Browsing by Department "Construction Science"

Now showing 1 - 8 of 8

A Natural Language based Data Retrieval Engine for Automated Digital Data Extraction for Civil Infrastructure Projects
Construction Science; TAMU; https://hdl.handle.net/20.500.14641/675; National Science Foundation
This research project will create new knowledge and resources to significantly enhance the reusability of digital data during the lifecycle of civil infrastructure assets. The rapid development of digital technologies is transforming how civil infrastructure asset data and information is produced, exchanged, and managed throughout its life cycle. Despite growing digital data availability, such data cannot be fully exploited without the ability to infer meaning from the varying data terminologies entered by practitioners. The lack of common understanding of the same data, or similar data given in different terms, preclude data exchange or can lead to extraction of the wrong data and misinterpretation. This research project will leverage the advancements in linguistics and computer science to develop a novel approach that can recognize users' intention from their natural language input and automatically extract the desired data from heterogeneous datasets. The results of this research will benefit the construction industry by accelerating the industry's transition to digital data-based project delivery and asset management. The research will also broaden engineering education by creating advanced course materials both at undergraduate and graduate levels. Diversity in data terminology creates an important hurdle for computer-to-computer communication, creating a big burden to end users who must perform the role of middleware in digital data exchange. This issue exists throughout the life cycle of a civil infrastructure asset. This project will develop a computational theory and a platform for its implementation to analyze users' plain English data requirements, and automatically match their intention to the data entities in heterogeneous source datasets based on semantic equivalence. To accomplish this goal, the research team will: a) utilize Natural Language Processing and machine learning techniques to recognize user's intention from their natural language queries, b) translate text-based domain knowledge into an extensive civil engineering machine-readable dictionary that defines meanings of technical terms using a text-based automated ontology learning method, c) design an algorithm that finds the most semantic-relevant data entities in digital data sets for a given keyword input, and d) test the performance of the algorithm in terms of its accuracy using civil infrastructure text documents such as technical specifications, design manuals, and guidelines. The research outcomes will provide fundamental tools and resources for other researchers and industry professionals for various text-mining and intelligence-inference systems. It will facilitate seamless data exchange between various proprietary software applications used during the life cycle of civil infrastructure assets, including applications involving design evaluation and selection, digital model construction, and regulation compliance checking.
Collaborative Proposal: FW-HTF-P: Anthropocentric Robot Collaboration in Construction
Construction Science; TAMU; https://hdl.handle.net/20.500.14641/529; National Science Foundation
Labor-intensive construction accounts for a significant portion of the U.S. economy. However, construction suffers from significant occupational injuries/deaths, stagnant productivity, a lack of skilled laborers, and an aging workforce. As one means to address these issues, the construction industry is gradually adopting robotic automation, particularly in human-robot collaboration where humans and robots work together in unstructured and dynamic construction environments. Despite recent advancement of the functionality and capability of robots, many fundamental questions in human-robot collaboration remain unanswered. These include: 1. How can a robot work with a human worker, and build and maintain trust when they work together in the same space? 2. What are the best strategies to design future construction tasks and work environments for such human-robot collaboration? 3. How can the construction industry retrain existing workers and attract new ones in this new and unprecedented working environment? To answer these questions, this project carries out a human-centered investigation where a human worker's response to different scenarios of human-robot collaboration in construction is non-invasively and continuously monitored in order to maximize the overall performance of human-robot collaboration. The outcome of the investigation has the potential to build foundational knowledge on how we can prepare our existing and new workforce for future construction. Researchers have identified three major open research areas in human-robot construction. First is the in-depth understanding of human's physical, cognitive and emotional response in human-robot collaboration, a critical knowledge in allowing a robot's adaptable behaviors to be calibrated to a human response. Second is to explore how to redesign construction tasks, operations, and job sites to better serve human-robot collaboration. Studying such designs could involve a significant number of tests in the real world which may be impractical or infeasible, thus innovative