基因矿物加工与工艺流程智能决策研究--以铜硫矿物浮选分离为例

杨佳伟 ,  周俊武 ,  王庆凯 ,  朱阳戈 ,  宋振国 ,  邹国斌 ,  高希宇

有色金属(选矿部分) ›› 2026, Vol. 0 ›› Issue (8) : 26 -40.

PDF (5061KB)
有色金属(选矿部分) ›› 2026, Vol. 0 ›› Issue (8) : 26 -40. DOI: 10.20239/j.issn.1671-9492.2026.08.003
基因选矿

基因矿物加工与工艺流程智能决策研究--以铜硫矿物浮选分离为例

作者信息 +

Research on Genetic Mineral Processing and Intelligent Decision-Making for Process Flowsheets:A Case Study on Copper-Sulfide Mineral Flotation Separation

Author information +
文章历史 +
PDF (5182K)

摘要

孙传尧院士提出的“基因矿物加工”理念深刻改变了传统选矿技术的研究范式, 将矿床成因、矿石性质与矿物特性等“基因”特征作为工艺决策的核心依据, 实现了从经验驱动向知识-数据双驱动的范式跃迁。本文以铜硫矿为研究对象, 系统阐述了基因矿物加工的理论与方法体系:基于规则推理(RBR)和案例推理(CBR)构建知识驱动的流程决策框架, 实现原则流程设计与浮选回收率预测;针对高维度-小样本条件下的潜在逻辑关系挖掘问题, 提出基于机器学习的分段建模与多分类决策模型, 完成磨矿制度、选别工艺、药剂制度的个性化推荐;在此基础上, 创新性地构建了“RBR+CBR+ML+LLM”多算法融合决策架构, 通过先验知识补偿解决数据稀疏条件下的泛化难题。试验验证结果表明, 该系统推荐的工艺流程方案与专家设计方案的吻合度达到85%以上, 显著缩短了工艺设计周期并降低了试验成本, 为基因矿物加工从理论走向工程应用提供了技术支撑, 也为选矿工艺的智能化转型开辟了新的路径。

Abstract

The concept of “Genetic Mineral Processing” (GMP) proposed by Academician Sun Chuanyao has profoundly transformed the research paradigm of traditional mineral processing, elevating genetic characteristics-such as ore deposit genesis, ore properties, and mineralogical features-to the core basis for process decision-making. This shift realizes a paradigm transition from experience-driven to knowledge-data dual-driven approaches. Taking copper-sulfide ores as the research object, this paper systematically presents the theoretical framework and methodological system of GMP:a knowledge-driven process decision-making framework is constructed based on Rule-Based Reasoning (RBR) and Case-Based Reasoning (CBR), enabling flowsheet design and flotation recovery prediction. To address the challenge of mining latent logical relationships under high-dimensional, small-sample conditions, a machine learning-based piecewise modeling and multi-classification decision model is proposed for personalized recommendation of grinding regimes, separation stages, and reagent schemes. A novel “RBR+CBR+ML+LLM” multi-modal hybrid decision-making architecture is innovatively developed, which leverages prior knowledge compensation to overcome generalization difficulties in data-sparse scenarios. Industrial validation demonstrates that the process routes recommended by this system achieve over 85% agreement with expert-designed schemes, significantly reducing design cycle time and experimental costs. This work provides technical support for translating GMP from theory to engineering practice and opens a new pathway toward intelligent transformation of mineral processing operations.

关键词

基因矿物加工 / 智能决策 / 知识推理 / 机器学习 / 混合架构 / 铜硫矿

Key words

genetic mineral processing / intelligent decision-making / knowledge reasoning / machine learning / hybrid architecture / copper-sulfide mineral

引用本文

引用格式 ▾
杨佳伟,周俊武,王庆凯,朱阳戈,宋振国,邹国斌,高希宇. 基因矿物加工与工艺流程智能决策研究--以铜硫矿物浮选分离为例[J]. 有色金属(选矿部分), 2026, 0(8): 26-40 DOI:10.20239/j.issn.1671-9492.2026.08.003

登录浏览全文

4963

注册一个新账户 忘记密码

参考文献

[1]

赵杰, 李航谦, 张博文, 等. 矿物加工过程智能化的进展[J]. 生态产业科学与磷氟工程, 2024, 39(11): 75-80.

