基于CART模型的高铁灰渣玻璃形成能力研究

硅酸盐通报 ›› 2024, Vol. 43 ›› Issue (9): 3330-3336.

基于CART模型的高铁灰渣玻璃形成能力研究

王伟¹, 方广¹, 陈祎², 张乾生², 徐凯¹

1.武汉理工大学硅酸盐建筑材料国家重点实验室,武汉 430070;
2.中广核环保产业有限公司,深圳 518028

收稿日期:2024-01-10 修订日期:2024-03-15 出版日期:2024-09-15 发布日期:2024-09-19
通信作者: 徐凯,博士,研究员。E-mail:kaixu@whut.edu.cn
作者简介:王伟(1997—),男,硕士研究生。主要从事危险废物玻璃固化的研究。E-mail:2977885359@qq.com
基金资助:
湖北省重点研发计划(2022BCA070)

Investigation of Glass-Forming Ability of High-Fe Ash Based on CART Model

WANG Wei¹, FANG Guang¹, CHEN Yi², ZHANG Qiansheng², XU Kai¹

1. State Key Laboratory of Silicate Materials for Architectures, Wuhan University of Technology, Wuhan 430070, China;
2. China General Nuclear Power Environmental Protection Industry Co., Ltd., Shenzhen 518028, China

Received:2024-01-10 Revised:2024-03-15 Published:2024-09-15 Online:2024-09-19

摘要/Abstract

摘要： 固化技术是极具前景的危废无害化与资源化处理技术,而高铁类危废灰渣铁含量高,易诱发玻璃体产物析晶或分相,这成为固化过程的难点之一。本文依据高铁类危废灰渣组成,采用极端顶点设计方法,设计了385个SiO₂-Al₂O₃-CaO-Na₂O-TiO₂-Fe₂O₃体系玻璃配伍,并通过光学显微镜、X射线衍射及酸溶试验,确定其中136个配伍可形成化学稳定性良好的玻璃态样品。结合决策树(CART)模型分析,确定了具有优化玻璃形成能力的高铁类危废灰渣玻璃化配伍范围(按质量分数w计):40.0%≤w(SiO₂)≤55.0%、10.0%≤w(CaO)<14.0%、14.0%≤w(Na₂O)≤18.0%、5.0%≤w(Other)<9.5%或35.0%≤w(SiO₂)<40.0%、9.0%≤w(TiO₂)≤10.0%、5.0%≤w(Other)<9.5%,为高铁类危废灰渣的玻璃化配伍提供了设计与计算依据。

关键词: 危险废物, 固化, 玻璃形成能力, 玻璃化配伍, CART模型

Abstract: Vitrification technology is a promising method for hardless and resourceful treatment of hazardous waste. However, the vitrification of high-Fe hazardous waste ash is difficult due to its high-Fe content, which can lead to the crystallization or phase separation of glass. In this paper, based on the composition of high-Fe hazardous waste ash, 385 glass formulations with SiO₂-Al₂O₃-CaO-Na₂O-TiO₂-Fe₂O₃ systems were designed using extreme vertices design method. Optical microscopy, X-ray diffraction and acid dissolution test were employed to identify 136 formulations to form glass samples exhibiting excellent chemical durability. Based on CART model analysis, the study determines the range of glass formulation for high-Fe hazardous waste ash with optimal glass-forming ability, in mass fraction (w): 40.0%≤w(SiO₂)≤55.0%, 10.0%≤w(CaO)<14.0%, 14.0%≤w(Na₂O)≤18.0%, 5.0%≤w(Other)<9.5% or 35.0%≤w(SiO₂)<40.0%, 9.0%≤w(TiO₂)≤10.0%, 5.0%≤w(Other)<9.5%. The research in this paper provides design and computation for glass vitrification of high-Fe hazardous waste ash.

Key words: hazardous waste, vitrification, glass-forming ability, glass formulation, CART model

中图分类号:

TQ171

王伟, 方广, 陈祎, 张乾生, 徐凯. 基于CART模型的高铁灰渣玻璃形成能力研究[J]. 硅酸盐通报, 2024, 43(9): 3330-3336.

WANG Wei, FANG Guang, CHEN Yi, ZHANG Qiansheng, XU Kai. Investigation of Glass-Forming Ability of High-Fe Ash Based on CART Model[J]. BULLETIN OF THE CHINESE CERAMIC SOCIETY, 2024, 43(9): 3330-3336.

