Scholarly Works, Myers-Lawson School of Construction

Permanent URI for this collection

https://hdl.handle.net/10919/111114

Browse

Now showing 1 - 20 of 71

Analysis of Current BIM Execution Plans and Contract Documents to Support Automation of Clash Resolution
Harode, Ashit; Mills, Thomas; Thabet, Walid (EasyChair, 2023-04-04)
Step one of MEP coordination process identifies the clash between MEP elements followed by step two identifying their potential resolution. Clash identification has been automated using software like Navisworks yet clash resolution remains a slow and manual process. Use of Machine Learning has been explored by researchers to automate clash resolution. These researches utilize graphical information and attributes embedded into Building Information Model (BIM) elements to develop a Machine Learning model making BIMs an integral part of the automation. The literature review shows that the successful implementation of BIMs is supported by well-executed BIM Execution Plans (BxP) and Standards. Therefore, it can be said that a successful implementation of clash resolution automation will require the support of these documents. To assess the readiness of BxP to support the automation of clash resolution, the authors in this paper reviewed three BxP and Standard guides. A comparative analysis of three industry standard BxP and Standard guides was conducted to reveal the topic covered by them. Results from the review show that the BxPs and Standards are lacking to support the automation of clash resolution. Suggested potential changes to make these documents ready for the implementation of automation of clash resolution are discussed.
Digital twin in healthcare facilities: Linking real-time air quality data to BIM
Harode, Ashit; Thabet, Walid; DuLaney, Michael B. (CRC Press, 2023-03-08)
In this paper, the authors provide an overview of what are Digital Twins (DT), why DTs provide advantages to facility management (FM) practices and how can a DT be implemented. Focusing on healthcare facilities, the paper defines how a DT implementation can support two broad areas in healthcare: facility maintenance and space management. A case study of an operating room (OR) is used to illustrate the implementation of a DT prototype. Realtime sensor data is linked to an OR BIM using Azure cloud services and Microsoft Power BI. An example dashboard is created in Power BI to demonstrate various visualization tools of Power BI and its interaction with live sensor data. The authors also reflect on how the system architecture proposed in this paper can reduce the complexity of creating a DT and how standardization in DT creation can support the scalability of the discussed DT prototype.
A Proposed Systems-Centric Ontology for a Graph-Based Digital Twin
Yanamala, Akhileswar; Harode, Ashit; Thabet, Walid (European Council for Computing in Construction, 2023-07)
This research utilizes the Neo4j platform to create a graph database to represent the graphical components of a facility model and their spatial relationships. A graphbased digital twin is proposed for a 2-story facility by embedding systems-centric static data into the graph and linking it to the building’s Navisworks BIM using a python script. The outputs of this study include a new ontology for creating graph-based digital twins, implementation of the graph using Neo4j, and a python script to link the graph to the model. Linking dynamic data to the graph model is explored and discussed. This approach can improve the representation and understanding of facility systems and their interrelationships.
Feature Engineering for development of a Machine Learning Model for Clash Resolution
Harode, Ashit; Thabet, Walid; Leite, Fernanda L. (EasyChair, 2022-05-15)
To automate clash resolution tasks, it is important to capture domain knowledge for the Machine Learning (ML). One way to add domain knowledge is by training data that divides tasks into input and output variables. The selection of input variables that are most relevant to a task is an important step towards automation. In this paper, the authors detail framework that uses literature review, industry interviews, and Modified Delphi to capture domain knowledge for clash resolution. The features identified through this paper can in future be processed through Feature Selection, that can provide empirical evidence of why the selected features or set of features are important to ML algorithm. Data collection processes discussed in this paper is not finalized and is discussed to help provide readers with framework of the proposed systematic method. Factors considered when resolving clashes were identified through literature review (22 factors) and industry interviews (16 factors). 14 factors identified from the interviews had a similar matching factor in the literature reviewed, the other 2 factors were not mentioned in any publications found during the initial literature review. After comparing results from literature review and interviews, 13 factors were considered critical for automating clash resolution.
