原文传递
BACKCALCULATION OF FLEXIBLE PAVEMENT MODULI FROM DYNAMIC DEFLECTION BASINS USING ARTIFICIAL NEURAL NETWORKS.
| 题名： | BACKCALCULATION OF FLEXIBLE PAVEMENT MODULI FROM DYNAMIC DEFLECTION BASINS USING ARTIFICIAL NEURAL NETWORKS. |
| 作者： | Meier-RW; Rix-GJ |
| 关键词： | BACKCALCULATION-; FLEXIBLE-PAVEMENTS; MODULUS-OF-ELASTICITY; PAVEMENT-LAYERS; DYNAMIC-DEFLECTION-DETERMINATION; ARTIFICIAL-NEURAL-NETWORKS; REAL-TIME |
| 摘要： | The falling weight deflectometer (FWD) test measures the response of a pavement system to a transient load applied at the pavement surface. A limitation of existing, widely used techniques for backcalculating pavement layer moduli from FWD results is that they are based on a static analysis of pavement response. Previous studies have shown that significant errors in moduli can accrue from the discrepancy between this static assumption and the dynamic nature of the FWD test. Dynamic solutions for pavement response are available, but their computational complexity makes them impractical for use in conventional backcalculation programs that use gradient search or data base techniques. This limitation has been overcome by applying artificial neural network technologies to the backcalculation problem. An artificial neural network has been trained to backcalculate pavement layer moduli for three-layer flexible pavement systems with synthetic dynamic deflection basins. The dynamic pavement response was calculated by using an elastodynamic Green function solution based on a stiffness matrix formulation of the pavement system. The computational efficiency of the trained neural network means that moduli can be backcalculated with a speed that is several orders of magnitude greater than that which can be achieved by conventional gradient search and data base approaches. This is significant because it demonstrates the feasibility of backcalculating pavement layer moduli from dynamic deflection basins in real time. |
| 总页数： | Transportation Research Record. 1995. (1473) pp72-81 (9 Fig., 1 Tab., 21 Ref.) |
| 报告类型： | 科技报告 |
相关文献
- BACKCALCULATION OF FLEXIBLE PAVEMENT MODULI USING ARTIFICIAL NEURAL NETWORKS.
- USING ARTIFICIAL NEURAL NETWORKS AS A FORWARD APPROACH TO BACKCALCULATION.
- DIPLOBACK: NEURAL-NETWORK-BASED BACKCALCULATION PROGRAM FOR COMPOSITE PAVEMENTS.
- Interpretation of FWD Data When Pavement Layers Are Not Intact; Final rept. Jul 95-Jun 97
- PERFORMANCE EVALUATION OF BACKCALCULATION ALGORITHMS THROUGH THREE-DIMENSIONAL FINITE-ELEMENT MODELING OF PAVEMENT STRUCTURES.
- Guidelines for Review and Evaluation of Backcalculation Results.
检索历史
应用推荐
