AI in Project Management: Machine Learning Application for Construction Scheduling - Ph.D. Thesis

Aug 4, 2026

Upload by Ophelia

This thesis investigates how Artificial Intelligence and Machine Learning can improve construction project scheduling by addressing inefficiencies of traditional planning tools that depend on manual inputs. It targets gaps in prior AI/ML work, especially the treatment of activity relationships, critical path analysis, and practical interfaces for industry use. A Random Forest Regressor is trained on real power-sector data and validated with R² and MAE, supported by a Streamlit prototype for rapid schedule generation and usability assessment.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages224

Reading Time9 h 24 min

AccessFree to download

Contents

List of Figures

List of abbreviations

Salford School of Science, Engineering & Environment AI in Project Management: Machine Learning Application for Construction Scheduling. A Thesis submitted for the fulfillment of the requirements of The University of Salford for the degree of [ [Ph.D. in](Ph.D. in) Project Management] Under the supervision of Dr. Mustapha Munir & Prof. Jason Underwood AbdElMottaleb, Mohamed ID: @00505304 2021-2025 Statement of originality I confirm that the academic material presented in this study is entirely my own work, and I have acknowledged all sources and references used in the preparation of this paper. I also confirm that I have not manipulated any findings or results. Furthermore, I have read and comprehended the University's guidelines on assessed work. AbdElMottaleb, Mohamed ID: @00505304 Acknowledgments The completion of this doctoral research would not have been possible without the guidance, support, and encouragement of several individuals and institutions. I wish to express my sincere gratitude to all those who have contributed to this journey. First and foremost, I extend my deepest appreciation to my supervisor, Dr. Mustapha Munir. His insightful guidance, unwavering support, and expert advice were invaluable throughout every stage of this research. His patience and consistent encouragement kept me motivated, and his critical feedback significantly shaped the direction and quality of this work. I am truly grateful for his mentorship. I would also like to offer my gratitude to all the academic and administrative staff at the School of Science, Engineering & Environment, University of Salford. Your collective efforts create an environment conducive to learning and research, and I am appreciative of the support provided during my doctoral studies. This research relied heavily on the participation and data provided by numerous construction professionals and organizations. I am profoundly grateful to all the survey respondents for generously sharing their time and expertise. I also extend my sincere thanks to the individuals who provided access to the project data crucial for the development and validation of the machine learning model. Your willingness to contribute to this research is deeply appreciated. On a more personal note, this journey has been made possible by the unwavering love, support, and sacrifices of my family. I owe an immeasurable debt of gratitude to my beloved father and mother. Your constant belief in me, your prayers, and your endless encouragement have been my pillars of strength. You have instilled in me the value of perseverance and hard work, and this achievement is as much yours as it is mine. To my dear wife, thank you for your incredible patience, understanding, and unwavering support throughout these demanding years. Your encouragement during challenging times and your sacrifices have been instrumental in allowing me to pursue this endeavor. Your love and belief in my abilities have been a constant source of motivation. This thesis is a testament to the collective support I have received, and for that, I am eternally grateful. Abstract This study investigates the integration of Artificial Intelligence (AI) and Machine Learning (ML) into construction project scheduling to address inefficiencies in traditional methods. While conventional tools like Primavera and MS Project rely heavily on manual input, existing AI/ML research often neglects critical scheduling components such as activity relationships, critical path analysis, and user-friendly interfaces. This research aims to bridge these gaps by developing an ML-driven scheduling tool that automates activity sequencing, duration prediction, and critical path identification, while incorporating a practical interface for industry adoption. The study employs a multi-methods approach, integrating both quantitative and qualitative data gathered from a survey of construction professionals with a design science fram

FAQs

What problem does the thesis address in construction project scheduling?

It addresses inefficiencies in traditional scheduling methods that require heavy manual input and often do not cover key scheduling components such as activity relationships and critical path analysis.

How is the machine learning model developed and evaluated?

The study builds a Random Forest Regressor trained on real overhead transmission line and substation project data, and evaluates performance using R² and MAE metrics.

How does the proposed system support end users in practice?

A Streamlit prototype enables dynamic schedule generation in under 30 seconds, with options to adjust duration constraints and export outputs to Excel and XER with limited manual effort.

Aug 4, 2026

Upload by Ophelia