Optimization of Neural-Network Models Using a Meta-Heuristic Algorithm for the Estimation of Dynamic Poisson’s Ratio of Selected Rock Types

Abstract

Abstract This research investigates the dynamic behavior of rocks subjected to excitation frequencies at ambient condition. The dynamic response of rocks was evaluated in terms of quality factor (Q), resonance frequency (FR), acoustic impedance (Z), oscillation decay factor (α), and dynamic Poisson’s ratio (v). These parameters were measured in both longitudinal and torsion modes. Their ratios were taken to reduce data variability and make them dimensionless for analysis. Results showed that with the increase in excitation frequencies, the stiffness of the rocks got increased because of plastic deformation of pre-existing cracks and then started to decrease due to the development of new microcracks. After the evaluation of the behavior of the rocks, the v was estimated by the prediction modeling. Overall, 15 models were developed by using the backpropagation neural network algorithms including feed-forward, cascade-forward, and Elman. Among all models, the feed-forward model with 40 neurons was considered as best one due to its comparatively good performance in the learning and validation phases. The values of its Pearson correlation coefficient (R = 0.885) and coefficient of determination (R2 = 0.797) were estimated higher than the rest of the models. To further improve its quality, the model was optimized using the particle swarm optimization (PSO) algorithm. The optimizer ameliorated its R and R2 values from 0.885 to 0.980 and 0.797 to 0.954 respectively. The outcomes of this study exhibit the effective utilization of a meta-heuristic algorithm to improve model quality that can be used as a reference to solve several problems regarding data modeling, pattern recognition, data classification, etc.