| Medium: |
conference paper |
| Language(s): |
English
|
| Conference: |
IABSE Workshop: Ignorance, Uncertainty, and Human Errors in Structural Engineering, Helsinki, Finland, 15-16 February 2017 |
| Published in: |
IABSE Workshop Helsinki 2017 |
|
Page(s):
|
32-42
|
Total no. of pages: |
11 |
|
|
Page(s):
|
32-42
|
| Total no. of pages: |
11 |
| DOI: |
10.2749/helsinki.2017.032 |
|
Abstract:
|
This paper describes an acquisitive method of rule‐type knowledge from the field inspection data
on highway bridges. The proposed method is enhanced by introducing an improvement to a
traditional data mining technique, i.e. applying the rough set theory to the traditional decision
table reduction method. The new rough set theory approach helps in cases of exceptional and
contradictory data, which in the traditional decision table reduction method are simply removed
from analyses. Instead of automatically removing all apparently contradictory data cases, the
proposed method determines whether the data really is contradictory and therefore must be
removed or not. The method has been tested with real data on bridge members including girders
and filled joints in bridges owned and managed by a highway corporation in Japan. There are,
however, numerous inconsistent data in field data. A new method is therefore proposed to solve
the problem of data loss. The new method reveals some generally unrecognized decision rules in
addition to generally accepted knowledge. Finally, a computer program is developed to perform
calculation routines, and some field inspection data on highway bridges is used to show the
applicability of the proposed method.
|
|
Keywords:
|
highway bridge bridge Inspection data mining rough sets contradictory data
|
