Determining optimal combination of roller compacted concrete pavement mixture containing recycled asphalt pavement and crumb rubber using hybrid artificial neural network–genetic algorithm method considering energy absorbency approach

Abstract

The present study investigates the effectiveness of evolutionary algorithms such as genetic algorithm (GA) evolved neural network in estimating roller compacted concrete pavement (RCCP) characteristics including flexural and compressive strength of RCC and also energy absorbency of mixes with different compositions. A real coded GA was implemented as training algorithm of feed forward neural network to simulate the models. The genetic operators were carefully selected to optimize the neural network, avoiding premature convergence and permutation problems. To evaluate the performance of the genetic algorithm neural network model, Nash-Sutcliffe efficiency criterion was employed and also utilized as fitness function for genetic algorithm which is a different approach for fitting in this area. The results showed that the GA-based neural network model gives a superior modeling. The well-trained neural network can be used as a useful tool for modeling RCC specifications.

Design of Experiment on Concrete Mechanical Properties Prediction: A Critical Review

“…In another study, the ANNs method was compared with Genetic Programming [ 94 ], but the differences in accuracy are indiscernible as both methods produce highly accurate models. However, Chandwani et al [ 100 ] proposed the hybridization of ANN and Genetic Algorithm (GA), which improved the convergence speed and accuracy of the model [ 101 ] and helped in the derivation of optimal result [ 102 ]. ANN-GA is currently not too widely applied in concrete material studies, but has seen usage in complex studies involving more advanced technologies, such as self-healing concrete [ 103 ].…”

Tailoring of Compaction Parameters of the Vibratory Table and Vibratory Hammer for Roller Compacted Concrete Pavements to Resemble Field Properties

“…The ASTM C1176 (19) standard is being followed for specimen fabrication through the VT method, in which cylindrical specimens (150 mm diameter) are molded in three layers with a surcharge load of 9 kg for 20 s or until the formation of a mortar ring on the periphery of surcharge, whichever comes first. However, numerous studies have varied the abovementioned compaction parameters of the VT-the number of layers varied in the range of one to three, and the deployed surcharge load is about 9-22.7 kg (20)(21)(22)(23). Some instances are available wherein the compaction duration is increased up to 60 s to achieve the maximum compactness (22)(23)(24), as evident from Table 1.…”