Stochastic, discrete-event simulation modeling has emerged as a useful tool for facilitating decision making in construction. Owing to the rigidity inherent to distribution-based inputs, current simulation models have difficulty incorporating new data in real-time, and fusing these data with subjective judgments. Accordingly, application of this valuable technique is often limited to project planning stages. To expand implementation of simulation-based decision-support systems to the execution phase, this research proposes the use of Bayesian inference with Markov chain Monte Carlo (MCMC)–based numerical approximation approach as a universal input model updating methodology of stochastic simulation models for any given univariate continuous probability distribution. Found capable of (1) fusing actual performance with expert judgment, (2) integrating actual performance with historical data, and (3) processing raw data by absorbing uncertainties and randomness, the proposed method will considerably improve the resilience, reliability, accuracy, and practicality of stochastic simulation models, thereby enabling the application of stochastic simulation in the execution phase of construction.

Although methods for assessing and simulating the influence of safety-related measures on safety performance have been proposed, practical applications remain limited. Data required by these methods are dispersed across departments, necessitating the development or redesign of data warehouses. This research proposes a simulation-based analytics approach to enhance safety management system (SMS) decision making using distributed simulation to overcome limitations associated with previous approaches. This distributed simulation approach is used to (1) integrate historical data without modifying data-warehouse structures (i.e., data fusion component), (2) link data to an artificial neural network–based analysis component for determining the influence of safety-related measures on incident levels, (3) connect data and analysis components to existing simulation components, and (4) combine the outputs, resulting in a comprehensive safety performance evaluation system to examine incident levels. Results demonstrate that this approach successfully fuses and integrates data from several sources with analysis and simulation components in a cost-, labor-, and time-efficient manner. A distributed simulation–based analytics approach represents a considerable opportunity for industrial construction companies to more effectively use historical data, analysis tools, and simulation models.

To achieve meaningful results, data-driven decision-support systems in construction require the integration of fragmented data from multiple standalone databases. In practice, a manual brute-force approach is often the only available means of integrating structured, yet semantically-ambiguous, construction data. Two common data integration challenges include the identification of (1) key strings (i.e., product identification) partially shared between two data sources; and (2) relationships (overlap, included, or outside) between two 3D object lists based on coordinates. This research has developed a framework that includes two generic solutions to the identified semantic mapping challenges. The proposed framework automatically integrates fragmented and incompatible data (exhibiting similar semantic mapping challenges) from various sources into a tidy format for input into a diverse range of industrial construction applications. Verification and functionality of the framework were confirmed using both artificial data and a real case study of a large oil-and-gas project. The ability of the proposed data integration functions and framework to automate otherwise manual data integration processes was demonstrated. Results of this study are expected to enhance real-time information flow, improve data quality, and promote the use of fragmented data for critical decision support in practice.

Simulation has assisted engineers in various decision-making processes for decades. Particularly, modeling inputs as probabilistic distributions enables these stochastic models to capture uncertainties and represent random processes. A significant number of studies have developed an accurate input model from a single source type (i.e., quantitative observations or subjective information), but few have integrated multiple information sources dynamically. Nevertheless, the latter situation is common in construction projects, especially during project execution when quantitative observations and expert opinions need to be factored into models in real time. This paper is the first to propose coupling a Markov chain Monte Carlo (MCMC)–based numerical method with a weighted geometric average (GA) as a novel approach to systematically update inputs for stochastic simulation models. The proposed method handles both objective and subjective project data to effectively update the input models in real time, producing more accurate representations of probabilistic input models for any Monte Carlo (MC)–driven simulation. This method considerably improves the reliability, accuracy, and practicality of stochastic simulation models.