Data-Driven Strategies to Improve the Construction Equipment Management

• Author / Creator

  Liu, Chang

• Construction equipment management is critical for the long-term success of construction companies. Managing equipment in a cost-efficient manner for project or corporate operations is a key concern for construction companies. Although equipment cost is normally simplified to be a unit rate in project bidding and management, it is actually an aggregate of numerous small components. To maintain a competitive edge, construction companies need to analyze these small components and obtain cost- or time-saving strategies to enhance their management performance and decision making. The goal of this research is to introduce a new generation of data-driven, simulation-based analytics for construction equipment management to provide analytical decision support to industrial practitioners.

  Current construction equipment management requires both experience and expertise. Data plays a vital role in assisting decision making for equipment management. Vast amounts of data are available today, especially for the equipment costs and location-tracking, but only a small portion has been used. Additionally, simplified analytical tools used in some management strategies overlook valuable information and enhance data collected through processing, structuring, and interpretation. To address the limitations of current practices, this research created data-driven, simulation-based analytics to provide decision support to construction equipment management as follows: 1) dynamic quantification methods to achieve bargains in equipment trading; 2) simulation-based life-cycle cost analysis for heavy equipment; and 3) performance measurement method for equipment logistics.

  For the input modeling, K-means clustering and the Expectation-Maximization (EM) algorithm were used to obtain the distributions of inputs. To achieve dynamic updating, Bayesian inference was applied, integrating newly-generated and historical data to re-calibrate the inputs. Markov Chain Monte Carlo (MCMC) method was employed to approximate the posterior distribution after Bayesian inference. For the analytics, mathematical modelling was applied, and social network analysis (SNA) was introduced to evaluate equipment dispatch. Life-cycle cost analysis (LCCA) was also applied to incorporate both maintenance and ownership costs. Feasibility and functionality of the proposed research was validated through practical case studies. These case studies demonstrated the applications of proposed simulation-based analytics in detail and provided valuable information for practitioners. These approaches have been shown to be effective in achieving bargains in equipment acquisition and disposal, predicting the cumulative total cost of equipment, and evaluating equipment logistics performance, all of which can provide analytical decision support for equipment-management practitioners.

• Subjects / Keywords

  • Data-driven Analytics
  • Equipment Management

• Graduation date

  Spring 2020

• Type of Item

  Thesis

• Degree

  Doctor of Philosophy

• DOI

  https://doi.org/10.7939/r3-69zf-k302

• License

  Permission is hereby granted to the University of Alberta Libraries to reproduce single copies of this thesis and to lend or sell such copies for private, scholarly or scientific research purposes only. Where the thesis is converted to, or otherwise made available in digital form, the University of Alberta will advise potential users of the thesis of these terms. The author reserves all other publication and other rights in association with the copyright in the thesis and, except as herein before provided, neither the thesis nor any substantial portion thereof may be printed or otherwise reproduced in any material form whatsoever without the author's prior written permission.