testing technologies and methods are needed. Third involves strategies for training new and existing workers for future human-robot collaborative construction. In this project, researchers will test the feasibility of the three following research activities in the context of the above research areas: 1) testing wearable biosensors to non-invasively and continuously measure a human worker's emotional response in human-robot collaboration; 2) investigating the feasibility of virtual reality as an alternative to certain real construction tests for redesigning tasks and job sites for human-robot collaboration; and 3) organizing two workshops to collect broad perspectives from different stakeholders and experts to refine research thrusts for future human-robot collaboration in construction. The ultimate goal of this project is to develop the necessary research personnel, research infrastructure, and foundational work to expand the opportunities for studying future technology, future workers, and future work at the level of a FW-HTF full research proposal. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
Collaborative Research: Transforming Teaching of Structural Analysis through Mobile Augmented Reality
Construction Science; TAMU; https://hdl.handle.net/20.500.14641/539; National Science Foundation
Structural Analysis is an introductory core course that is taught in almost all civil engineering, architectural engineering, and construction undergraduate programs across the U.S. Previous research unveils students' deficits in understanding the behavior of structural elements in a three-dimensional (3D) context due to the shortcomings of traditional lecturing approaches. In particular, such approaches often put too much emphasis on the analysis of individual structural members, thereby falling short in providing a solid, easy-to-follow, and holistic approach to comprehending and analyzing complex structures with a large number of interconnected elements. This research is transforming existing teaching pedagogy in structural analysis and filling a major gap in how structural engineering is currently taught to the nation's future workforce in U.S. institutions. In this project, mobile augmented reality (AR) is used to superimpose views of the real world with computer generated 3D models of structures under load. In doing so, the potential of AR for improving learning and increasing student engagement in the learning process is being systematically assessed. Building upon theoretical perspectives on how people learn, this project is also examining if pedagogy involving AR creates an effective learning environment for students, as well as if it enhances adaptive flexibility, which is deemed to be essential to be a successful engineer in the 21st Century. The broader impacts of this project extend beyond its confines through outreach activities such as integrating AR technology into lower-level engineering courses that aim to increase the number of ethnically-diverse students pursuing STEM degrees. The learning modules integrating AR into teaching of structural analysis will be made available online. A website and online repository are to include specific details about the learning objectives, implementation procedures, and instructor reflections on things to consider while implementing the teaching techniques. The developed software components and 3D models will be open source.
I-Corps: Artificial Intelligence-Driven Disaster Risk Prediction and Assessment
Construction Science; TAMU; https://hdl.handle.net/20.500.14641/233; National Science Foundation
The broader impact/commercial potential of this I-Corps project is the development of a rapid and automated scene understanding technology to intelligently evaluate existing conditions of vulnerability and assess potential disaster risks more proactively and effectively. This technology may help make informed decisions regarding steps to reduce the impacts of disasters. Developing and implementing the technology to reduce disaster risk requires identifying and assessing the sources of potential risk effectively, but a lack of a rapid and automated tools makes practitioners rely on manual inspection. The proposed innovation is to make the current disaster risk assessment process more intelligent and efficient by reducing time-consuming and labor-intensive manual inspection. If the project is completed successfully, the proposed innovation will enhance scientific and technological understanding of rapid and automated visual sensing and analytics for disaster risk prediction and assessment. This I-Corps project is based on the development of the integrated analysis of low-level image features together with high-level semantic models, which enables robust scene understanding and risk prediction in complex environments. By leveraging large-scale data from multimodal visual sensors (e.g., drones, security cameras, etc.), the technology automatically encodes the context of potential disaster risk into machine vision algorithms to identify the elements at risk on video recordings and assess the degree of vulnerability and the elements at risk in complex environments. The system generates site-specific managerial information in an automated manner, which may enhance risk-informed decision-making for disaster mitigation and preparedness, thereby reducing both the level of risk and the impacts of disasters effectively. The proposed innovation may also provide the foundation for further vision-based reasoning for disaster management. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria
