Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Enhanced Approach to Develop the International Roughness Index Prediction Model
https://orcid.org/https://orcid.org/0000-0003-4606-4408
Practical methodologies to accurately predict international roughness index (IRI) are still questionable due to the limited IRI historical database and considerable number of factors affecting the IRI. Therefore, this study mainly focused on developing a practical model to accurately predict IRI, based on a big database of historical IRI measurements. The historical IRI data were collected annually from the same testing location between 2014 and 2021, and a total of 1,670,288 IRI measurements were used. Since the pavement age information was unavailable from the collected historical IRI data, this study proposed the enhanced approach for processing historical IRI data to estimate the pavement age of each field section. Then, three IRI prediction models were developed for three road classifications based on the processed historical IRI data, and the developed models only consider pavement age as input to be practical. It was found that the developed models can represent typical behavior of IRI over time. These models were verified by comparing the measured and predicted IRI, and they exhibited good accuracy in predicting IRI values for all road classifications. Therefore, the developed IRI prediction models may be used for pavement management systems (PMS) to provide more insights into the functional conditions of in-service flexible pavements.
Enhanced Approach to Develop the International Roughness Index Prediction Model
https://orcid.org/https://orcid.org/0000-0003-4606-4408
Practical methodologies to accurately predict international roughness index (IRI) are still questionable due to the limited IRI historical database and considerable number of factors affecting the IRI. Therefore, this study mainly focused on developing a practical model to accurately predict IRI, based on a big database of historical IRI measurements. The historical IRI data were collected annually from the same testing location between 2014 and 2021, and a total of 1,670,288 IRI measurements were used. Since the pavement age information was unavailable from the collected historical IRI data, this study proposed the enhanced approach for processing historical IRI data to estimate the pavement age of each field section. Then, three IRI prediction models were developed for three road classifications based on the processed historical IRI data, and the developed models only consider pavement age as input to be practical. It was found that the developed models can represent typical behavior of IRI over time. These models were verified by comparing the measured and predicted IRI, and they exhibited good accuracy in predicting IRI values for all road classifications. Therefore, the developed IRI prediction models may be used for pavement management systems (PMS) to provide more insights into the functional conditions of in-service flexible pavements.
Enhanced Approach to Develop the International Roughness Index Prediction Model
https://orcid.org/https://orcid.org/0000-0003-4606-4408
Practical methodologies to accurately predict international roughness index (IRI) are still questionable due to the limited IRI historical database and considerable number of factors affecting the IRI. Therefore, this study mainly focused on developing a practical model to accurately predict IRI, based on a big database of historical IRI measurements. The historical IRI data were collected annually from the same testing location between 2014 and 2021, and a total of 1,670,288 IRI measurements were used. Since the pavement age information was unavailable from the collected historical IRI data, this study proposed the enhanced approach for processing historical IRI data to estimate the pavement age of each field section. Then, three IRI prediction models were developed for three road classifications based on the processed historical IRI data, and the developed models only consider pavement age as input to be practical. It was found that the developed models can represent typical behavior of IRI over time. These models were verified by comparing the measured and predicted IRI, and they exhibited good accuracy in predicting IRI values for all road classifications. Therefore, the developed IRI prediction models may be used for pavement management systems (PMS) to provide more insights into the functional conditions of in-service flexible pavements.
Enhanced Approach to Develop the International Roughness Index Prediction Model
Carter, Alan (Herausgeber:in) / Vasconcelos, Kamilla (Herausgeber:in) / Dave, Eshan (Herausgeber:in) / Park, Bongsuk (Autor:in) / Cho, Seonghwan (Autor:in) / Nantung, Tommy E. (Autor:in) / Haddock, John E. (Autor:in)
International Symposium on Asphalt Pavement & Environment ; 2024 ; Montreal, QC, Canada
14th International Conference on Asphalt Pavements ISAP2024 Montreal ; Kapitel: 34 ; 203-208
24.12.2024
6 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
International Roughness Index prediction model for flexible pavements
| Taylor & Francis Verlag | 2020
Dual Model for International Roughness Index Classification and Prediction
| DOAJ | 2025
Prediction of International Roughness Index Based on Stacking Fusion Model
| DOAJ | 2022
Prediction of International Roughness Index Using CatBooster and Shap Values
| Springer Verlag | 2024
Prediction of International Roughness Index Using CatBooster and Shap Values
| Springer Verlag | 2024