Using a Systems-Centric Knowledge Graph to support Facility Maintenance
Yanamala, Akhileswar; Harode, Ashit; Thabet, Walid (2025)
Throughout an asset's lifecycle, rates of early failure, random failure, and wear-out failure underscore the need for robust maintenance strategies, including Corrective, Preventive, and Predictive approaches. Even though the use of BIM has increased in recent years in the field of facility maintenance and management, the BIM technology is not utilized to its full potential to make the facility management more proactive and cost efficient. While existing research focused on developing systems-centric FM-Capable BIMs, there are limitations in how the data is stored and accessed. Existing research also shows that access to the right data at the right time is very crucial for proactive maintenance decision making and cost management. The literature review of recent efforts uncovered gaps in research regarding the utilization of knowledge graphs for facility management. This research presents a novel approach to represent Building Information Modeling (BIM) data as a systems-centric knowledge graph. This systems-centric knowledge graph enhances facility management by facilitating efficient queries for maintenance and emergency scenarios. To validate the utilization of knowledge graphs for systems-centric searches, authors selected a case study as a mechanical zone of an elementary school building. To create the knowledge graph of the case study, authors divided the systems in the zone into subsystems and developed small component knowledge graphs for each subsystem. Later all the component graphs were merged to create a federated knowledge graph of the selected zone. This process allowed authors to create the knowledge graph without complications and helped in quality control by eliminating any input errors. The developed knowledge graph was queried for various emergency scenarios developed based on the discussions with FM staff. The queried results were highlighted in the Navisworks 3D model to display. This research implementation offers practical implications for facility managers, emphasizing the potential for further advancements in Digital Twin development.
Work order prioritization using neural networks to improve building operation
Ensafi, Mahnaz; Thabet, Walid; Gao, Xinghau (2024-04)
Current practices for prioritizing maintenance work orders are mainly user-driven and lack consistency in collecting, processing, and managing the large amount of data. While decision-making methods have been used to address some of the existing challenges such as inconsistency, they also have challenges including variation between comparison during the actual prioritization task as opposed to those outside of maintenance context. The data analytics and machine learning methods can help with extracting meaningful and valuable information, finding patterns, and drawing conclusions from the available data. Such methods have benefits including faster prioritization performance leading to less failure and downtimes, reduced impact of knowledge loss, decreased cognitive workload, identification of errors for adjusting the system, and determination of important factors impacting work order processing to support the development of data requirements. This paper summarizes the background on existing gaps in processing maintenance work orders and provides an overview of machine learning methods to support prioritizing work order. The paper then discusses the work order data of an educational facility as a case study, presents information on data exploration and data cleaning approach, and provides insights gained from their maintenance work order data. The insights gained present challenges such as submission of multiple work orders as one, missing data for certain criteria, long durations for addressing some of the work orders, and the correlation between criteria collected by the facility and the schedule. The paper continues by implementing artificial neural networks to benefit from work order data collected for automatically prioritizing the future work orders. The results present the optimum neural network structure based on mean squared error estimated and provides the best value for each parameter used for the development of the model. The accuracy and efficiency of the developed model was validated by the facility experts of the educational facility.
Configuring BIM Models to Support a Systems-Driven Visualization Approach: A Case Study
Ensafi, Mahnaz; Harode, Ashit; Thabet, Walid (IOP Publishing, 2022)
Models developed through design and construction are not intended to support facility management. They don’t generally have the life-cycle data and information required or they are not configured to support visualization of model graphics from a system’s perspective. Current implementation for BIM-FM focuses mainly on including facility life cycle data to support space management or asset management. Models are not customized with necessary data and classification that allow for isolating and visualizing components of a specific building system (e.g. supply air). This is necessary in an emergency situation to allow facility staff diagnose the problem associated with the system and its components, identify the problem and make necessary and informed action. In this paper, we discuss requirements for preparing an as-built BIM model to be systems-centric using a case study approach of a two-story science building. A system classification hierarchy was developed to classify the systems and sub-systems of the building. Sixteen systems-centric properties were also defined to search, filter, isolate, and display elements in a specific system or sub-system. The configured systems-centric model will also help facility managers understand the dependencies across different systems to accurately determine impacts across the facility and develop strategies to rapidly respond to any emergency. The case study focused on the mechanical and plumbing systems only. Several example emergencies are discussed and presented.
