accurate analysis of sewer pipeline exfiltration. Previous research studies have not paid attention to proposing an index to represent the exfiltration severity. To this end, this study introduces a novel Exfiltration Severity Index (ESI) by considering the frequency and severity of defects captured from Closed-Circuit Television (CCTV) reports. To address the need for a proactive tool that automates the exfiltration estimation and reduces dependence on CCTV reports, we leverage Machine Learning (ML) and Deep Learning (DL) models to predict sewer exfiltration occurrence and severity. In this regard, our proposed methodology comprises a series of steps that start by computing the ESI of pipeline segments considering the frequency, type, and severity of defects. After that, physical, environmental, and climatic factors influencing pipeline exfiltration are gathered and aggregated to build predictive models. We compare the performance of six ML models and two DL models, developed in two tiers to predict exfiltration occurrence and severity, respectively. The hyperparameters of each model are optimized using GridSearchCV to enhance prediction accuracy. Among the eight algorithms, the light gradient-boosting machine performs best, with 71% and 85% accuracy in the first and second tiers, respectively. Furthermore, our study investigates the influence of various factors on pipeline exfiltration and reveals that pipe diameter and population have the most significant impact on exfiltration occurrence and severity. Our method provides a valuable tool for managing sewer pipeline exfiltration and can be utilized to prioritize sewer network maintenance and repair efforts. [ABSTRACT FROM AUTHOR]

Estimating wastewater treatment plants' (WWTPs) influent parameters such as 5-day biological oxygen demand (BOD 5) and chemical oxygen demand (COD) is vital for optimizing electricity and energy consumption. Against this backdrop, the existing body of knowledge is bereft of a study employing Artificial Intelligence-based techniques for the prediction of BOD 5 and COD. Thus, in this study, Gene expression programming (GEP), multilayer perception neural networks, multi-linear regression, k-nearest neighbors, gradient boosting, and regression trees -based models were trained for predicting BOD 5 and COD, using monthly data collected from the inflow of 7 WWTPs over a three-year period in Hong Kong. Based on different statistical parameters, GEP provides more accurate estimations, with R2 values of 0.784 and 0.861 for BOD 5 and COD respectively. Furthermore, results of sensitivity analysis undertaken by monte Carlo simulation revealed that both BOD 5 and COD were mostly affected by concentrations of total suspended solids, and a 10% increase in the value of TSS resulted in a 7.94% and 7.92% increase in the values of BOD 5 and COD, respectively. It is seen that the GEP modeling results complied with the fundamental chemistry of the wastewater quality parameters and can be further applied on other sewage sources such as industrial sewage and leachate. The promising results obtained pave the way for forecasting the operational parameters during sludge processing, leading to an extensive energy savings during the wastewater treatment processes. • Different machine learning techniques for predicting BOD 5 and COD were employed. • GEP showed superior performance against other machine learning-based techniques. • BOD 5 and COD were correlated with TSS, NH 3 , OrgN, InorgP and OrgP. • The sensitivity analysis was undertaken through Monte Carlo simulation. [ABSTRACT FROM AUTHOR]

Developing a sustainable community is mainly contingent upon energy infrastructure driven by energy alternatives. It has been attempted to accomplish energy sustainability by just ranking energy alternatives. In the current work, an integrated decision support tool (IDST) and multi-level hierarchical structure (MLHS) are developed to instigate new notions for energy alternatives. The developed IDST is unique in dealing with two-dimensional assessment information and can also concurrently analyze hybrid information. The MLHS comprises eighteen attributes grouped into five sustainability aspects (operational, economic, technological, environmental, and social) to assess energy alternatives, including gas, coal, nuclear, solar, hydro, wind, and biomass. Firstly, the importance of attributes is calculated using the optimal weighting approach. Then, the ranking of alternatives is determined and validated. Lastly, the multi-facet performance of alternatives is assessed in terms of distributed performance and indexing using the probabilistic evidential reasoning algorithm, and the acceptability of alternatives is classified. The results revealed hydro is the most favorable energy alternative for achieving sustainability, followed by solar and wind, with a 'very good' index overall. The developed framework is useful for designing sustainable hybrid energy infrastructures and for intergovernmental organizations to draft long- and short-term policies for achieving the energy sustainability targets of SDG-7. • Constructed critical success factors for energy system quantitatively. • Evidential reasoning driven integrated multi-attribute decision tool is used. • Two-dimensional and hybrid assessment information of factors is used concurrently. • Sustainability is evaluated using some new notions in energy domain. • Long- and short-term policy recommendations for energy sustainability in Pakistan. [ABSTRACT FROM AUTHOR]

