A Machine Learning driven flow modelling of fragmented rocks in cave mining

机器学习驱动的洞穴采矿中碎石流动建模

• 批准号: LP200100038
• 负责人: A/Prof Murat Karakus
• 金额: $ 36.64万
• 依托单位: The University of Adelaide
• 依托单位国家: 澳大利亚
• 项目类别: Linkage Projects
• 财政年份: 2020
• 资助国家: 澳大利亚
• 起止时间: 2020-07-01 至 2024-06-30
• 项目状态: 已结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/LP200100038
• 关键词: Machine; Learning; driven; flow; modelling

The project aims to develop an integrated method that uses micro scale and macro scale information to predict block scale behaviour so that a better cave mining design can be established. The role of various mineral composition on the energy storage and fracture properties of rocks will be investigated to examine rock fragmentation for block cave mining. Later Machine Learning based models will be developed to establish various predictive models for Block Scale rock mass behaviour and caveability of ore deposit. Finally, we will develop a new constitutive model based on a dual damage concept that will capture the rock fragmentation and simulate the cave propagation in a large scale mine layout using Smoothed-particle hydrodynamics.

该项目旨在开发一种综合方法，利用微观尺度和宏观尺度的信息来预测块体尺度的行为，以便制定更好的洞穴采矿设计。将研究各种矿物成分对岩石的能量储存和断裂特性的作用，以检查块体洞穴采矿的岩石破碎。随后将开发基于机器学习的模型，以建立块体规模岩体行为和矿石存款可崩性的各种预测模型。最后，我们将开发一个新的本构模型的基础上的双重损伤的概念，将捕获岩石破碎和模拟洞穴的传播在一个大规模的矿山布局使用光滑粒子流体动力学。