Usage
  • 29 views
  • 13 downloads

Multi-Level Knowledge Extraction and Modeling to Support Job Hazard Analysis Process for Oil and Gas Pipeline Projects

  • Author / Creator
    Altawil, Shadi N A
  • Construction projects are impacted negatively by construction safety incidents. Job hazard analysis (JHA) process is a critical process component of safety management system in the construction industry. The JHA process is a planning process that aims to address potential hazards associated with execution of construction activities. It involves collecting knowledge from several safety knowledge resources. Explicit resources such as safety manuals, safety codes and regulation, and safety best practices are the primary input knowledge. In addition, tacit safety knowledge that is related to the experience of construction professionals is a critical knowledge component that feeds into the JHA process. JHA documents is the output of each JHA process for each construction activity. The construction industry is a very dynamic and complex environment. Collecting knowledge to perform JHA process requires time and significant efforts. Construction personnel do not have the same experience and ability in identifying construction hazards. In addition, new construction manpower is continually joining the workforce and they lack sufficient experience and knowledge required for hazard identification. Previous JHA documents, which were prepared in previous projects, contain valuable knowledge related to construction hazards. Currently, documents are scattered and not reused for future JHA processes. Oil and Gas Pipeline Projects consist of risky construction activities that involve dynamic interaction between humans, heavy construction equipment, heavy material, and the complex surrounding environment. Currently, safety research related to nonbuilding construction projects is not sufficient. Nonbuilding projects such as pipeline construction and complex infrastructure need research focus due to their execution complexity and high potential risks. This research aims to introduce a method for hazard knowledge extraction and modeling to assist and make the JHA process more consistent and systematic. To reuse the hazards knowledge embedded in JHA forms, multi- levels of knowledge extraction are performed. Text mining is used to organize documents in classes by adopting two stages of machine learning algorithms, clustering and classification. Moreover, JHA forms’ contents were analyzed to extract hazards’ concepts and relationships to build a hazard dictionary and knowledge schema. Text mining for concept extraction is used along with qualitative approach to build hazard dictionary. Ontology modeling is used to model the extracted knowledge schema. The model aims to represent the knowledge concepts, taxonomies, and semantic relationships. The knowledge model will support the JHA process by enabling retrieval and communication of hazards knowledge in future projects.

  • Subjects / Keywords
  • Graduation date
    2017-11:Fall 2017
  • Type of Item
    Thesis
  • Degree
    Doctor of Philosophy
  • DOI
    https://doi.org/10.7939/R3N58D09T
  • License
    This thesis is made available by the University of Alberta Libraries with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.
  • Language
    English
  • Institution
    University of Alberta
  • Degree level
    Doctoral
  • Department
    • Department of Civil and Environmental Engineering
  • Specialization
    • Construction Engineering and Management
  • Supervisor / co-supervisor and their department(s)
    • Dr. Yasser Mohamed
  • Examining committee members and their departments
    • Dr. Ming lu (Department of Civil and Environmental Engineering)
    • Dr. Carlos Cruz Noguez (Department of Civil and Environmental Engineering)
    • Dr. Emad Elwakil (School of Construction Management)
    • Dr. Simaan Abourizk (Department of Civil and Environmental Engineering)