原文传递
Road Surface Crack Condition Forecasting Using Neural Network Models
| 题名： | Road Surface Crack Condition Forecasting Using Neural Network Models |
| 作者： | Zhenyu Lou, Jian John Lu. and Manjriker Gunaratne |
| 关键词： | Crack, Forecasting, Pavement performance. Neural network. Surface distress |
| 摘要： | Accurate forecasting of pavement crack condition is essential for pavement management systems (PMS) at either network or project level. Up to now, mechanistic-empirical and purely empirical models have been used to forecast pavement crack condition. A characteristic feature of these models is that they are formulated based on laboratory and/or field statistical data. Hence, selection of appropriate function forms could be difficult with a large data dimension. This report summarizes the results obtained from a research project sponsored by Florida Department of Transportation to develop a Backpropagation Neural Network (BPNN) model for the forecasting of pavement crack condition of Florida’s highway network. The BPNN model, which is able to learn the hidden information from the historical crack condition data, has the capability to forecast future crack condition. In order to setup an effective model, the concept of BPNN was introduced along with its mathematical training algorithm. The neural network model was then trained and tested with field data collected from Florida’s highway network. Further, the BPNN model was compared with a commonly used autoregressive (AR) model. Finally, a validation step was performed to identify the forecasting errors on the 1998 data set. It was concluded that the BPNN model was more accurate than the AR model and could be applied to forecast pavement crack condition. |
| 报告类型： | 科技报告 |
相关文献
- NOVEL APPROACH TO PAVEMENT CRACKING DETECTION BASED ON NEURAL NETWORK.
- Initial Results in Vision Based Road and Intersection Detection and Traversal.
- FORECASTING OF PAVEMENT CRACK PERFORMANCE WITH ADAPTIVE FILTER MODEL.
- Short-Term Freeway Traffic Volume Forecasting Using Radial Basis Function Neural Network
- TRAFFIC VOLUME FORECASTING OF URBAN HIGHWAY IN SHANGHAI.
- Development and Validation of Deterioration Models for Concrete Bridge Decks: Phase 1: Artificial Intelligence Models and Bridge Management System.
检索历史
应用推荐
