Graduate Thesis Or Dissertation
 

Automated Monitoring of Construction Operations for Data-Driven Decision Making

Public Deposited

Downloadable Content

Download PDF
https://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/44558n53z

Descriptions

Attribute NameValues
Creator
Abstract
  • The continuous improvement of construction operations requires a systematic approach of monitoring and making appropriate control actions. However, the lack of real-time information hinders this workflow and eventually compromises timely and effective decision-making. Project managers spend a great deal of time and effort to solve problems emerging from lack of timely information, poor coordination, and inaccurate out-of-date data. Emerging technologies like advanced data analytics, the internet of things, and superior computational power can aid in obtaining real-time information and actionable insight from the construction site. This is reflected in the growing use of emerging technologies to automatically monitor construction activities to improve the efficiency of construction management. The overarching research goal of this dissertation is to advance the body of knowledge and practice by integrating emerging technologies with project monitoring for data-driven decision-making. Specifically, this research develops a systematic framework to automatically identify activities performed by construction resources and then uses this real-time information to optimize the operations for data-driven decision-making. The methods developed in this study are applied to two different types of construction operations: heavy civil construction, and prefabricated construction. For both types of operations, first consumer-grade sensors, such as inertial measurement units (IMUs), microphones, RFID sensors were used to automatically identify, and track activities performed in the construction site utilizing machine learning and deep learning algorithms. Then the output from the activity identification framework was used as inputs to simulation models for dynamic productivity estimation and optimization of the operation to enable data-driven decision-making. This study contributes to the body of knowledge by providing a means for automated monitoring of construction operations using emerging technologies and assessing the use of simulation modeling for data-driven decision-making.
Contributor
License
Resource Type
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Academic Affiliation
Rights Statement
Publisher
Peer Reviewed
Language

Relationships

Parents:

This work has no parents.

In Collection:

Items

Thumbnail Title Date Uploaded Visibility Actions
file details RashidKhandakarM2022.pdf 2021-12-29 Public Download