Optimum Repair Planning of Existing Bridges by Genetic Algorighm Based on Inspection Data
Grant-in-Aid for Scientific Research (C)
|Allocation Type||Single-year Grants|
|Research Institution||KANAZAWA UNIVERSITY|
CHIKATA Yasuo Graduate School of Natural Science and Technology, KANAZAWA UNIVERSITY Assoc. Prof., 自然科学研究科, 助教授 (50155298)
|Project Period (FY)
1997 – 1999
Completed(Fiscal Year 1999)
|Budget Amount *help
¥2,900,000 (Direct Cost : ¥2,900,000)
Fiscal Year 1999 : ¥300,000 (Direct Cost : ¥300,000)
Fiscal Year 1998 : ¥1,000,000 (Direct Cost : ¥1,000,000)
Fiscal Year 1997 : ¥1,600,000 (Direct Cost : ¥1,600,000)
|Keywords||bridge maintenance / database / repair planning / Genetic Algorithm / GIS / inspection data|
This study deals with the optimum repair planning of existing bridges based on the results of their visual inspection.
The results of project work are summarized as the followings.
・The results of visual inspection of existing bridges and the bridge's fundamental data are transported from printed objects into the digital data, and DBMS has been built.
・The DBMS has extended to the network accessibility, and GIS system has been introduced to the system in order to make visual investigation and presentation of the data.
・Based on the data base of existing bridges, repair planning is formulated as a knapsack problem (combinations of bridges and their parts to be repaired ). Because of huge number of the combinations, GA(Genetic Algorithm) was adopted to solve the knapsack problem.
・On the windows 95/98/NT system, an linkage (integrated) GUI program has been made, that links the DBMS and the GA system.
・The reliability of the data included in the DBMS depends on the expert engineers who execute visual inspection, and there may be some data with contradiction. By using SOM/LVQ, the data included in the DBMS are investigated, and the data is checked its accuracy.
・The report will be in public on the Web site, as the file in PDF format(in Japanese only).
Research Output (19results)