Automated knowledge discovery and data-driven simulation model generation of construction operations

Abstract

Computer simulation models help construction engineers evaluate different strategies when planning field operations. Construction jobsites are inherently dynamic and unstructured, and thus developing simulation models that properly represent resource operations and interactions requires meticulous input data modeling. Therefore, unlike existing simulation modeling techniques that mainly target long-term planning and close to steady-state scenarios, a realistic construction simulation model reliable enough for short-term planning and control must be built using factual data obtained from ongoing processes of the real system. This paper presents the latest findings of authors' work in designing an integrated data-driven simulation framework that employs a distributed network of sensors to collect multi-modal data from construction equipment activities. Collected data are fused to create metadata structures and data mining methods are then applied to extract key parameters and discover contextual knowledge necessary to create or refine data-driven simulation models that represent the latest conditions on the ground.

Model simplification in manufacturing simulation – Review and framework

“…Various data sources may be considered, for example, technical data describing the production system, organizational data capturing system planning and control, and system load data (Bergmann & Strassburger, 2010). In addition, techniques like data and process mining and machine learning may be adopted for interpreting data (Van der Aalst, 2012, Akhavian & Behzadan, 2013;Bergmann, Feldkamp, & Strassburger, 2017). For example, process mining may be helpful in supporting model simplification of complex manufacturing systems, by distilling main product categories by identifying common routings.…”

Visualization, Information Modeling, and Simulation: Grand Challenges in the Construction Industry

“…One major encouraging factor that will help gain credibility and trust for the use of simulation by industry is leveraging reliable contextual input information to build simulation models. This practice is currently pursued in the academic research community, to design and develop more realistic and subsequently reliable simulation models (Lee et al 2009;Akhavian and Behzadan 2013a).…”

Joint probability for evaluating the schedule and cost of stochastic simulation models

“…Several researchers in the construction management field stated that time and cost are correlated [14,48]. Although there have been several advancements in construction simulation such as agent-based simulation [24], and automated knowledge discovery and data-driven simulation [3], the multiple performance indices obtained as the output of a simulation model are still treated as independent variables. Therefore, there is a need for a method that describes, analyzes and represents the knowledge of this correlation using joint probability.…”

“…Therefore, there is a need for an analytical method to overcome these shortcomings. The objectives of this paper are to: (1) develop a method for considering the joint probability in construction simulation and quantifying its impact on the project duration and cost; (2) calculate the conditional probability of the project cost given a specific project duration, and vice versa; (3) find the best project duration and cost that meet a specific joint probability; (4) estimate the project schedule and cost joint contingency using joint probability; and (5) generate a schedule representing a specific joint probability. Applying this method is expected to have a noteworthy impact on reducing project risk and providing the decision makers with more accurate and useful information to plan and manage their projects.…”