Novel Extreme Learning Machine-Multi-Verse Optimization Model for Predicting Peak Particle Velocity Induced by Mine Blasting

Peak particle velocity (PPV) is an important criterion for assessing the risk level of ground vibration induced by mine blasting. Based on this criterion, many efforts to predict accurately and mitigate PPV have been studied. In this paper, a novel integration approach based on the extreme learning machine (ELM) and multi-verse optimization (MVO), named the MVO-ELM model, was proposed to predict PPV. MVO was applied to initialize the number of populations and optimize the weights of the ELM model. For this, 137 blasting events in a copper mine in China with blasting parameters and rock properties were collected to test the proposed model. They were then divided into training and testing subsets for developing and testing the model, respectively. Different training/testing ratios of data subsets (e.g., 80/20 and 70/30), different topology networks (e.g., 22 neurons and 25 neurons), and various activation functions (e.g., elu, relu, tanh, and sigmoid) were considered to determine the best data subset ratio and topology network of the proposed model. To evaluate the enhanced accuracy of the proposed MVO-ELM, the traditional ELM, multi-perceptron (MLP) neural network, and the USBM (United States Bureau of Mines) models were applied to predict PPV for comparison with the optimized MVO-ELM model. The results revealed that the MVO-ELM model was the best one, with data subset ratio of 80/20, topology network with 25 hidden neurons, and elu activation function. The performance metrics also indicated that the optimized MVO-ELM model provided high-caliber performance compared with the ELM, MLP, and USBM models, i.e., RMSE (root-mean-squared error) = 0.196 and 0.374, R-2 (determination coefficient) = 0.980 and 0.943, MAPE (mean absolute percentage error) = 0.206 and 0.670, VAF (variance accounted for) = 98.048 and 94.350, on the training and testing data subsets, respectively. Moreover, the accuracy of the optimized MVO-ELM model was improved by approximately 36% compared to the traditional ELM model. In contrast, the ELM, MLP, and USBM yielded lower performances, i.e., RMSE = 0.846, 0.657, 1.008, R-2 = 0.638, 0.782, 0.558, MAPE = 1.242, 0.653, 0.691, and VAF = 63.787, 78.126, 53.406, on the training dataset; RMSE = 1.020, 0.718, 0.834, R-2 = 0.619, 0.827, 0.815, MAPE = 1.219, 1.090, 0.868, and VAF = 58.284, 79.191, 75.565, on the testing data subset. The results also revealed that the maximum explosive charged per delay, monitoring horizontal distance, and rock mass integrity coefficient significantly affected PPV predictions.

Automated summary

Peak particle velocity (PPV) is a crucial criterion in assessing ground vibration risk from mine blasting. A novel MVO-ELM model was proposed, using MVO to optimize ELM weights. The optimized model outperformed traditional ELM, MLP, and USBM models, with significant factors affecting PPV predictions identified as explosive charges, monitoring distance, and rock properties.