[2]

Zhao Jie, Li Hangqian, Zhang Bowen, et al. Progress in intelligent mineral processing[J]. Eco-industry Science & Phosphorus Fluorine Engineering, 2024, 39(11): 75-80.

[3]

孙传尧, 周俊武, 贾木欣, 等. 基因矿物加工工程研究[J]. 有色金属(选矿部分), 2018(1): 1-7.

[4]

Sun Chuanyao, Zhou Junwu, Jia Muxin, et al. Research on genetic mineral processing engineering[J]. Nonferrous Metals (Mineral Processing Section), 2018(1): 1-7.

[5]

Moore P, Pham H V. Intelligent context with decision support under uncertainty[C]// 2012 Sixth International Conference on Complex, Intelligent, and Software Intensive Systems. Palermo, Italy, 2012: 977-982.

[6]

Zheng Peng, Liu Dongliang, Guo Junke, et al. A new method for optimizing process parameters of active measurement grinding based on grey target decision making[J]. Proceedings of the Institution of Mechanical Engineers, Part C:Journal of Mechanical Engineering Science, 2020, 234(23): 4645-4658.

[7]

Finnie G, Sun Zhaohao. R 5 model for case-based reasoning[J]. Knowledge-Based Systems, 2003, 16(1): 59-65.

[8]

Sun Zhaohao, Finnie G. A unified logical model for CBR-based e-commerce systems[J]. International Journal of Intelligent Systems, 2005, 20(1): 29-46.

[9]

Gomez-Flores A, Ilyas S, Heyes G W, et al. A critical review of artificial intelligence in mineral concentration[J]. Minerals Engineering, 2022, 189: 107884. DOI: 10.1016/j.mineng.2022.107884.

[10]

Ai Mingxi, Xie Yongfang, Xie Shiwen, et al. Data-driven-based adaptive fuzzy neural network control for the antimony flotation plant[J]. Journal of the Franklin Institute, 2019, 356(12): 5944-5960.

[11]

Ai Mingxi, Xie Yongfang, Tang Zhaohui, et al. Deep learning feature-based setpoint generation and optimal control for flotation processes[J]. Information Sciences, 2021, 578: 644-658.

[12]

Aldrich C, Avelar E, Liu Xiu. Recent advances in flotation froth image analysis[J]. Minerals Engineering, 2022, 188: 107823. DOI: 10.1016/j.mineng.2022.107823.

[13]

Pan Jeff Z, Simon R, Jan-Christoph K, et al. Large language models and knowledge graphs:opportunities and challenges[J]. Transactions on Graph Data and Knowledge, 2023, 1(1): 1-38.

[14]

Pan Shirui, Luo Linhao, Wang Yufei, et al. Unifying large language models and knowledge graphs:a roadmap[J]. IEEE Transactions on Knowledge and Data Engineering, 2024, 36(7): 3580-3599.

[15]

Zhao Mingxiong, Wang Han, Guo Jin, et al. Construction of an industrial knowledge graph for unstructured Chinese text learning[J]. Applied Sciences, 2019, 9(13): 2720. DOI: 10.3390/app9132720.

[16]

Ko H, Witherell P, Lu Yan, et al. Machine learning and knowledge graph based design rule construction for additive manufacturing[J]. Additive Manufacturing, 2021, 37: 101620. DOI: 10.1016/j.addma.2020.101620.

[17]

于宏东, 孙传尧. 不同成因黄铁矿的物性差异及浮游性研究[J]. 中国矿业大学学报, 2010, 39(5): 758-764.

[18]

Yu Hongdong, Sun Chuanyao. Study of divergences of floatability and physical property of pyrite from different geo-genetic deposits[J]. Journal of China University of Mining & Technology, 2010, 39(5): 758-764.

[19]

王海明, 邢运涛, 王瑞丰. 浅谈砂岩型矿矿床地质特征及其成因[J]. 能源与节能, 2014(12): 110-111, 167.

[20]

Wang Haiming, Xing Yuntao, Wang Ruifeng. On the geological characteristics and causes of formation of sandstone-type ore deposits[J]. Energy and Energy Conservation, 2014(12): 110-111, 167.

