Construction project risk prediction model based on EW-FAHP and one dimensional convolution neural network

Yawen Zhong; Hailing Li; Leilei Chen

doi:10.1371/journal.pone.0246539

Construction project risk prediction model based on EW-FAHP and one dimensional convolution neural network

PLoS One. 2021 Feb 9;16(2):e0246539. doi: 10.1371/journal.pone.0246539. eCollection 2021.

Authors

Yawen Zhong¹, Hailing Li², Leilei Chen³

Affiliations

¹ School of Engineering, Southwest Petroleum University, Nanchong, China.
² School of Civil Engineering and Environment, Xihua University, Chengdu, China.
³ Sichuan University of Science and Engineering, the Artificial Intelligence Key Laboratory of Sichuan Province, Zigong, China.

Abstract

In order to solve the problem of low accuracy of traditional construction project risk prediction, a project risk prediction model based on EW-FAHP and 1D-CNN(One Dimensional Convolution Neural Network) is proposed. Firstly, the risk evaluation index value of construction project is selected by literature analysis method, and the comprehensive weight of risk index is obtained by combining entropy weight method (EW) and fuzzy analytic hierarchy process (FAHP). The risk weight is input into the 1D-CNN model for training and learning, and the prediction values of construction period risk and cost risk are output to realize the risk prediction. The experimental results show that the average absolute error of the construction period risk and cost risk of the risk prediction model proposed in this paper is below 0.1%, which can meet the risk prediction of construction projects with high accuracy.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Fuzzy Logic
Humans
Neural Networks, Computer*

Grants and funding

[This research was supported by National Natural Science Foundation of China (Nos. 11705122, 61640223), Sichuan Provincial Department of Science and Technology Project (No. 2019YJ0477), Artificial intelligence Sichuan Key Laboratory Project (No.2019RYY01), Nanchong Science and Technology Bureau Project (No.19SXHZ0040)]