For maximum metal recovery, considering the movement of ore and waste during the blasting process in loading design is meaningful for reducing ore loss and ore dilution in an open-pit mine. The blast-induced rock movement (BIRM) can be directly measured; nevertheless, it is time-consuming and relative expensive. To solve this problem, a novel intelligent prediction model was proposed by using dimensional analysis and optimized artificial neural network technique in this paper based on the BIRM monitoring test in Husab Uranium Mine, Namibia and Phoenix Mine, USA. After using dimensional analysis, five input variables and one output variable were determined with both considering the dimension and physical meaning of each dimensionless variable. Then, artificial neural network technique (ANN) technique was utilized to develop an accurate prediction model, and a metaheuristic algorithm namely the Equilibrium Optimizer (EO) algorithm was applied to search the optimal hyper-parameter combination. For comparison aims, a linear model and a non-linear regression model were also performed, and the comparison results show that the provided hybrid ANN-based model can yield better prediction performance. As a result, it can be concluded that the developed intelligent model in this article has the potential to predict BIRM during bench blasting, and the analysis method and modeling process in this paper can provide a reference for solving other engineering problems.

为了最大程度地回收金属，在装载设计中考虑爆破过程中矿石和废物的移动对于减少露天矿中的矿石损失和矿石稀释是有意义的。爆炸引起的岩石运动（BIRM）可以直接测量。然而，这是耗时且相对昂贵的。为解决这一问题，本文基于BIRM监测试验，在美国纳米比亚Husab铀矿和美国Phoenix矿中，采用尺寸分析和优化的人工神经网络技术，提出了一种新型的智能预测模型。使用维度分析后，在考虑了每个维度和物理含义的情况下，确定了五个输入变量和一个输出变量无量纲变量。然后，利用人工神经网络技术（ANN）建立精确的预测模型，并采用元启发式算法，即均衡优化器（EO）算法搜索最优超参数组合。为了达到比较目的，还建立了线性模型和非线性回归模型，比较结果表明，所提供的基于混合神经网络的混合模型可以产生更好的预测性能。因此，可以得出的结论是，本文开发的智能模型具有预测台阶爆破过程中BIRM的潜力，本文的分析方法和建模过程可为解决其他工程问题提供参考。