Search

The application of deep learning in construction has attracted increasing attention among researchers in recent years. In this review article, comprehensive scientometric analysis and critical review were performed to analyze the state-of-the-art literature on the application of deep learning in construction. This research used the science mapping method to quantitatively and systematically analyze 423 related bibliographic records retrieved from the Scopus database, and further, a critical review was performed on the collected themes of all the related publications. The results of the critical review indicate that deep convolution neural networks, you only look once, single-shot detectors, recurrent neural networks, residual neural networks, and fast region-based convolution neural networks have been the most widely used deep-learning methods in the construction industry. The most commonly addressed problems in the construction industry using deep-learning methods include classification of construction equipment, worker's safety helmet detection, ergonomics analysis, image enhancement, and feature extraction. This paper provides an in-depth understanding and big-picture overview of the existing literature along with the challenges and future direction of research on deep learning in construction.

Worksite communication is a key to boosting teamwork and improving worker performance on the construction worksite. Communication among workers on the construction site mostly consists of speech communication. However, construction sites are typically noisy due to construction tasks like drilling and operation of heavy equipment. Meanwhile, workers on construction sites typically represent a range of different ethnic and linguistic backgrounds and have different speaking accents. This can make it difficult for the listener to understand the speaker clearly, leading to miscommunication and errors in decision making on the construction site. Technological advancements in recent years can be leveraged to mitigate this problem. In this paper, a keyword identification framework is developed for speech communication on the construction site. For this framework, 12 hours of raw audio data containing 18 crane signalman speech commands (referred to as “keywords”) are collected. The crane signalman uses specific keywords to communicate with the crane operator and guide the crane operator in the crane operations. The 2-second audio clips (this being the approximate duration of each keyword) are extracted from the raw audio dataset, and construction site noise is added. Moreover, mel-frequency cepstral coefficients are extracted from the waveform audio dataset. The extracted mel-frequency cepstral coefficients, in turn, are used to train the 1-dimensional convolutional neural network. After training, the model is found to achieve a training accuracy of 97.3%, a validation accuracy of 96.1%, and a testing accuracy of 93.8%. The model is further deployed for real-time identification of keywords in speech, with the model achieving an accuracy of 95.3%. In light of these findings, it can be concluded that the developed framework is suitable for real-time application in noisy construction sites for identifying specific keywords in speech.

While the design practice in the architecture, engineering, and construction (AEC) industry continues to be a creative activity, approaching the design problem from a perspective of the decision-making science has remarkable potentials that manifest in the delivery of high-performing sustainable structures. These possible gains can be attributed to the myriad of decision-making tools and technologies that can be implemented to assist design efforts, such as artificial intelligence (AI) that combines computational power and data wisdom. Such combination comes to extreme importance amid the mounting pressure on the AEC industry players to deliver economic, environmentally friendly, and socially considerate structures. Despite the promising potentials, the utilization of AI, particularly reinforced learning (RL), to support multidisciplinary design endeavours in the AEC industry is still in its infancy. Thus, the present research discusses developing and applying a Markov Decision Process (MDP) model, an RL application, to assist the preliminary multidisciplinary design efforts in the AEC industry. The experimental work shows that MDP models can expedite identifying viable design alternatives within the solutions space in multidisciplinary design while maximizing the likelihood of finding the optimal design.

Municipal drainage systems play a key role in public health and are considered one of the main components of every modern city’s infrastructure. However, as a drainage system ages, its pipes gradually deteriorate at rates that vary based on the conditions of utilization. To prevent unexpected failures, municipalities have adopted a proactive approach that relies on regular condition assessments of their assets. At this juncture, a question that needs to be answered is how these assessment data can be used to optimize the frequency of inspections of the drainage pipes. In fact, when the assessment information is used in conjunction with deterioration models, city managers are able to develop data-driven maintenance, rehabilitation, and replacement plans based on the current condition of the assets and their risk of failure. As a result, understanding the rate at which defects evolve over time provides valuable information in terms of understanding the relationship between the various factors affecting defect development and pipe deterioration. This research presents an image registration framework for extracting crack development information from closed-circuit television (CCTV) videos of sewer pipes. Image processing techniques are used to estimate the relative change for a given defect from images taken at two different times. Because the parameters of cameras (e.g., model, location, angle of view) are generally not expected to be identical for consecutive inspection campaigns, the images to be compared were first scaled using a technique referred to as the area scaler (AS) to ensure all images have the same frame of reference. This scaling procedure is illustrated in a case study, containing 49 pairs of images that led to a relative error (with respect to the mean) generally not exceeding 5% when frames of the same defects contained a sufficient number of matching points.