Investigation of work order processing in different facilities: a questionnaire-based survey
Ensafi, Mahnaz; Thabet, Walid; Besiktepe, Deniz (Emerald, 2024-01-30)
Purpose: The aim of this paper was to study current practices in FM work order processing to support and improve decision-making. Processing and prioritizing work orders constitute a critical part of facilities and maintenance management practices given the large amount of work orders submitted daily. User-driven approaches (UDAs) are currently more prevalent for processing and prioritizing work orders but have challenges including inconsistency and subjectivity. Data-driven approaches can provide an advantage over user-driven ones in work-order processing; however, specific data requirements need to be identified to collect and process the functional data needed while achieving more consistent and accurate results. Design/methodology/approach: This paper presents the findings of an online survey conducted with facility management (FM) experts who are directly or indirectly involved in processing work orders in building maintenance. Findings: The findings reflect the current practices of 71 survey participants on data requirements, criteria selection, rankings, with current shortcomings and challenges in prioritizing work orders. In addition, differences between criteria and their ranking within participants’ experience, facility types and facility sizes are investigated. The findings of the study provide a snapshot of the current practices in FM work order processing, which aids in developing a comprehensive framework to support data-driven decision-making and address the challenges with UDAs. Originality/value: Although previous studies have explored the use of selected criteria for processing and prioritizing work orders, this paper investigated a comprehensive list of criteria used by various facilities for processing work orders. Furthermore, previous studies are focused on the processing and prioritization stage, whereas this paper explored the data collected following the completion of the maintenance tasks and the benefits it can provide for processing future work orders. In addition, previous studies have focused on one specific stage of work order processing, whereas this paper investigated the common data between different stages of work order processing for enhanced FM.
Formulation of Feature and Label Space Using Modified Delphi in Support of Developing a Machine-Learning Algorithm to Automate Clash Resolution
Harode, Ashit; Thabet, Walid; Leite, Fernanda (ASCE, 2023-12-30)
To improve the current manual and iterative nature of clash resolution on construction projects, current research efforts continue to explore and test the utilization of machine-learning algorithms to automate the process. Though current research shows significant accuracy in automating clash resolution, many have failed to provide clear explanation and justification for the selection of their feature and label space. Since this is critical in developing an effective and explainable solution in machine learning, it is crucial to address this research gap. In this paper, the authors utilize an in-depth literature review and industry interviews to capture domain knowledge on how design clashes are resolved by industry experts. From analysis of the knowledge captured, we identified 23 factors considered by experts when resolving clashes and five alternative solutions/options to resolve a clash. Using a pool of industry experts, a modified Delphi approach was conducted to validate the factors and options and to determine a priority ranking. The authors identified 94 industry experts based on a predetermined qualification matrix to take part in the modified Delphi. Twelve participants responded and took part in the first round, and 11 completed the second round. A consensus was reached on all clash factors and resolution options. Factors including "clashing elements type,""constrained slope,""critical element in the clash,""location of the clash,""code compliance,"and "project stage clashing element is in"were ranked as the most important factors, while "clashing element material"and "insulation type"were considered the least important. Participants also showed more preference to the "moving the clashing element with low priority in/along x-y-z directions"option to resolve clashes. These identified factors and options will be utilized to collect specific clash data to train and test effective and explainable machine-learning algorithms toward automating clash resolution.