I-Corps: Artificial Intelligence-Driven Disaster Risk Prediction and Assessment
Construction Science; TAMU; https://hdl.handle.net/20.500.14641/233; National Science Foundation
The broader impact/commercial potential of this I-Corps project is the development of a rapid and automated scene understanding technology to intelligently evaluate existing conditions of vulnerability and assess potential disaster risks more proactively and effectively. This technology may help make informed decisions regarding steps to reduce the impacts of disasters. Developing and implementing the technology to reduce disaster risk requires identifying and assessing the sources of potential risk effectively, but a lack of a rapid and automated tools makes practitioners rely on manual inspection. The proposed innovation is to make the current disaster risk assessment process more intelligent and efficient by reducing time-consuming and labor-intensive manual inspection. If the project is completed successfully, the proposed innovation will enhance scientific and technological understanding of rapid and automated visual sensing and analytics for disaster risk prediction and assessment. This I-Corps project is based on the development of the integrated analysis of low-level image features together with high-level semantic models, which enables robust scene understanding and risk prediction in complex environments. By leveraging large-scale data from multimodal visual sensors (e.g., drones, security cameras, etc.), the technology automatically encodes the context of potential disaster risk into machine vision algorithms to identify the elements at risk on video recordings and assess the degree of vulnerability and the elements at risk in complex environments. The system generates site-specific managerial information in an automated manner, which may enhance risk-informed decision-making for disaster mitigation and preparedness, thereby reducing both the level of risk and the impacts of disasters effectively. The proposed innovation may also provide the foundation for further vision-based reasoning for disaster management. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
Real-time feedback-enabled simulation modeling of dynamic construction processes (ongoing)
Construction Science; TAMU; https://hdl.handle.net/20.500.14641/539; National Science Foundation
According to the U.S. Census Bureau, in 2015, the U.S. construction industry will surpass $1 Trillion Dollars in spending. Construction and infrastructure projects consist of interconnected networks of people, equipment, and materials. Most often, finding optimal work strategies, and making timely operational decisions that lead to maximum productivity while minimizing project completion cost and time is not trivial. Unlike manufacturing and industrial systems, construction projects involve dynamic (constantly evolving) layouts, complex resource interactions, uncertainties in workflows and processes, and unforeseen conditions that can result in deviations from plans and unwanted delays. Figures show that only 30 percent of construction projects finish on time and within budget. Therefore, the accuracy and timeliness of operational-level decision-making in construction projects is of utmost importance. This award supports fundamental research to enhance construction decision-making accuracy by reducing uncertainties through the seamless integration of process-level data into decision-making. This will be achieved by building the theoretical foundation and significantly advancing the current state of construction simulation modeling through enabling real-time interaction with a simulation model as the real project evolves, and communicating the simulation output through a feedback loop to steer the events in the real project. Therefore, results from this research will benefit the U.S. economy and the society since it leads to better decision-making which results in reducing waste, rework, cost, time, and ensures safety. The multi-disciplinary nature of this project will help broaden participation of underrepresented and diverse student groups in integrated research and pedagogical activities, and positively impact engineering education. The knowledge-based simulation modeling framework in this project enables process-level models to autonomously learn from and adapt to ever-changing and evolving construction systems. Process-level knowledge that serves as the input of such simulation models is obtained from ubiquitous sensory data that describe relationships, interactions, and uncertainty attributes of field processes, and enable the generation and maintenance of more accurate simulation models. In doing so, some scientific barriers are yet to be overcome to realize the full accreditation and application of this framework. The research team will design and test methods that draw from data mining, machine learning, forecasting, and control to fill the existing knowledge gaps in capturing and mining complex data and meta-data from equipment and human crew interactions. The resulting process-level knowledge will be rich enough to describe, model, analyze, and project the uncertainties of construction systems at any point in time and consequently help adjust resource allocations and operational scenarios on the job site.
