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
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.
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