In northern Canada, due to the harsh weather and high labor cost, contractors prefer to using modular construction approach to complete heavy industrial projects, where mobile crane are used for onsite module installations. In current practice, module lifts are often planned manually by rigging engineers. With a large number of heavy lifts to be analyzed per project, the planning process is tedious and error prone. This paper represents a data-driven crane management system with three features: (1) identification of design errors in lifting planning; (2) responses to design changes; and (3) dynamic 3D trajectory-based lifting visualization. It covers two types of crane operations: pick from a fixed location, and pick and walking operation. This developed system helps reduce lifting time and improves safety and quality, where various lifting scenarios need to be analyzed. The system has been implemented at a collaborator company for demonstration and validation.

Purpose Researchers have not widely explored design-based factors that govern buildings’ physical properties and human–building interactions. This paper aims to understand the influence of design-related factors on the time-on-market (TOM) of listed houses and, consequently, study the effect of design features on the desirability of a given house. Design/methodology/approach This research analyzes a dataset of listed houses, provided by the REALTORS® Association of Edmonton (RAE) and covers a period extending from January 2009 to August 2019, using Cox proportional-hazards regression model to identify building features that influence people purchasing decisions. Findings The research findings affirm the statistical insignificance of the price on the TOM compared to other design features, such as the construction method, the installed mechanical systems and cladding materials. Research limitations/implications The data used in the analysis comes from a single North American region, i.e. Edmonton, Alberta, Canada. Also, the data provided by the RAE includes only records that involve a realtor. Practical implications The observations of the research presented in this paper influence the housing market players’ decisions about housing designs, mainly those concerned with building new residential dwellings such as speculative builders and designers. Originality/value The research novelty stems from two aspects: the medium used for analysis, i.e. Cox proportional-hazards regression model, which allows considering the listed-but-not-sold units and helps to eliminate the survivorship bias that leads to over-optimistic outcomes; and the assessment of design-related features which allows to understand people’s preferences in design alternatives.

The modular construction approach relies heavily on mobile cranes. With the increase in weight of modules, the ground bearing pressure (GBP) applied by the hydraulic crane also increases. To avoid ground failure, the primary technique is to determine the GBP by calculating the resulting force at each outrigger and assuming it is distributed uniformly over the surface area of the mat under the outrigger. Finite element analysis (FEA) indicates that the pressure profile beneath the crane mat is not uniform in nature, which means the traditional method of calculating the GBP is inaccurate. In this study, a new method is proposed to determine the GBP profile. The proposed methodology can determine the GBP at 16 points, the four corners of each of the four outriggers. For a theoretical case study, a hydraulic crane Grove GMK 7550 with three different payloads is examined and the results are verified by using FEA.

The research in value-oriented design reports the importance of displaying the interdependencies between product components and stakeholders’ values, where it argues that the display of interdependencies is indispensable for the optimal decision-making and for the success of the value-oriented design. However, applications for value visualization in the construction industry lack one or both of the following: (1) the support for multi-value assessment and visualization and (2) the ability to visualize value(s) over time. These two shortcomings hinder the construction industry from fully embracing sustainable value-oriented design. Hence, this paper proposes a visualization framework to bridge the gap in the practice of value visualization regarding (i) the number of visualized values and (ii) time-based multiple-value visualization. The paper also contains a case study that utilizes a condominium building to show the implementation of the proposed framework and demonstrate how results can be interpreted and utilized in the design process.

Researchers have been extensively exploring the employment of generative systems to support design practices in the architecture, engineering and construction industry since the 1970s. More than half a century passed since the first architecture, engineering and construction industry’s generative systems were developed; researchers have achieved remarkable leaps backed by advances in computing power and algorithms’ capacity. In this article, we present a systematic analysis of the literature published between 2009 and 2019 on the utilization of generative systems in the design practices of the architecture, engineering and construction industry. The present research studies present trends, collaborations and applications of generative systems in the architecture, engineering and construction industry in order to identify existing shortcomings and potential advancements that balance the need for theory development and practical application. It provides insightful observations that are translated into meaningful recommendations for future research necessary to progress the incorporation of generative systems into the design practices of the architecture, engineering and construction industry.

