Prediction of Dust Abatement Costs in Construction Demolition Projects

Abstract

Dust pollution arising out of building demolition has serious health implications on workers, as well as the neighboring communities. Existing research has shown that regulatory and engineering control methods are the most popular for dust pollution control on demolition sites. Though engineering control methods are effective in suppressing dust pollution, they have enormous cost implications for demolition companies. Therefore, accurate prediction of dust treatment costs is an important element of the demolition planning process. However, very little information is available in the existing research about treatment costs. In addition, there has not been any attempt to develop a model which can accurately predict the cost of dust treatment during building demolition. To overcome this knowledge gap, a grey prediction model is built according to the information obtained from twenty previous demolition projects. The historical trend of demolition project cost is combined to establish the prediction model based on GM (1, 1), which can be used to obtain the dust treatment cost of a project with very high accuracy. To further improve the prediction accuracy, this paper also builds a Single Function Residual Identifiability (SFRI) model. The relative error between the actual and predicted dust treatment costs from 2013 to 2021 ranges from 0.003% to 0.077%. Through detailed assessment of various treatment measures using a case study, it was found that the results obtained by the prediction model are very close to the actual costs incurred, which verifies the accuracy of the proposed model.