Developing a Machine-Learning Model to Predict Clash Resolution Options
Harode, Ashit; Thabet, Walid; Gao, Xinghua (ASCE, 2024-01-10)
Even with the utilization of software tools like Navisworks to automate clash detection, clash resolution in construction projects remains a slow and manual process. The reason is the meticulous nature of the process where coordinators need to ensure that resolving one clash does not lead to new clashes. The use of machine learning to automate clash resolution as a potential option to improve the clash resolution process has been suggested with research showing positive results to support the implementation. While the research shows high accuracy in predicting clash resolution options to support automation, the scope limits the discussion on the complex and often lengthy process of developing a machine-learning model. Based on this research gap, the authors in this paper discuss the development of a prediction model to identify clash resolution options for given clashes. The discussion is focused on individual steps involved in creating machine-learning models like data collection, data preprocessing, and machine-learning algorithm development and selection. The authors also address common challenges in the development of machine-learning models including class imbalance and availability of limited data. The authors utilize a multilabel synthetic oversampling method to generate different percentages of synthetic data to account for class imbalance and limited data sets. Using this data set, the authors trained five machine-learning algorithms and reported on their accuracy. The authors concluded that increasing the data set with 20% synthetic data, and using an artificial neural network to develop the machine-learning model to automate the resolution of clashes have generated better results with an average accuracy of around 80%.
Extracting BIM data to support a machine learning model for automated clash resolution
Harode, Ashit; Thabet, Walid (EasyChair, 2023-12-11)
Clash resolution is considered a critical step to resolve issues among the different disciplines for a construction design to be realized as expected. This step, however, continues to remain slow and manual which can significantly delay a project and drive-up costs. A combined machine learning model was proposed by Harode and Thabet (2021) to automate the clash resolution process. A large amount of labeled dataset is required to train and test the proposed model. The dataset is planned to be extracted from various industry-provided federated construction BIMs. Federated construction models are created from multiple subcontractor component models authored using different software. As a result, data is stored in various formats using different data structures making the extraction process difficult. In this paper, the authors demonstrate the use of commercially available software tools including iConstruct, Dynamo, and Talend to overcome this limitation and extract the necessary data. The paper first defines the required data structure followed by a data extraction process to capture required data from clashing elements in the federated BIMs. The paper also discusses a novel method of extracting end point coordinates and moveable area for clashing elements using bounding boxes. The paper concludes with future research directions.
Challenges and gaps with user-led decision-making for prioritizing maintenance work orders
Ensafi, Mahnaz; Thabet, Walid; Afsari, Kereshmeh; Yang, Eunhwa (Elsevier, 2023-05-01)
A vast amount of work orders is submitted daily which is a critical component of management for any facility. The process taken for prioritizing work orders, however, shows a high dependency on the extent of knowledge and experience of responsible staff available and is challenged by inconsistency in data collection, and uncertainty in decision-making. Making decisions and responding to a high number of requests demand intensive labor hours resulting in delays causing issues for facility managers. The high number of service requests, various work orders, and the required balance between cost and budget highlight the importance of the need for improving work order processing to optimize time and cost of buildings' operation. Through review of the literature, unstructured and semi-structured interviews, and a qualitative analysis approach, this paper identifies various challenges and gaps in user-driven decision-making for processing work orders and determines best practices. The challenges identified include inconsistency in prioritizing orders, lack of data requirements and knowledge management, cognitive workload and biases, and inconsistency in data collection. Using data-driven decision-making methods can address existing challenges, improve the process of prioritizing work orders and enhance the quality of the work performed by timely responding to submitted requests. This will improve the operation and maintenance of building facilities and increase occupants’ satisfaction.
