资源利用与能耗约束下铁矿采选品位的智能优化  

Intelligent Optimization of Mining& Milling Grades in Iron Mine Under the Constraints of Resource Utilization and Energy Consumption

作　　者：贺勇[1] 廖诺[1] HE Yong LIAO Nuo(School of Management, Guangdong University of Technology, Guangzhou 510520, China)

机构地区：[1]广东工业大学管理学院,广东广州510520

出　　处：《运筹与管理》2016年第5期88-94,共7页Operations Research and Management Science

基　　金：国家自然科学基金项目(71303061;71301030);教育部人文社科研究项目(11YJCZH057)

摘　　要：集成非线性目标规划模型与差分进化(DE)及神经网络(ANN)等智能算法,提出了资源利用和节能降耗约束下铁矿采选生产品位的动态优化方法。首先建立以截止品位和入选品位为决策变量,精矿产量、资源利用率、总用电量以及经济效益为目标约束的非线性目标规划模型,模型中包括损失率、选矿金属回收率和采选成本三个非线性函数;然后将所构建的非线性目标规划模型转化成无约束优化问题,将DE的高效寻优能力和ANN的建模功能相结合,构成DE-ANN算法来搜索最优采选品位组合;最后以D铁矿为例进行研究,结果表明了所提出方法的有效性。该方法综合考虑了资源利用、节能降耗等因素,为新时期铁矿的采选品位优化提供了科学可行的思路。The method of dynamic optimization of mining ＆ milling grades is proposed under the constraints of theresource utilization and energy consumption, by integrating nonlinear goal programming （NGP） model and theintelligent algorithms of differential evolution （DE） and artificial neural network （ANN）. First, the nonlinear goalprogramming model is established, with cut-off grade and dressing grade as decision variables, and concentrateproduction, resource utilization rate, total electricity consumption and economic benefit as goal constraints. TheNGP model contains three nonlinear functions which are loss rate function, milling metal recovery rate functionand the cost function. Then the NGP model is transformed into unconstrained optimization problem. Consideringthe advantage optimization ability of DE and modeling function of ANN, the DE and ANN are combined to theDE-ANN algorithm, to search the optimal grades combination. Finally, taking D Iron Mine as a ease study, theresult shows the validity of the proposed method. Taking into consideration of the resource utilization and energyconsumption, the proposed method provides a scientific and feasible idea for grades optimization.

关 键 词：采选品位 智能优化 非线性目标规划 资源利用 能耗 

分 类 号：F224.31[经济管理—国民经济]