Assigning labour-hours to a certain scope of work during design and estimating is still more of an art than a science. This research proposes a data-driven approach that uses multiple linear regression (MLR) and available historical data from building information models (BIM) to associate project labour-hours and project design features. The framework relies on an enhanced version of stepwise regression technique to select the most relevant predictive factors and generate a predictive model without compromising the achievable accuracy of regression. The framework also encompasses analytical methods for justifying MLR application, validating the resulting model, and establishing range estimates for point-value predictions. In collaboration with an industry partner, the framework application is exemplified by analyzing labour-hours and design features for structural steel fabrication, leading to the creation of a valid MLR model in the simplest form. Finally, pros and cons for the proposed framework and opportunities for future research are discussed.
The behaviour of partially grouted (PG) masonry shear walls is complex due to masonry’s anisotropic nature and the nonlinear interactions among its constituents. Currently available code- and research-based shear strength equations provide highly variable results when predicting the in-plane shear strength of PG masonry walls. It is crucial to develop a greater understanding in this area, as sudden shear failures of masonry walls can lead to catastrophic losses of human life and property. This study presents the development of several new in-plane shear strength models for PG masonry walls using stepwise regression and model trees with data compiled from 292 experimentally tested walls. The models are found to significantly outperform existing code- and research-based shear strength equations. It was found that, of the variables studied, the most significant ones are the axial load, wall geometry, compressive strength of mortar, and area of interior vertical reinforcement.
The model tree algorithm of M5 is integrated with the multiple linear regression technique called modified stepwise regression (MSR), resulting in a new methodology for modeling complex civil engineering problems. We purposefully chose artificial neural networks (ANN) for comparison against the proposed “M5+MSR” because they fall at the two ends of the model interpretability spectrum in machine learning. In two application cases (case 1: concrete workability and case 2: steel fabrication estimating), the proposed “M5+MSR” gave rise to explainable regression tree models featuring substantially reduced complexities against ANN and model prediction errors comparable to ANN. In both cases, the resulting “M5+MSR” models consistently outperformed ANN in terms of model overfitting metrics by 19% in case 1 and by 21% in case 2, thus boasting better learning performances. The proposed new methodology will potentially find applications in tackling a wide range of complicated engineering problems that entail fitting prediction models based on laboratory or field data.
Earthmoving is one of the main processes involved in heavy construction and mining projects. It requires a significant share of the project budget and can dictate its overall success. Earthmoving related activities have a stochastic nature that affects the project cost and duration. In common practice, the equipment required for a project is selected using average operating cycles, neglecting the stochastic nature of operations and equipment. Ultimately this can lead to rough estimates and poor results in meeting the projects’ objectives. This research aims to provide a decision-support tool for earthmoving operations and achieve the best arrangement of equipment based on project objectives and equipment specifications by utilizing historical data. Operation simulation is identified as an efficient technique to model and analyze the stochastic aspects of the cost and duration of earthmoving operations in construction projects. Therefore, two simulation models—namely the Decision-Support Model and the Estimation Model, have been developed in the Symphony.net modeling environment to address the industry needs. The Decision-Support Model provides the best arrangement of equipment to maximize global resource utilization. In contrast, the Estimation Model captures more of the project details and compares various equipment arrangements. In this paper, these models are created, and the modeling logic is validated through a case study employing a real-world earthmoving project that demonstrates the model’s capabilities. The decision support model showed promising results in determining the optimized fleet selection when considering equipment and shift variations, and the cost model helped better quantifying the impact of the decision on the cost and profit of the project. This modeling approach can be reproduced by others in any case of interest to gain optimal fleet management.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.