Prediction of highway asphalt pavement performance based on Markov chain and artificial neural network approach
Department of Civil and Environmental Engineering
In order to study the problems of inadequate maintenance measures, inappropriate maintenance time, and unreasonable use of funds in asphalt pavement maintenance of Highway in China, the maintenance of highway pavement is taken as the research object in this study, and a prediction model is established for preventive maintenance performance of highway by using neural network. Firstly, the performance of pavement is evaluated. The pavement performance prediction model is studied, and some mature prediction models are introduced. It is concluded that for the early built highways, the models are used when the acceptance of maintenance and preventive maintenance concepts is poor and the pavement performance shows a decreasing trend, but for the existing maintenance and preventive maintenance sections, the pavement performance detection shows a wave. The dynamic descent section is not suitable. The results show that the forecasting model proposed in this study is consistent with the development trend of the measured results, and can be used to predict the pavement performance under this model. Therefore, a theoretical basis is provided for the investment of highway maintenance funds and the scientific selection of maintenance schemes. The study has important guiding significance for the future highway management units in the selection of maintenance measures, the determination of maintenance timing, and the size of capital investment.
Journal of Supercomputing
Prediction of highway asphalt pavement performance based on Markov chain and artificial neural network approach.
Journal of Supercomputing.
Retrieved from: https://digitalcommons.mtu.edu/michigantech-p/2040