A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Modeling the Roughness Progression of Kansas Portland Cement Concrete (PCC) Pavements
Long-term prediction of the performance and durability of pavement represents a critical and vital issue in the pavement surface type selection process by the Kansas Department of Transportation (KDOT) using the life-cycle-cost analysis. Accurate prediction of roughness progression on Portland Cement Concrete (PCC) pavements is very important since the current model used by KDOT is based on the pavement serviceability guidelines (1993 AASHTO Design Guide). In this study, dynamic Artificial Neural Network (ANN) and statistical analysis approaches were used to develop reliable and accurate time-dependent roughness (International Roughness Index, IRI) prediction models for the newly constructed Kansas Jointed Plain Concrete Pavements (JPCP). To achieve this objective, data used in the model development process include construction and materials data as well as other inventory items, such as, traffic and climatic related data, which reflect the section-specific local conditions in Kansas. Utilizing a two-stage training approach, a three-layer (19-10-1) time-dependent ANN-based roughness prediction model was developed. It was able to project the time-dependant roughness behavior with a reasonably high coefficient of determination, R2 = 0.90 (ANN-based model) and R2 = 0.73 (SAS-based model). The sensitivity analysis performed herein quantified, to some degree, the impact of various key input parameters on the PCC pavement roughness profile. To further validate the developed ANN-based model, it was used to predict IRI values for years 2001 (R2 = 0.80) and 2002 (R2 = 0.74) data. Using multiple regression analysis technique, a statistical-based model was developed and then used to project the 20-year and 30-year IRI values.
Modeling the Roughness Progression of Kansas Portland Cement Concrete (PCC) Pavements
Long-term prediction of the performance and durability of pavement represents a critical and vital issue in the pavement surface type selection process by the Kansas Department of Transportation (KDOT) using the life-cycle-cost analysis. Accurate prediction of roughness progression on Portland Cement Concrete (PCC) pavements is very important since the current model used by KDOT is based on the pavement serviceability guidelines (1993 AASHTO Design Guide). In this study, dynamic Artificial Neural Network (ANN) and statistical analysis approaches were used to develop reliable and accurate time-dependent roughness (International Roughness Index, IRI) prediction models for the newly constructed Kansas Jointed Plain Concrete Pavements (JPCP). To achieve this objective, data used in the model development process include construction and materials data as well as other inventory items, such as, traffic and climatic related data, which reflect the section-specific local conditions in Kansas. Utilizing a two-stage training approach, a three-layer (19-10-1) time-dependent ANN-based roughness prediction model was developed. It was able to project the time-dependant roughness behavior with a reasonably high coefficient of determination, R2 = 0.90 (ANN-based model) and R2 = 0.73 (SAS-based model). The sensitivity analysis performed herein quantified, to some degree, the impact of various key input parameters on the PCC pavement roughness profile. To further validate the developed ANN-based model, it was used to predict IRI values for years 2001 (R2 = 0.80) and 2002 (R2 = 0.74) data. Using multiple regression analysis technique, a statistical-based model was developed and then used to project the 20-year and 30-year IRI values.
Modeling the Roughness Progression of Kansas Portland Cement Concrete (PCC) Pavements
V. Felker (author) / Y. M. Najjar (author) / M. Hossain (author)
2004
47 pages
Report
No indication
English
Road Transportation , Construction Equipment, Materials, & Supplies , Highway Engineering , Pavements , Pavement surface type , Kansas , Artificial Neural Network , International Roughness Index , Jointed plain concrete pavement , Life cycle cost , Portland cement concrete , Statistical analysis , Portland Cement Concrete (PCC) , Artificial Neural Network (ANN) , International Roughness Index (IRI)
Factors Affecting Rapid Roughness Progression on Portland Cement Concrete Pavements in Kansas
| British Library Online Contents | 2002
Factors Affecting Rapid Roughness Progression on Portland Cement Concrete Pavements in Kansas
| British Library Conference Proceedings | 2002
Portland cement concrete pavements
| Engineering Index Backfile | 1926
Portland Cement Concrete Pavements
NTIS | 1977