Enhanced prediction intervals of tunnel-induced settlement using the genetic algorithm and neural network

Liuyang Feng and Limao Zhang

Reliability Engineering and System Safety, 2022, vol. 223, issue C

Abstract: This paper constructs the prediction intervals (PIs) of the tunnels’ settlement caused by the shielding steering process. The hybrid genetic algorithm -neural network (GA-NN) is developed to obtain the upper and lower bound of the settlement based on a series of shield operating parameters, geological condition parameters, tunnel geometric parameters, and anomalous conditions. An improved prediction interval-based cost function is proposed to enable the consideration of the uncertainty from model misspecification and noise variance. The genetic algorithm optimizes the weighted parameters in the neural network by minimizing the cost function value. This study adopts a metro tunnel construction case in China to verify the effectiveness of the proposed hybrid genetic algorithm-neural network approach. The results based on the study case illustrate the superiority of the proposed hybrid approach in (1) overcoming the limitations of the conventional prediction interval indicator; (2) achieving comparative results with the deterministic estimation based on the least squares support vector machine; (3) providing a probability prediction of the settlement only based on deterministic input multivariables. Overall, this study contributes to (1) the uncertainty assessment of tunnel settlement based on the deterministic variables, (2) developing a new PIs based cost function which is stable and reliable, (3) the engineering practice for a safer assessment based on the prediction intervals.

Keywords: Prediction intervals; Tunnel-induced settlement; Artificial intelligence (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (5)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0951832022001053
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:reensy:v:223:y:2022:i:c:s0951832022001053

DOI: 10.1016/j.ress.2022.108439

Access Statistics for this article

Reliability Engineering and System Safety is currently edited by Carlos Guedes Soares

More articles in Reliability Engineering and System Safety from Elsevier
Bibliographic data for series maintained by Catherine Liu ().