[21]

刘恩法, 李书文, 刘向阳. 砂岩型铜矿成矿机制分析[J]. 价值工程, 2014, 33(31): 317-318.

[22]

Liu Enfa, Li Shuwen, Liu Xiangyang. Analysis of sandstone type copper mine metallogenic mechanism[J]. Value Engineering, 2014, 33(31): 317-318.

[23]

李德东, 王玉往, 龙灵利, 等. 中国岩浆型铜镍硫化物矿床类型浅谈[J]. 矿产勘查, 2014, 5(2): 124-130.

[24]

Li Dedong, Wang Yuwang, Long Lingli, et al. Discussion on the classification of magmatic type of copper-nickel sulfide deposits in China[J]. Mineral Exploration, 2014, 5(2): 124-130.

[25]

陈述文, 胡熙庚. 黄铁矿化学组成不均匀性与可浮性关系[J]. 湖南有色金属, 1991, 7(5): 278-283.

[26]

Chen Shuwen, Hu Xigeng. Relationship between chemical composition heterogeneity and floatability of pyrite[J]. Hunan Nonferrous Metals, 1991, 7(5): 278-283.

[27]

印万忠. 基于晶体化学的硫化铁矿物浮选特性研究[D]. 沈阳: 东北大学, 2015.

[28]

Yin Wanzhong. Study on flotation characteristics of iron sulfide minerals based on crystal chemistry[D]. Shenyang:Northeastern University, 2015.

[29]

洪秋阳, 汤玉和, 王毓华, 等. 磁黄铁矿结构性质与可浮性差异研究[J]. 金属矿山, 2011, 40(1): 64-67.

[30]

Hong Qiuyang, Tang Yuhe, Wang Yuhua, et al. Investigation on properties and structure of pyrrhotite and the difference of its floatability[J]. Metal Mine, 2011, 40(1): 64-67.

[31]

印万忠, 孙传尧. 硅酸盐矿物浮选原理的研究进展[C]//第四届全国矿山采选技术进展报告会. 张家界, 2001: 138-143.

[32]

Yin Wanzhong, Sun Chuanyao. Research progress on flotation principle of silicate minerals[C]// The 4th National Symposium on Mining and Mineral Processing Technology Progress. Zhangjiajie, 2001: 138-143.

[33]

Wen Shuming, Deng Jiushuai, Xian Yongjun, et al. Theory analysis and vestigial information of surface relaxation of natural chalcopyrite mineral crystal[J]. Transactions of Nonferrous Metals Society of China, 2013, 23(3): 796-803.

[34]

胡岳华, 刘晓文, 邱冠周, 等. 一水硬铝石型铝土矿铝硅浮选分离溶液化学Ⅰ:晶体结构与可浮性[J]. 矿冶工程, 2000, 20(2): 11-14.

[35]

Hu Yuehua, Liu Xiaowen, Qiu Guanzhou, et al. Solution chemistry of flotation separation of diaspore-type bauxite(I):crystal structure and floatability[J]. Mining and Metallurgical Engineering, 2000, 20(2): 11-14.

[36]

陈建华, 冯其明, 卢毅屏. 电化学调控浮选能带模型及应用(Ⅰ)①:半导体能带理论及模型[J]. 中国有色金属学报, 2000, 10(2): 240-244.

[37]

Chen Jianhua, Feng Qiming, Lu Yiping. Energy band model of electrochemical flotation and its application(Ⅰ)①:theory and model of energy band of semiconductor solution interface[J]. The Chinese Journal of Nonferrous Metals, 2000, 10(2): 240-244.

[38]

瞿幼苗. 面向智能决策的推理引擎技术[D]. 西安: 西北工业大学, 2018.

[39]

Qu Youmiao. Key technologies of reasoning engine for intelligient decision[D]. Xi'an:Northwestern Polytechnical University, 2018.

基金资助

国家科技重大专项(2024ZD1002000)

矿冶科技集团有限公司先导计划项目(02-2419)

AI Summary AI Mindmap
PDF (5061KB)

3

访问

0

被引

详细

导航
相关文章

AI思维导图

/

〈 〉