Construction projects are planned in a complex and dynamic environment characterized by high risks and uncertainties amidst resource constraints. Assessing construction schedule risk facilitates informed decision-making, especially in a resource-constrained situation, and allows proactive actions to be taken so that project objectives are not jeopardized. This study presents a stochastic multiskilled resource scheduling (SMSRS) model for resource-constrained project scheduling problems (RCSPSP) considering the impact of risk and uncertainty on activity durations. The SMSRS model was developed by integrating a schedule risk analysis (SRA) model (developed in MS Excel) with an existing multiskilled resource scheduling (MSRS) algorithm for the development of a feasible and realistic schedule. The computational experiment carried out on three case projects using the proposed SMSRS model revealed an average percentage deviation of 10.50%, indicating the inherent risk and uncertainty in activity durations of the project schedule. The core contribution of the proposed SMSRS model is that it: (1) presents project practitioners with a simple tool for assessing the risks and uncertainty associated with resource-constrained project schedules so that necessary response actions can be taken to ensure project success; (2) provides the small-scale construction businesses with an affordable tool for evaluating schedule risk and developing a feasible and realistic project schedule.
Road construction projects are complex endeavors, likewise the associated risks. Thus, identifying and assessing the potential risks associated with road projects is crucial to achieving project success. However, these associated risks are complex and dynamic, and the traditional risk assessment methods cannot accurately assess the risks. Hence, this paper presents a neural network approach by developing a deep neural network (DNN) model for assessing risk impact on project schedule and cost performance of road projects. The proposed DNN model was used to assess and predict the risk impact on 207 road projects in the Republic of Korea (ROK), and the accuracy was compared with a baseline neural network (BNN) and random forest regressor (RFR) models. The results show that the DNN model outperformed the BNN and RFR models, given the lowest mean squared error (MSE) and mean absolute error (MAE) values. The theoretical contribution of this study is related to risk assessment theory and the integration of expert judgment into a DNN model for effective risk assessment of road projects. Also, this study provides the practitioners with a systematic approach to predict accurate project schedule and cost performance considering the significant risk factors while enabling proper allocation of contingency allowance to schedule and cost baselines to guarantee project success.
Risk management (RM) in construction projects is a knowledge-intensive process that requires an efficient mechanism for capturing, storing, exploiting, and managing risk-related knowledge. Although some existing studies have proposed various knowledge-based risk management (KBRM) tools. However, not all tools suit all projects, as every project is unique. Besides, each tool is developed based on certain assumptions with methodological drawbacks. Hence, new tools are required in response to the continuous change in the project environment, complexity, and dynamism by adopting new technologies to improve the RM processes. This study proposes a knowledge graph technique to improve risk-related knowledge storage, sharing, and reuse in managing construction project risks. This study constructed a risk knowledge graph (RisKG) based on a project risk register. The proposed RisKG was then used to develop a construction risk dashboard (ConRisk Dashboard) that can be used for quick risk information retrieval to support the RM of construction projects. The effectiveness of the proposed ConRisk Dashboard was verified through its use for the search and retrieval of risk assessment details of a particular risk source associated with the case project used in RisKG. The results indicate that the ConRisk Dashboard can improve the RM processes by saving time spent on project documentation reviews and cost expended on expert workshops at the beginning of every new project. Conclusively, the contribution of this study to the body of knowledge is that it provides a framework for developing knowledge-based risk management systems (KBRMS) and intelligent tools that can facilitate integrated risk management and digital collaboration among project stakeholders to support informed decision-making in construction projects. In addition, this work paves the way for research towards developing and adopting digital tools that can facilitate the digital transformation of RM and CM practices to improve project performance and productivity in the construction industry.