Learning from Experience: A Faculty-Led Collaborative Inquiry Exploring Embedded Communication Skills Across Engineering Curricula
Biviano, Angelo; Branscome, Caroline; Burgoyne, Christine Bala; Carper, Kathleen; Iorio, Josh; Scarff, Kelly; Taylor, Ashley R.; Arena, Sara (ASEE Conferences, 2024-06-23)
This evidence-based practice paper describes a collaborative inquiry process to explore a critical question for engineering faculty: what are practical strategies for leveraging evidence-based practices to embed communication skills across core engineering curricula? Within engineering education, there is a growing consensus that communication skills are essential for engineering graduates. For example, the Accreditation Board for Engineering and Technology (ABET) distinctly highlights communication skills as a required student learning outcome for accreditation of engineering programs in ABET Criterion 3.3.: an ability to communicate effectively with a range of audiences. Numerous studies exploring engineers’ school-to-work transition suggest that communication is one of the most important skill sets for engineering practice according to both recent graduates (Passow, 2012) and industry (Male et. al, 2010). As the Engineer of 2020 Report concisely noted, “good engineering will require good communication” (National Academy of Engineering, 2004, p. 56). Despite the engineering education community’s shared vision for ensuring engineering graduates can communicate effectively, few practical examples exist to illuminate how faculty can leverage evidence-based practices to integrate communication skills into their existing technical curricula. Therefore, the purpose of this paper is to share seven practical case-based examples of strategies implemented in a spectrum of engineering disciplines and learning environments to support faculty in integrating communication skills into existing engineering curriculum. We first describe our collaborative inquiry process to create a “systematic structure for learning from experience” (Yorks & Kasl, 2002, p. 3). Our learning from experience is rooted in the reflections of faculty representing seven engineering departments who teach communication skills across a diverse range of engineering curricular contexts (e.g., course size, course level, technical subject, etc.) Next, we provide seven case studies of evidence-based strategies-in-action across this range of learning contexts, including both undergraduate and graduate education. For example, one case study discusses the integration of a community-focused debate project in a mining engineering undergraduate course to build students’ communications skills in rhetorical situation analysis while another study in a construction engineering management department attends to aspects of diversity and inclusion by promoting a writing process that begins with visual design. These case studies provide rich context for the learning environment and the implementation of the evidence-based practice, with the ultimate goal of supporting faculty in drawing connections to their own teaching strategies. Finally, we conclude by situating the case studies in the broader engineering education literature and sharing reflections for lessons learned on integration of communication instruction across existing engineering curricula.
Interdisciplinary Perspectives on Green Infrastructure: A Systematic Exploration of Definitions and Their Origins
Adesoji, Tolulope; Pearce, Annie R. (MDPI, 2024-01-02)
Green Infrastructure (GI) is rooted in ecology and cuts across multiple disciplines, including landscape architecture, environmental sciences, planning, policy, and engineering. Likewise, the definition of this concept also cuts across disciplines, which creates ambiguity around what GI is and what makes up GI in practice—for example, mistaking bioswales for regular tree planters or green space within communities in which they are installed. We undertook a systematic literature review of 38 peer-reviewed articles for this study using the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) method to identify and synthesize the different disciplinary definitions of GI in the literature. This study also presents the types of GI systems mentioned in the peer-reviewed articles while identifying other benefits apart from the primary benefit of GI installation, which is stormwater management. The analysis revealed three clusters of GI definitions: (I) Interconnected natural areas and other open spaces, (II) Strategically planned natural and semi-natural areas, and (III) Decentralized systems and techniques. However, we got rid of the third cluster during the analysis because GI is known to be a decentralized system, and the definition region could not be tracked. These clusters represent a spectrum, one of which employs the structure of natural systems already in place to support human goals (bio-inclusivity). The other includes living systems as components within engineered solutions to achieve objectives (bio-integration). This review points to the need for an encompassing definition that cuts across disciplines with a consensus on the adoption and concise categorization of GI types and the multiple benefits they provide to humans and ecosystems. A consensus definition helps clear misconceptions and improve the understanding of GI, potentially improving receptivity towards these solutions within communities from a community member perspective.