Revealing Hidden Safety Hazards Using Workers Collective Bodily and Behavioral Response Patterns
Construction Science; TAMU; https://hdl.handle.net/20.500.14641/529; National Science Foundation
Current hazard-identification efforts in safety management are mostly limited by humans' abilities to recognize hazards and/or by their existing knowledge of known hazards. Consequently, numerous hazards go unidentified, creating unmanageable risks. To enhance hazard recognition capabilities, this research focuses on understanding and exploiting humans' bodily and behavioral responses in their interaction with the physical environmental system. It is well recognized that a potential hazard within the system may cause instability in actions, and ultimately accidents. However, the unpredictable nature of human behavior poses a critical challenge in utilizing the analysis of such actions for the identification of unstable system conditions. Methodologies developed in this research will enable the evaluation of collective patterns associated with human responses to estimate the likelihood of hazard locations across a construction site. Thus, knowledge gained from this research will advance our ability to utilize response information for accident prevention, leading to reduced injuries and fatalities from construction-related accidents. Research outcomes will be integrated into engineering curriculum development, undergraduate research activities, industry workshops, and outreach activities for K-12 students and underrepresented student groups, especially women and minorities. The objective of this research is to examine whether, how, and to what extent workers' collective bodily and behavioral response patterns identify recognized/unrecognized hazards for the purpose of enhancing safety performance in construction environments. This research focuses on detecting hazards that causes fall accidents, a single most dangerous injury event within the construction industry, using workers - kinematic sensing data captured from wearable inertial measurement sensors. This research hypothesizes that the collective abnormalities apparent in multiple workers' balance and gait in one location is correlated with the likelihood of the presence (and/or the risk) of a recognized/unrecognized fall hazard in that location. To test this hypothesis, this project will: 1) identify appropriate metrics that characterize the perturbation to workers' balance and gait caused by recognized and unrecognized hazards; 2) model a near-miss index (NMI) that evaluates the abnormalities of workers' gait and balance; 3) investigate the relationship between the collective NMI patterns and the presence and risk of a hazard in each location; 4) identify and examine appropriate sensor network platforms for the scalable implementation of the approach; and 5) validate the efficacy and usefulness of the developed approach through its application within construction sites.
Uncovering Potential Risks of Wind-induced Cascading Damages to Construction Projects and Neighboring Communities
Construction Science; TAMU; https://hdl.handle.net/20.500.14641/233; National Science Foundation
Unstructured construction sites, including incomplete structures and unsecured resources (e.g., materials, equipment, and temporary facilities), are among the most vulnerable environments to windstorms such as hurricanes. Wind-induced damages to construction sites cause substantial losses, disruption, and considerable schedule delays, and thus negatively impact the efficiency of construction projects. Moreover, wind-induced damage caused by equipment, materials or structural elements, for example, originating from construction sites negatively affect neighboring communities, triggering structural damage, serious injuries, and casualties, as well as economic losses. This project will create and validate a new streamlined Imaging-to-Simulation framework to prevent wind hazard events from causing catastrophic damage to construction projects and neighboring communities. This project will benefit our society as it will significantly enhance current windstorm preparedness and mitigation plans, which ultimately promote public safety, property loss reduction, insurance cost reduction, and induce a culture of preparedness for disasters. This multidisciplinary research will help broaden participation of a new generation of young people in the Science, Technology, Engineering and Math (STEM) fields through integrated research and pedagogical activities. Using knowledge on potential at-risk construction resources obtained through experimental testing of extreme wind events, this project will partially or fully automatically model the current state of construction sites through machine vision techniques using multimodal visual data obtained from construction workers and camera-equipped unmanned aerial vehicles. To perform multi-physics simulation of multiple discrete objects in unstructured construction sites, an impulse-based discrete element method will be conceptualized. This method explicitly accounts for impulse-based dynamics by realizing efficient computing, which enable balancing between significant speed-up and reasonable simulation fidelity. The approach can describe the collective motion of mutually interacting components over time. Component-based vulnerability and impact analysis with 3D Building or Civil Information Models (BIM/CIMs) will then be conducted to generate fundamental and highly specific knowledge on wind-induced damage mechanisms. Finally, the entire system will be validated in real-world construction projects and within a 12-fan Wall of Wind facility that can generate up to hurricane category 5 wind speeds.