Search

Backcalculation of pavement layer moduli refers to the process of evaluating the pavement layers using pavement surface deflections. The genetic algorithm (GA) technique was successfully used in the past for backcalculation. The BACKGA model developed by the Indian Institute of Technology, Kharagpur is one such program used for backcalculation using the GA technique. Though GA-based backcalculation models are considered to be robust due to the search algorithm adopted in the process, they require more computational time due to the large number of times the surface deflections are computed using different sets of layer moduli. In the present work, artificial neural network (ANN) models have been developed for computing surface deflections using elastic moduli and thicknesses of pavement layers as inputs. The ANN models have been used in BACKGA for forward calculation of surface deflections to combine the computational efficiency of ANNs with the robustness of the GAs. The performance of the resulting model, BACKGA–ANN, has been evaluated and found to be satisfactory. [ABSTRACT FROM AUTHOR]

In the context of pavement evaluation, backcalculation is the process of estimation of elastic properties of pavement layers using measured structural responses. A number of backcalculation programs are available for estimating effective pavement layer moduli from surface deflections. Different optimization techniques have been used in the development of these backcalculation models. Genetic algorithm (GA) has been used successfully in the recent past for backcalculation of pavement layer moduli. Selection of appropriate GA parameters is important for the efficient performance of the GA-based algorithm. However, there are no general guidelines available at present for the selection of GA parameters. This paper presents a study conducted for the selection of optimal GA parameters to be adopted for backcalculation of pavement layer moduli. The parameters have been selected on the basis of the level of accuracy desired and the corresponding computational effort (CE). The performance of the GA-based program with the selected parameters was evaluated using some hypothetical and field problems. [ABSTRACT FROM AUTHOR]