A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Artificial neural network modelling to predict international roughness index of rigid pavements
This research focuses on predicting the International Roughness Index (IRI) of rigid pavements using the Artificial Neural Network (ANN) model that uses climate and traffic parameters as inputs. A Long-Term Pavement Performance (LTPP) database is used to extract data from wet-freeze, wet no-freeze, dry-freeze, and dry no-freeze climatic zones. The climate and traffic parameters are Mean Annual Air Temperature, Annual Average Freezing Index, Annual Average Maximum and Minimum Humidity, Annual Average Precipitation, Annual Average Daily Traffic, and Annual Average Daily Truck Traffic. The ANN model is trained with 70% of climate, traffic and IRI data, rest 15% data is used to test the model, and remaining 15% data is used to validate the model. The trained and the validated models are compared by calculating Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). Among many results, the datasets that are tested with 7–9–9–1 ANN structure with hyperbolic tangent sigmoidal transfer function generated the best prediction models with an RMSE value of 0.01 and MAPE value of 0.01 (1% error) for a rigid pavement located in the wet no-freeze climatic zone.
Artificial neural network modelling to predict international roughness index of rigid pavements
This research focuses on predicting the International Roughness Index (IRI) of rigid pavements using the Artificial Neural Network (ANN) model that uses climate and traffic parameters as inputs. A Long-Term Pavement Performance (LTPP) database is used to extract data from wet-freeze, wet no-freeze, dry-freeze, and dry no-freeze climatic zones. The climate and traffic parameters are Mean Annual Air Temperature, Annual Average Freezing Index, Annual Average Maximum and Minimum Humidity, Annual Average Precipitation, Annual Average Daily Traffic, and Annual Average Daily Truck Traffic. The ANN model is trained with 70% of climate, traffic and IRI data, rest 15% data is used to test the model, and remaining 15% data is used to validate the model. The trained and the validated models are compared by calculating Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). Among many results, the datasets that are tested with 7–9–9–1 ANN structure with hyperbolic tangent sigmoidal transfer function generated the best prediction models with an RMSE value of 0.01 and MAPE value of 0.01 (1% error) for a rigid pavement located in the wet no-freeze climatic zone.
Artificial neural network modelling to predict international roughness index of rigid pavements
Int. J. Pavement Res. Technol.
Hossain, Mohammad (author) / Gopisetti, Leela Sai Praveen (author) / Miah, Md. Suruz (author)
International Journal of Pavement Research and Technology ; 13 ; 229-239
2020-05-01
11 pages
Article (Journal)
Electronic Resource
English
| British Library Conference Proceedings | 2013