| dc.description.abstract | Efficient resource utilization is crucial for achieving optimal performance in construction projects. In the
context of blockwork erection, the allocation and coordination of resources play a significant role in
ensuring productivity, cost-effectiveness, and timely completion. This paper proposes the application of
artificial neural network (ANN) predictive modelling to optimize resource operation in blockwork
erection. The study focuses on developing an ANN-based predictive model that takes into account various
input parameters such as project characteristics, workforce availability, material type and availability, and
task dependencies, among others. The model aims to predict the optimal allocation of resources, including
labor, materials, and equipment, to maximize productivity and minimize overall project duration.
To develop the ANN model, historical data from past blockwork erection projects was collected,
encompassing the various project parameters and resource allocation scenarios. This data was used for
training, validating, and testing the ANN model. The model was designed to learn the complex
relationships between input parameters and resource allocation outcomes, enabling it to make accurate
predictions for new project scenarios. The proposed ANN model offers several advantages over
traditional resource allocation approaches. By leveraging the computational power of neural networks, it
can capture and learn from intricate patterns within the data, leading to improved prediction accuracy.
Additionally, the model can adapt and update its predictions as new data becomes available during project
execution, enhancing its effectiveness in dynamic construction environments.
The research outcomes provide valuable insights into the optimal allocation and operation of resources
for blockwork erection. The ANN model serves as a decision support tool for construction project
managers, enabling them to make informed resource allocation decisions and enhance project
performance. Ultimately, the application of this predictive modelling approach can lead to improved
efficiency, cost savings, and the timely completion of blockwork construction projects. | en_US |
