Artificial Neural Network-Based Method for Real-Time Estimation of Compaction Quality of Hot Asphalt Mixes

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.