Purpose The purpose of this paper is to develop a clear understanding of the features that increase the probability of condos’ sale, with a focus on design-related features. Design/methodology/approach The present research uses survival analysis (SA) and the Cox proportional-hazards regression (CPHR) to analyze condo sales data provided by the REALTORS® Association of Edmonton (RAE) (Alberta, Canada). Findings The analysis of the provided data shows that the listed price, building age, appliances and condo fees have less effect on the time a condo spends on the market compared to the condo’s physical features, such as construction material, interior finishing and heating type and source. Research limitations/implications The data used in the present research comes from one geographical area (i.e. Edmonton, Canada). Furthermore, the data provided by the RAE does not include any real estate transactions not involving a realtor. Additionally, the present research, owing to its focus on design-related features, does not control features related to the external environment, such as community and transportation proximity. Practical implications The findings of the present research help construction practitioners (e.g. architects, builders and realtors) better understand the features that influence condo buyers’ decisions. This knowledge helps to develop designs and marketing strategies that increase the likelihood of selling and decrease the time listed condos spend on the market. Originality/value The present research expands our knowledge of the drivers influencing the purchasers’ decisions concerning the building’s physical features that can be controlled during the design stage. Also, analyzing the provided data by using SA and CPHR, as followed in this paper, facilitates the inclusion of records that are listed but not sold, which helps to overcome the survivorship bias and avoid the over-optimism that exists in the present literature.

As indicated by several researchers, the objective assessment of design prior to commencing construction is essential for achieving sustainability requirements and improving the competitiveness of the construction company. This process is far from being a simple task, as it requires a detailed evaluation of a plethora of options that designers may not have time to do. To help designers evaluating the excessive number of possible design combinations they encounter, this paper explores the application of reinforced learning (RL) to develop a model that assist designers in their pursuit of the optimal design. The present research utilizes the Markov Decision Process (MDP) as an application of RL and multi-attribute utility to solve the problem of the objective assessment of the design. The paper also presents a case study that demonstrates the utilization of the developed model to optimize the design of a single-family house.

Modular projects in the construction industry employ high-capacity crawler cranes. Due to the significant increase in the weights of modules in recent years, ensuring the integrity of groun...

PurposeThe purpose of this paper is to use the concepts of the multi-attribute utility theory to develop a model to evaluate the design of low-density residential units to increase the profit of the company from a certain design, by assessing the changes in the market shares as a result of the built unit’s attributes.Design/methodology/approachThe proposed platform consists of two stages: Stage I or relational model development and Stage II or design evaluation. Stage I is concerned with developing a mathematical model that links design variables (e.g. the R-Value of the building envelope and construction material) with the assessment attributes (e.g. price and carbon emissions). Stage II ensures the fulfillment of the corporation’s goals in maximizing profit and market shares using multi-attribute utility theory.FindingsThe application of the proposed model on a case study – a single-family house – shows that reducing the selling price of the unit is not always the best marketing strategy builders should pursue to increase their sales and accordingly their profit, as accounting for other attributes (e.g. performance, operational cost and environmental impact) leads to larger changes in the market shares and accordingly in profit.Research limitations/implicationsThe limitations of this research are manifested in the following points: it does not account for the impact of the marketing campaigns on the market shares; it considers the profit as a percentage of the construction cost; and it has not been validated on high-density residential buildings.Practical implicationsThis research provides speculative builders with a platform that allows the objective evaluation of houses’ designs prior to introducing them to the market so builders can increase their market shares and consequently their profit. The proposed platform also contributes to increasing the sustainable performance of the housing industry, as it allows for the assessment of the design against economic, environmental and social attributes concurrently, which ensures a balanced consideration of the built houses on sustainability pillars.Social implicationsThe proposed platform for design evaluation extends the assessment attributes beyond the traditionally considered economic and environmental attributes. By doing so, it assists decision-makers in evaluating the potential social influence of the proposed design and, as a result, reduces the unwanted impact.Originality/valueThis research combines the concepts of multi-attribute utility with market studies to develop an objective decision support tool for evaluating the design of speculative houses to increase the sustainable performance of the builders without compromising on their profit.

Population ageing is stimulating an increase in the demand for housing suitable for seniors. To meet the demand, the market share of senior housing needs to increase substantially in a relatively short period of time; therefore, panelized construction, as an efficient, economical, and environmentally-friendly construction method, can be regarded as a promising building approach to meet urgent demand for multi-unit housing. However, prior to construction, decisions regarding the location selection for building panelized housing can have a great influence on the level of accessibility that seniors have to neighbouring facilities and services, further affecting their health and quality of life. Based on this, the research presented in this paper aims to search potential land areas for panelized housing developments for seniors from the perspective of accessibility. A set of methods is proposed to define the opportunities and constraints for potential land, measure the accessibility, and select the most suitable location for senior housing by means of suitability analysis. A case study of Edmonton is then analyzed to illustrate the application of these methods.

