Abstract—Aiming at the problems of heavy workload and large errors in traditional substation engineering estimation methods, an intelligent estimation method for substation engineering based on Building Information Modeling (BIM) combined with a Differential Evolution (DE) algorithm to optimize Random Forest (RF) is proposed. This proposed method uses DE to optimize the RF model’s splitting features and decision trees to enhance the model’s estimation accuracy. The BIM of the substation project is used to determine engineering quantity information, which serves as the input of the DE-RF model, enabling intelligent cost estimation of the substation project. The results of the example analysis show that the relative error of the proposed cost estimation method for substation engineering based on BIM and DE-RF is below 10%. This accuracy level meets various substation engineering cost estimation scenarios, validating the feasibility and correctness of the proposed model.
 
Keywords—building information modeling, random forest, optimization, differential evolution


Copyright © 2023 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.