Construction inspection & monitoring with quadruped robots in future human-robot teaming: A preliminary study
Halder, Srijeet; Afsari, Kereshmeh; Chiou, Erin; Patrick, Rafael; Hamed, Kaveh Akbari (Elsevier, 2023-04-15)
Construction inspection and monitoring are key activities in construction projects. Automation of inspection tasks can address existing limitations and inefficiencies of the manual process to enable systematic and consistent construction inspection. However, there is a lack of an in-depth understanding of the process of construction inspection and monitoring and the tasks and sequences involved to provide the basis for task delegation in a human-technology partnership. The purpose of this research is to study the conventional process of inspection and monitoring of construction work currently implemented in construction projects and to develop an alternative process using a quadruped robot as an inspector assistant to overcome the limitations of the conventional process. This paper explores the use of quadruped robots for construction inspection and monitoring with an emphasis on a human-robot teaming approach. Technical development and testing of the robotic technology are not in the scope of this study. The results indicate how inspector assistant quadruped robots can enable a human-technology partnership in future construction inspection and monitoring tasks. The research was conducted through on-site experiments and observations of inspectors during construction inspection and monitoring followed by a semi-structured interview to develop a process map of the conventional construction inspection and monitoring process. The study also includes on-site robot training and experiments with the inspectors to develop an alternative process map to depict future construction inspection and monitoring work with the use of an inspector assistant quadruped robot. Both the conventional and alternative process maps were validated through interview surveys with industry experts against four criteria including, completeness, accuracy, generalizability, and comprehensibility. The findings suggest that the developed process maps reflect existing and future construction inspection and monitoring work.
Perceived benefits, barriers, perceptions, and readiness to use exoskeletons in the construction industry: Differences by demographic characteristics
Gutierrez, Nancy; Ojelade, Aanuoluwapo; Kim, Sunwook; Barr, Alan; Akanmu, Abiola; Nussbaum, Maury A.; Harris-Adamson, Carisa (Elsevier, 2023-12-21)
Exoskeletons (EXOs) are a promising wearable intervention to reduce work-related musculoskeletal disorder risks among construction workers. However, the adoption of EXOs may differ with demographic characteristics. Survey data (n = 361) were collected from construction industry stakeholders and a summation score method was used to summarize respondent's benefits and barriers to EXO use, along with perceptions and readiness to use. Responses were stratified by race (White vs. non-White), sex (male vs. female), and age (<47 years vs. ≥47 years). Both a higher Benefits score and a higher Perceptions score were significantly and positively associated with a higher Readiness to Use score. There were also significant differences in perceived barriers to EXO use by race and sex. These results demonstrate substantial interest in EXO use but also emphasize the need to ensure proportionate access to the potential benefits of EXO technology.
Immersive Cross-platform X3D Training: Elevating Construction Safety Education
Roofigari-Esfahan, Nazila; Polys, Nicholas F.; Johnson, Ashley; Ogle, J. Todd; Sandbrook, Ben (ACM, 2023-10-09)
A multi-platform Virtual Reality (VR) approach is proposed to complement the traditional approaches for construction safety training. Visual simulations of a highway construction project were developed and presented through the developed platforms, aiming at giving students immersive experience of actual construction environments. The simulated worksite scenarios included active traffic, multiple worker roles and heavy equipment, and was rendered at different times of day and weather conditions. We used this material in an undergraduate class activity with 50 students. During a session in our visualization lab, students experienced the scenarios presenting day shift, afternoon shift with adverse weather and night shift and were asked to develop daily report of their job site observation. The scenrios were presented via the following platforms: TV projection, Mobile Phone, Head-Mounted Display (HMD), and CAVE projection room. The results demonstrates that the multi-platform immersive experience has the potential to significantly improve hazard recognition skill of construction students.
