Implementation of Bayesian Updating and Markov Chains to Improve Simulation of Stochastic Processes in Construction

• Author / Creator

  Werner, Michael S

• This thesis was mainly concerned with improving model-based prediction and forecasting of state variables of processes or systems using new, periodically-generated data within the construction domain. Some of these data are generated from field tests performed during feasibility studies, while other data are acquired during the execution phase of the project. The primary matters that are examined in this research relate to prediction of a physical attribute of the environment that is interacting with the work face; specifically, ground conditions in tunneling projects. The approaches explored include the use of Markov chains and statistical distributions for representing uncertainty and stochasticity within simulation models in a dynamic fashion. Parameters for these are changed frequently, using Bayesian updating algorithms, as new data are received. The simulations and updating were implemented in an automated fashion. The merits of these techniques were demonstrated in case studies implemented within the tunnel construction domain. Results demonstrate that the proposed method was able to provide more reliable predictions with relatively little effort.

• Subjects / Keywords

  • Markov chains
  • Bayesian updating
  • Geological prediction
  • Construction simulation
  • Tunneling simulation

• Graduation date

  Spring 2018

• Type of Item

  Thesis

• Degree

  Master of Science

• DOI

  https://doi.org/10.7939/R3H708F9D

• 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.