With the advancement of intelligent compaction technology, real-time quality control has been widely investigated on the subgrade, while it is insufficient on asphalt pavement. This paper aims to estimate the real-time compaction quality of hot mix asphalt (HMA) using an artificial neural network (ANN) classifier. A field experiment of HMA compaction was designed. The vibration patterns of the drum were identified by using the ANN classifier and classified based on the compaction levels. The vibration signals were collected and the degree of compaction was measured in the field experiment. The collected signals were processed and the features of vibration patterns were extracted. The processed signals were tagged with their corresponding compaction level to form the sample dataset to train the ANN models. Four ANN models with different hidden layer setups were considered to investigate the effect of hidden layer structure on performance. To test the performance of the ANN classifier, the predictions made by ANN were compared with the measuring results from a non-nuclear density gauge (NNDG). The testing results show that the ANN classifier has good performance and huge potential for estimating the compaction quality of HMA in real-time.

The primary goal of this study is to find an easy and convenient way to estimate the degree of compaction in real time for compaction quality control. In this paper, an artificial neural network classifier is developed to identify the different characteristic patterns of drum vibration and classify them according to the different compaction levels. At first, a field compaction experiment is designed and performed in a construction site, and the degree of compaction and the vibration are measured. Then, the vibration signals collected from the experiment are processed to extract the features of vibration patterns and labeled with the compaction level to train the artificial neural network model. At last, the performance of the artificial neural network classifier is verified against the degree of compaction measured by using a nuclear density gauge. It can be found that artificial neural networks show good performance and huge potential for the problem of compaction quality control.