Automated monitoring and evaluation of highway subgrade compaction quality using artificial neural networks

The compaction quality of a highway subgrade is influenced by the compaction parameters and soil properties. Current practice lacks reliable models to assess this multivariate situation. This paper describes a monitoring and evaluation method based on intelligent compaction (IC) and artificial neural networks (ANNs) to assess the compaction quality of a highway subgrade. Field compaction tests were conducted at various roller speeds and vibratory modes. The compactness was predicted using a particle-swarm-optimization optimized backpropagation neural network (PSO-BP-NN) model. The model was integrated into the IC system to automatically evaluate compaction quality. It also demonstrated the advantage of high prediction accuracy with multiple input variables of operation parameters and soil gradation. By efficiently controlling subgrade compaction, the model can be employed for engineering practice and facilitate IC applications. • An advanced ANN model is proposed to evaluate the compaction quality. • Four compaction modes are identified to characterize different compaction parameters. • The particle gradation is an influential factor and is integrated into the correlation model. • The proposed evaluation model demonstrates a good generalization for different scenarios.