Modelling pavement performance is important to pavement asset management and to roadway safety and sustainability. While neural networks (NNs) have been employed to establish pavement performance models, past studies have mainly focused on achieving high model accuracy and generally failed to examine other model properties. This study calibrated feedforward neural networks with particle swarm optimization (PSO) to predict the rutting performance of asphalt pavement in the State of Idaho. The resulting models provided rutting predictions with higher accuracy than traditional mechanistic-empirical models. This study also employed various statistical methods in the pre-processing and post-analysis of PSO-NNs, such as the principal component analysis in the input selection and hypothesis tests in the model reproducibility and robustness evaluation. This study further explored the relationships between the model accuracy and updating efficiency and the number of calibrated parameters (hidden neurons). The selected PSO-NN structure struck the right balance between model accuracy, reproducibility and robustness of the models.
An Accurate, Reproducible and Robust Model to Predict the Rutting of Asphalt Pavement: Neural Networks Coupled With Particle Swarm Optimization
IEEE Transactions on Intelligent Transportation Systems ; 23 , 11 ; 22063-22072
2022-11-01
3024757 byte
Article (Journal)
Electronic Resource
English
Asphalt Pavement Rutting - Western States
NTIS | 1984
|Suitability of Asphalt Pavement Analyzer for Predicting Pavement Rutting
Transportation Research Record | 2000
|Suitability of Asphalt Pavement Analyzer for Predicting Pavement Rutting
British Library Conference Proceedings | 2000
|Statistical Model of Pavement Rutting in Asphalt Concrete Mixes
Transportation Research Record | 2001
|