采用模糊德尔菲法和基于混合人工神经网络的系统相结合的方法对爆破产生的地面振动进行预测。

A combination of fuzzy Delphi method and hybrid ANN-based systems to forecast ground vibration resulting from blasting.

机构信息

School of Mines, China University of Mining and Technology, Xuzhou, 210006, China.

Faculty of Civil and Environmental Engineering, Amirkabir University of Technology, 15914, Tehran, Iran.

出版信息

Sci Rep. 2020 Nov 10;10(1):19397. doi: 10.1038/s41598-020-76569-2.

DOI:10.1038/s41598-020-76569-2

PMID:33173048

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC7656269/

Abstract

This study presents a new input parameter selection and modeling procedure in order to control and predict peak particle velocity (PPV) values induced by mine blasting. The first part of this study was performed through the use of fuzzy Delphi method (FDM) to identify the key input variables with the deepest influence on PPV based on the experts' opinions. Then, in the second part, the most effective parameters on PPV were selected to be applied in hybrid artificial neural network (ANN)-based models i.e., genetic algorithm (GA)-ANN, particle swarm optimization (PSO)-ANN, imperialism competitive algorithm (ICA)-ANN, artificial bee colony (ABC)-ANN and firefly algorithm (FA)-ANN for the prediction of PPV. Many hybrid ANN-based models were constructed according to the most influential parameters of GA, PSO, ICA, ABC and FA optimization techniques and 5 hybrid ANN-based models were proposed to predict PPVs induced by blasting. Through simple ranking technique, the best hybrid model was selected. The obtained results revealed that the FA-ANN model is able to offer higher accuracy level for PPV prediction compared to other implemented hybrid models. Coefficient of determination (R) results of (0.8831, 0.8995, 0.9043, 0.9095 and 0.9133) and (0.8657, 0.8749, 0.8850, 0.9094 and 0.9097) were obtained for train and test stages of GA-ANN, PSO-ANN, ICA-ANN, ABC-ANN and FA-ANN, respectively. The results showed that all hybrid models can be used to solve PPV problem, however, when the highest prediction performance is needed, the hybrid FA-ANN model would be the best choice.

摘要

本研究提出了一种新的输入参数选择和建模程序，以控制和预测矿山爆破引起的峰值粒子速度（PPV）值。本研究的第一部分通过使用模糊德尔菲法（FDM），根据专家意见，确定对 PPV 影响最深的关键输入变量。然后，在第二部分，选择对 PPV 最有效的参数，应用于混合人工神经网络（ANN）模型，即遗传算法（GA）-ANN、粒子群优化（PSO）-ANN、帝国主义竞争算法（ICA）-ANN、人工蜂群（ABC）-ANN 和萤火虫算法（FA）-ANN 来预测 PPV。根据 GA、PSO、ICA、ABC 和 FA 优化技术的最具影响力的参数，构建了许多混合 ANN 模型，并提出了 5 种混合 ANN 模型来预测爆破引起的 PPV。通过简单的排名技术，选择了最佳的混合模型。结果表明，与其他实施的混合模型相比，FA-ANN 模型能够为 PPV 预测提供更高的准确性水平。GA-ANN、PSO-ANN、ICA-ANN、ABC-ANN 和 FA-ANN 的训练和测试阶段的决定系数（R）结果分别为 0.8831、0.8995、0.9043、0.9095 和 0.9133，0.8657、0.8749、0.8850、0.9094 和 0.9097。结果表明，所有混合模型都可用于解决 PPV 问题，但当需要最高的预测性能时，混合 FA-ANN 模型将是最佳选择。