Predicting the construction labour productivity using artificial neural network and grasshopper optimisation algorithm

The construction industry is mainly dependent on human resources, and labour costs are significant. Although many researchers have investigated construction labour productivity (CLP), the lack of adequate studies in this field is evident in developing countries. This paper intends to measure the CLP of the concrete pouring operations related to the construction of commercial-office complex projects in Iran. For this purpose, 19 critical factors with significant impact on the CLP were identified and listed in five groups, including individual, managerial, economic, technical, and environmental aspects. Then, a hybrid model based on artificial neural network (ANN) and Grasshopper optimisation algorithm (GOA) was developed to determine the most influential factors and increase the CLP model's precision. Data related to the CLP of 24 under-construction commercial-office complex projects in Iran were gathered. Results reveal the most influencing factors on the CLP are labour experience and skill and motivation of labour from the individual group, the amount of pay from the economic group, site accidents from the technical group, proper supervision from the management group, and weather conditions from the environmental group. The findings can facilitate the development of more efficient project schedules, increasing the CLP, and reducing project costs.

Automated summary

This study aims to measure the construction labour productivity (CLP) of concrete pouring operations in commercial-office complex projects in Iran and identify the significant factors affecting CLP. The findings can help improve project scheduling efficiency, increase CLP, and reduce project costs.