Developing Supplemental Instructional Videos for Construction Management Education
Barnes, Andrew F.; McCoy, Andrew P.; Warnick, Quinn (MDPI, 2023-09-28)
Technological advancements and lower production costs since the mid-1990s have dramatically improved opportunities for instructors to tailor self-made instructional videos for their students. However, video production technology has outpaced the development of educational theory, causing instructional videos to consistently fall short of their pedagogical potential. Responding to these shortcomings, scholars from various backgrounds have started publishing guidelines to help practitioners as they develop instructional videos for their respective fields. Using a rapid literature review, this article contributes to this ongoing effort by synthesizing theory-based, best-practice guidelines for a specific subcategory of educational videos called supplemental instructional videos (SIVs). SIVs are different from other types of instructional videos in that they are used to support and magnify other learning methods, mediums, and materials rather than substitute for them. Bringing the best-practice guidelines synthesized in this paper immediately into application, they were used to inform the production of SIVs for an undergraduate course that was held in the Building Construction Department of a major public university in the United States during the Spring 2020 semester. The methods used in the production of the SIV guidelines were systematically documented during the course for future researchers and practitioners to learn and build from.
Risk Analysis in Implementing Building Energy Performance Projects: Hybrid DANP-VIKOR Model Analysis — A Case Study in Iran
Naderi, Hossein; Heydari, Mohammad Hossein; Parchami Jalal, Majid (MDPI, 2023-08-14)
Building energy performance contracts have emerged as a highly effective strategy for reducing energy consumption in both developed and developing markets. These projects inherently involve risks, and a comprehensive risk analysis can greatly enhance their successful implementation, especially in emerging markets. This research aims to analyze risks associated with building energy performance projects, considering their interrelationships, prioritization, and the ranking of optimal project types based on the analyzed risks. Given its position as the largest electrical energy consumer in the Middle East and its status as an emerging market, Iran was selected as the case study for conducting the risk analysis. Thirteen risk factors were classified into four distinct risk groups, and their relationships and priority weights were determined using a hybrid DANP approach. Subsequently, the VIKOR method was employed to rank the most-advantageous project types based on their risk priorities. The findings of this research identified project lifecycle risks as the highest-priority risks, while external risks were determined to be the most-influential among all identified risks. Moreover, the implementation of packaged public projects was identified as the most-favorable alternative for promoting building energy performance projects in Iran and similar emerging markets. By providing a comprehensive understanding of risks, this study offers valuable insights that can aid emerging and developing markets in successfully implementing energy performance projects and improving overall energy efficiency.
Unmanned Aerial Systems and Deep Learning for Safety and Health Activity Monitoring on Construction Sites
Akinsemoyin, Aliu; Awolusi, Ibukun; Chakraborty, Debaditya; Al-Bayati, Ahmed Jalil; Akanmu, Abiola (MDPI, 2023-07-26)
Construction is a highly hazardous industry typified by several complex features in dynamic work environments that have the possibility of causing harm or ill health to construction workers. The constant monitoring of workers’ unsafe behaviors and work conditions is considered not only a proactive but also an active method of removing safety and health hazards and preventing potential accidents on construction sites. The integration of sensor technologies and artificial intelligence for computer vision can be used to create a robust management strategy and enhance the analysis of safety and health data needed to generate insights and take action to protect workers on construction sites. This study presents the development and validation of a framework that implements the use of unmanned aerial systems (UASs) and deep learning (DL) for the collection and analysis of safety activity metrics for improving construction safety performance. The developed framework was validated using a pilot case study. Digital images of construction safety activities were collected on active construction sites using a UAS, and the performance of two different object detection deep-learning algorithms/models (Faster R-CNN and YOLOv3) for safety hardhat detection were compared. The dataset included 7041 preprocessed and augmented images with a 75/25 training and testing split. From the case study results, Faster R-CNN showed a higher precision of 93.1% than YOLOv3 (89.8%). The findings of this study show the impact and potential benefits of using UASs and DL in computer vision applications for managing safety and health on construction sites.

Browse

Recent Submissions