56 0

Failure mode and effects analysis of RC members based on machine-learning-based SHapley Additive exPlanations (SHAP) approach

Title
Failure mode and effects analysis of RC members based on machine-learning-based SHapley Additive exPlanations (SHAP) approach
Author
전종수
Keywords
Failure mode and effects analysis; Columns; Shear walls; Machine learning; SHAP values
Issue Date
2020-09
Publisher
ELSEVIER SCI LTD
Citation
ENGINEERING STRUCTURES, v. 219, article no. 110927
Abstract
Machine learning approaches can establish the complex and non-linear relationship among input and response variables for the seismic damage assessment of structures. However, lack of explainability of complex machine learning models prevents their use in such assessment. This paper uses extensive experimental databases to suggest random forest machine learning models for failure mode predictions of reinforced concrete columns and shear walls, employs the recently developed SHapley Additive exPlanations approach to rank input variables for identification of failure modes, and explains why the machine learning model predicts a specific failure mode for a given sample or experiment. A random forest model established provides an accuracy of 84% and 86% for unknown data of columns and shear walls, respectively. The geometric variables and reinforcement indices are critical parameters that influence failure modes. The study also reveals that existing strategies of failure mode identification based solely on geometric features are not enough to properly identify failure modes.
URI
https://www.sciencedirect.com/science/article/pii/S0141029620307513?via%3Dihubhttps://repository.hanyang.ac.kr/handle/20.500.11754/170694
ISSN
0141-0296; 1873-7323
DOI
10.1016/j.engstruct.2020.110927
Appears in Collections:
COLLEGE OF ENGINEERING[S](공과대학) > CIVIL AND ENVIRONMENTAL ENGINEERING(건설환경공학과) > Articles
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE