| Project/Area Number |
07650523
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
土木材料・力学一般
|
|---|
| Research Institution | Graduate School of Information Sciences, Tohoku University |
|---|
Principal Investigator |
FUKUDA Tadashi Tohoku University, Graduate School of Information Sciences, Professor, 大学院・情報科学研究科, 教授 (40005385)
|
|---|
| Project Period (FY) |
1995 – 1996
|
| Project Status |
Completed (Fiscal Year 1996)
|
| Budget Amount *help |
¥2,400,000 (Direct Cost: ¥2,400,000)
Fiscal Year 1996: ¥1,200,000 (Direct Cost: ¥1,200,000)
Fiscal Year 1995: ¥1,200,000 (Direct Cost: ¥1,200,000)
|
|---|
| Keywords | performance model / PMS / neural network / optimization / pavement repair / life cycle cost / dynamic programming |
|---|
| Research Abstract |
A performance model predicting the behaviors of surface properties of a pavement and an optimazation technique comprise the nucleus of functions of a pavement management system. In this study, a pavement performance model according to a neural network based on a pavement design equation (AASHTO equation) was constructed. By using this performance model, it is possible to easily make perfomance models matching road surface property characteristics in various districts through training with of just a small amount of measurement date.
In this study, systems for optimazation of both project level and network level pavement repair programs were made up incorporating this neuro model in these systems and using dynamic programming as the optimization technique. Using these systems, it is possible to decide the optimum conditions of asphalt pavement, such as initial design and repair timing, for which the life cycle cost will be a minimum.
|