The increasing economic challenges and the environmental responsibilities the construction industry is facing necessitate reductions in the cost and environmental impact of buildings through their lifecycle without compromising the performance of building systems. In response to these challenges, this paper proposes a framework that (i) incorporates the behaviour of building systems (e.g., heating system and building envelope) to account for the interdependencies amongst the building systems, and (ii) evaluates the design of building systems in order to reduce their lifecycle cost and environmental impact. The proposed framework utilizes the failure model (i.e., the survivor function and Mean Time To Failure) of Reliability theory to model the behaviour of building systems during operations and measures the performance of these systems (i.e., assessing the time to failure) and multi-objective optimization to find the design alternative that reduces the impact of the assessment criteria and increase the performance of building systems as per the failure model. A case study is also presented in this paper in order to illustrate the application of the proposed framework during the design. The case study shows that the application of the proposed framework contributes to reducing the lifecycle negative impact of building systems on cost, fossil fuel consumption, Global Warming Potential, acidifications potentials, human health criteria, eutrophication potential, Ozon depletion potential, and smog potential, while increasing the lifespan (i.e. the selected performance measure) of the heating systems.

Service effectiveness (SEV) of bus transit indicates the impacts and quality of transit services. In any given city, not all residents enjoy the same level of accessibility to transit supply, with socially disadvantaged groups (SDGs) having more limited access. This study aims to measure the SEV of bus transit in terms of accessibility and investigate social equity in SEV among various population groups from a sustainability perspective. A systematic methodology is proposed integrating the cumulative opportunity measure and data envelopment analysis (DEA) in order to assess the accessibility-based service effectiveness (ABSEV) of bus transit, employing Lorenz curves and Gini coefficients to explore social equity in ABSEV. Using the elderly as an example of SDGs, an empirical application of Edmonton, Canada is provided. The results indicate that 18% of the total census tracts (CTs) perform effectively in ABSEV assessment of bus transit, while the remaining ineffective CTs are divided into three spatial clusters. For both seniors and the total population, Gini coefficients of ABSEV are under 0.5. The findings can provide policy makers with evidence on how to balance the ABSEV distribution of bus transit, improve benefits of bus transit to SDGs, and enhance sustainable development of urban bus transit systems.

High capacity cranes are the backbone of the heavy construction industry, which, over the last few years, has embraced modularization. Consequently, ground stability has become a critical i...

This research aims at improving the automation of the sewer pipe assessment process, specifically in terms of the development of a closed-circuit television (CCTV) video interpretation algorithm and sewer pipe video assessment (SPVA) system. A novel video interpretation algorithm for sewer pipes (VIASP) is proposed to use the labeled video (which is labeled by an automated defect detector) as the input in order to extract the useful information from the video, with the final output being the sewer pipe assessment report in textual format. To develop the VIASP, an optimization algorithm using simulated annealing (SA) is employed to determine the optimal human-defined parameters for the VIASP. A prototype of the SPVA system is developed to show how the developed automation techniques can fit into the daily workflow of sewer pipe assessment work. The effectiveness of the proposed method is validated in a case study.

Sewer pipe systems are of great importance to modern cities in various ways, making preventive maintenance a necessary activity to ensure an acceptable level of service at all times. In thi...

The construction of industrial projects involves fabricating and installing massive quantities of pipelines. The design data of pipelines is complex, usually unique for each project and not easily available to researchers and the public for confidentiality reasons. As a result, an industrial pipelines data generator able to realistically simulate pipelines structures will lessen the dependence on real-life data. This article describes an industrial pipelines data generator that was developed using topological and physical properties of pipelines from real industrial projects. This generator can simulate the properties (the type of component, length, diameter, running direction, and the connectivity relationships between components) of real industrial pipelines. Its application in construction engineering and management research, more specifically in the experimental analysis of an optimization algorithm, was described by the authors in previous work [1] . The data generator can be used to develop benchmark problem instances for optimization problems and for simulation studies of construction operations in industrial projects.

The construction industry has strived for higher productivity in the last several decades, which has resulted in innovations and improvements, including methodologies, tools, and machines. ...

Closed-circuit television (CCTV) is widely used in North America for sewer pipe inspection due to several benefits, such as easy operation and lower upfront costs. To be useful, video foota...

A vast amount of information is produced in each phase of major construction projects. However, extensive project lifespans and complex organizational relationships may contribute to signif...

Bus route networks play a pivotal role in public transit system planning, which, in turn, influences the geographical distribution and service coverage of bus transit. Although some advance...

The rapid growth of the older-adult segment of the population has a profound effect on urban development and the fulfillment of housing needs. The location of age-restricted communities tha...