• Critical causes of RMAA-related accidents are identified. • Novel hybrid fuzzy-based algorithms are employed for result accuracy enhancement. • Considerable inherent interrelationships exist among RMAA-related causal factors. • "Limited financial/safety resources of SMEs" is the most influential causal factor. • The identified causes are prioritized using IVIF-DEMATEL-ANP method. Despite the recent improvements made to the area of occupational health and safety (OHS) within the construction sector, the Repair, Maintenance, Minor alteration, and Addition (RMAA) works have been given scant attention. In this study, given the significance of the injuries reported in the RMAA sector, a meticulous investigation is conducted into the causal factors contributing to the related accidents by capturing their causal interrelationships together with their importance levels. To this end, first, a comprehensive list of factors contributing to RMAA accidents was obtained through an extensive literature review and experts' interviews. Then, through the lenses of qualified relevant experts in Hong Kong, the proposed interval-valued intuitionistic fuzzy (IVIF) DEMATEL and IVIF analytic network process were employed to respectively uncover the cause-and-effect relationships among these factors and prioritize them. The findings show that "the lack of assessment and praising of workers' OHS understanding and performance," "the high turnover rate of workers resulting in difficulties in providing safety training and education," and "lack of safety training for workers" are the most critical causes to be given full attention by construction safety managers. The methodological approach proposed in this study brings about two theoretical contributions: unraveling interrelationships existing among the causal factors, and prioritization of them considering their interrelationships. The findings reported in this study also aid decision-makers in improving the critical causal factors in a way to enhance the OHS of RMAA sector. [ABSTRACT FROM AUTHOR]

One of the main components of smart and sustainable urban management is well-performed sewer networks. Therefore, maintaining and enhancing the functionality of sewer projects at an affordable cost are major challenges for decision-makers. However, the embracement of the Value Engineering (VE) concept to assess new sewer designs has not yet been fully embraced especially in developing countries. Thus, this study introduces a systematic VE approach for major sewer projects. A computer model based on six phases of VE methodology was developed, and named "Value Engineering Model" (VEM). To show its efficacy, it was applied to a real-life case study, leading to the following major contributions to the body of relevant knowledge: (1) unraveling the logical relations between the project functions, (2) a detailed life cycle cost analysis (LCCA), (3) a weighted evaluation matrix towards facilitating the decision-making procedure and (4) achieving an approximate 36% reduction in the sewer's project cost as compared to the common VE analysis technique. The developed model serves as a guide for design engineers and decision-makers in sewer projects. It will enable achieving the embracement of smart and sustainable drainage systems within cities at a greater pace. The results of this study will be a guide for decision-makers to reduce costs and improve sustainability by introducing VEs in the Egyptian sewer industry. • A new inclusive value engineering model for major sewer projects is developed. • The logical relations between the project functions are unravelled. • A detailed life cycle cost analysis (LCCA) of sewer projects is provided. • A weighted evaluation matrix towards facilitating the decision-making procedure is developed. • An approximate 36% reduction in the sewer's project cost is achieved. [ABSTRACT FROM AUTHOR]

The present study proposes a novel hybrid methodological approach for meticulously investigating the factors causing Sewer Overflow (SO). The proposed framework is based on a systematic literature review, experts' interviews, PLS-SEM statistical technique, and system dynamic modeling. Based on a large number of data collected from experts having rich experience in developed countries, three major findings are obtained: (1) three main factors and eighteen sub-factors are the main culprit of SO occurrence, (2) under design pipe diameter, blockages, and infiltration and inflow are the most significant sub-factors within the respective clusters, and (3) physical-related sub-factors are the most influential causes of SO occurrence under a dynamic environment. The findings attained in this study offer an insightful account for the concerned environmental decision-makers on coming up with further fecund measures towards reducing the magnitude of SO, preserving our environment from the occurrence of such harmful incidents. [Display omitted] • Through extensive literature review and experts' interviews, the contributors to sewer overflow are identified. • Through the PLS-SEM, the significance of identified contributors is quantified. • Using the System Dynamic Modeling, complex interrelationships among the contributors are uncovered. • Several theoretical and managerial implications are offered for the concerned decision-makers. [ABSTRACT FROM AUTHOR]

• A meticulous investigation into the casual factors contributing to construction accidents in a developing country is investigated. • A novel fuzzy Delphi method for identifying and prioritizing the critical causes is proposed. • The cause-and-effect relationships among the critical casual factors are unraveled using the FDEMATEL technique. • Twenty-three sub-causes are seen to be the major culprits for the occurrence of related accidents. • Organizational and workplace and environmental causes turn out to be the most influential causes. Though some studies have explored the causes of accidents on construction sites, the interdependency among the underlying causes remains elusive. This undermines the efficacy of any decision made by safety experts in reducing accidents' impact. To fill this gap, a hybrid fuzzy-based framework is developed in this study to comprehensively identify and prioritize critical causes, as well as map interrelationships among these causes. The proposed framework is based on the infusion of the Pentagonal Fuzzy Delphi Method (PFDM) and Fuzzy DEMATEL techniques. Findings show that six main causes and twenty-three corresponding sub-causes (out of forty-seven identified ones) are the major culprits for the occurrence of related accidents. Furthermore, it was revealed that "organizational" and "workplace and environmental" causes turn out to be the most influential causes, while inappropriate safety guidelines and policies, poor safety management system, poor safety culture, poor safety knowledge of management team, the financial instability of firms, and corruption were the predominant sub-causes affecting the related accidents' impact. To validate findings, several interviews with senior experts are undertaken. The outcomes of this study are vital for the concerned safety decision-makers by highlighting the influential causes debilitating the safety and health of involved workers. [ABSTRACT FROM AUTHOR]

A smart and sustainable drainage system is strongly dependent on appropriate functioning of sewer pipelines existing within the infrastructure of cities' networks. Although numerous studies have been conducted on the sewer networks, the existing body of literature lacks a comprehensive review paper that contains scientometric analysis, critical review, and meta-analysis in one holistic frame. To fill this gap, this paper provides a review of sewer deterioration models and factors causing sewer pipeline deterioration through a hybrid review approach. Having meticulously reviewed the studies undertaken hitherto using the adopted hybrid review approach, the following conclusions are noted: (1) The meta-analysis results indicate that the most important factors impacting sewer pipeline deterioration include operational defect, pipe shape, pipe material, waste type, structural defect, and hydraulic conditions, (2) Factors and defects that cause sewer deterioration have a varying degree of impact on the deterioration process; a good understanding of their individual impact will improve the sewer infrastructure performance and save cost, and (3) Countries from Africa, South America, the Middle East, and Asia are lagging in this research area, although there might be some justification for this, such as availability of funds and research priority. Sewer infrastructure is an important part of the environment, and keen attention needs to be given to it; therefore, there is a need for more international research collaborations. The findings obtained from this review paper are expected to facilitate the adoption of sagacious policies by the concerned decision-makers, paving the way for realizing smarter and more sustainable cities. • An inclusive scientometric analysis on the papers published on sewer pipeline deterioration is undertaken. • An in-depth discussion on the methods used in modeling sewer pipeline deterioration is provided. • Critical factors playing role in the deterioration of sewers networks are identified. • The significance levels of identified critical factors are unraveled using meta-analysis approach. • Current research gaps together with the potential research streams to be undertaken are put forward. [ABSTRACT FROM AUTHOR]

Modular Integrated Construction (MiC) has recently grabbed the attention of numerous researchers and practitioners across the globe, even though their adoption on construction sites has led to some critical safety hazards that differ from those of common construction projects. In this regard, cranes are the most widely utilized equipment used in MiC projects; however, there have not been any studies carried out on the safety issues of cranes in such projects. Lack of such consideration not only leads to overshadowing the greater adoption of MiC-based technologies, but also worsens the safety and health of related workers. Considering this, a Crane Safety Index (CSI) is developed in this study to improve the Occupational Health and Safety (OHS) of such projects, which is based on experts' interviews together with the exploitation of the analytical hierarchy process. To validate the efficacy of the proposed CSI, its application to the case of three MiC-constructed projects was considered. Applying the CSI developed to the selected projects, the following contributions are noted: (1) identification of safety factors playing role in the safety of crane operations that are peculiar to the MiC projects, (2) obtaining a specific safety score for crane operations in MiC projects, and (3) determination of fruitful technologies improving the OHS of related operations. The outcomes of this study provide the related safety decision-makers with an inclusive plan for promoting the embracement of sustainability at a greater pace by improving the well-being of workers. • A crane safety index related to the MiC projects is developed for the first time in the relevant literature. • All the factors that are peculiar to the safety of crane operations in MiC projects are identified. • The identified factors are analyzed using Analytical Hierarchy Process. • Bunch of fruitful recommendations to improve the respective OHS operations are put forward. • The suitability of the developed safety index is shown through its application to case studies. [ABSTRACT FROM AUTHOR]

Green buildings (GBs) have been adopted mainly to minimize the negative effects of the design, construction, and building operations on the environment. However, the GB-related activities have been found to be jeopardizing the occupational health and safety (OHS) of related projects, thereby debilitating the safety and health of respective crew members. Despite such vital issues, no study has been conducted yet to investigate the safety issues associated with GB construction projects in developing countries, where the inclination towards the adoption of GB is on the rise. Using this as a point of departure, the present study assesses the safety risks caused by GB projects with the use of a fuzzy-based RAM, through the lenses of the experts in Kazakhstan. The proposed RAM integrates Fuzzy Delphi Method (FDM) and Fuzzy Best Worst Method (FBWM). The FDM results clearly indicated that sustainable buildings continue to endanger the safety and health of respective workers, while fall from height and overexertion are found to be the leading causes of GB-associated risks using the FBWM. Despite the research limitations, this study prudently assessed the OHS-related risks to the LEED-based (the most widely used certification in the country) projects, and offered a fertile ground for future research to be conducted in developing economy settings. The findings indicated that the construction key players need to pay more attention to the riskiest GB-related hazards by investing their efforts in making the built environment truly sustainable in a not-too-distant future, which can improve the well-being of workers involved. • The critical safety risks threatening the workers involved in green building construction projects are identified. • The critical safety risks in relation to GB projects are prioritized using fuzzy-based-constrained optimization model. • The prioritized safety risks are effectively evaluated using the concept of risk matrix. • The results produced from the study are validated through focus group discussion approach. [ABSTRACT FROM AUTHOR]