Contents Menu

Machine learning algorithm in J-BMS RC version and its effectiveness

Memoirs of the faculty of engineering, Yamaguchi university Volume 73 Issue 1 Page 1-9
published_at 2022-12
A040073000101.pdf
[fulltext] 990 KB
Title
橋梁維持管理支援システム(J-BMS)の学習機能と実橋での効果確認
Machine learning algorithm in J-BMS RC version and its effectiveness
Abstract
The Japanese Bridge Management System (J-BMS) RC version consists of the following three subsystems: (1) a bridge maintenance database system (J-BMS DB), (2) a concrete bridge rating expert system (RC-BREX) and (3) a maintenance plan optimization system (MPOS). Especially, in this paper, the RC-BREX system for deteriorating concrete bridges is described based on how to construct from a hierarchical neural network in order to carry out fuzzy inference and machine learning by using the neural network with the back-propagation method. Furthermore, the comparisons between diagnostic results by bridge experts and those of the proposed system are presented so as to demonstrate the validity of the system’s learning capability by using the training set for machine learning which obtained from inspection on actual in-service bridges and questionnaire surveys by bridge experts.
Creators Miyamoto Ayaho
Affiliate Master Yamaguchi University
[kakenhi]15501 grid.268397.1
Source Identifiers [PISSN] 0372-7661 [NCID] AN00244228
Creator Keywords
Japanese Bridge Management System (J-BMS) RC-BREX Machine learning On-site inspection effectiveness of learning function
Languages jpn
Resource Type departmental bulletin paper
Publishers 山口大学工学部
Date Issued 2022-12
File Version Version of Record
Access Rights open access