参考文献

[1] FAZZO L, MINICHILLI F, SANTORO M, et al. Hazardous waste and health impact: a systematic review of the scientific literature[J]. Environmental Health, 2017, 16(1): 107.
[2] LIU H M, LI S, GUO G Z, et al. Ash formation and the inherent heavy metal partitioning behavior in a 100 t/d hazardous waste incineration plant[J]. The Science of the Total Environment, 2022, 814: 151938.
[3] 雷洪鸣, 陈祎, 贾瑞东, 等. 垃圾焚烧飞灰与玻璃添加剂熔融固化物相转变研究[J]. 应用化工, 2023, 52(7): 2084-2087+2092.
LEI H M, CHEN Y, JIA R D, et al. Phase transitions of MSWI fly ash and glass additives during vitrification[J]. Applied Chemical Industry, 2023, 52(7): 2084-2087+2092 (in Chinese).
[4] SONG W F, ZHU Z W, CAO J W, et al. The effect of sulfur on the leaching of Cr³⁺, Cr⁶⁺, Pb²⁺ and Zn²⁺ from fly ash glass[J]. Chemosphere, 2022, 305: 135387.
[5] SANITO R C, BERNUY-ZUMAETA M, YOU S J, et al. A review on vitrification technologies of hazardous waste[J]. Journal of Environmental Management, 2022, 316: 115243.
[6] 徐凯. 核废料玻璃固化国际研究进展[J]. 中国材料进展, 2016, 35(7): 481-488+517.
XU K. Review of international research progress on nuclear waste vitrification[J]. Materials China, 2016, 35(7): 481-488+517 (in Chinese).
[7] LONG Y Y, SONG Y H, YANG Y Q, et al. Co-vitrification of hazardous waste incineration fly ash and hazardous waste sludge based on CaO-SiO₂-Al₂O₃ system[J]. Journal of Environmental Management, 2023, 338: 117776.
[8] 胡佳慧, 郑洋, 孙聪聪, 等. 危险废物焚烧飞灰玻璃化产物危险特性[J]. 环境科学研究, 2018, 31(8): 1450-1456.
HU J H, ZHENG Y, SUN C C, et al. Fly ash from hazardous waste incineration: vitrification and hazardous characteristics[J]. Research of Environmental Sciences, 2018, 31(8): 1450-1456 (in Chinese).
[9] LI B, WANG Y Y, LUO W Q, et al. Effects of Fe₂O₃ on the crystallization and structure of CaO-Fe₂O₃-SiO₂ glass ceramics[J]. Journal of Radioanalytical and Nuclear Chemistry, 2017, 314(3): 1619-1625.
[10] YU S, LI X F, WANG H C, et al. C_CART: an instance confidence-based decision tree algorithm for classification[J]. Intelligent Data Analysis, 2021, 25(4): 929-948.
[11] RAY C S, SAMARANAYAKE V A, MOHAMMADKHAH A, et al. Iron phosphate glass waste forms for vitrifying Hanford AZ102 low activity waste (LAW), part I: glass formation model[J]. Journal of Non-Crystalline Solids, 2017, 458: 149-156.
[12] SHARIFIKOLOUEI E, BAINO F, SALVO M, et al. Vitrification of municipal solid waste incineration fly ash: an approach to find the successful batch compositions[J]. Ceramics International, 2021, 47(6): 7738-7744.
[13] SHENG J W, LUO S G, TANG B L. Vitrification of borate waste generated by nuclear power plants[J]. Nuclear Technology, 1999, 125(1): 85-92.
[14] 国家市场监督管理总局, 国家标准化管理委员会. 固体废物玻璃化处理产物技术要求: GB/T 41015—2021[S]. 北京: 中国标准出版社, 2021.
State Administration for Market Regulation, Standardization Administration. Technical requirements for solid waste vitrification product: GB/T 41015—2021[S]. Beijing: Standards Press of China, 2021 (in Chinese).
[15] GHIASI M M, ZENDEHBOUDI S, MOHSENIPOUR A A. Decision tree-based diagnosis of coronary artery disease: cart model[J]. Computer Methods and Programs in Biomedicine, 2020, 192: 105400.
[16] CHOUBIN B, ZEHTABIAN G, AZAREH A, et al. Precipitation forecasting using classification and regression trees (CART) model: a comparative study of different approaches[J]. Environmental Earth Sciences, 2018, 77(8): 314.
[17] STROBL C, MALLEY J, TUTZ G. An introduction to recursive partitioning: rationale, application, and characteristics of classification and regression trees, bagging, and random forests[J]. Psychological Methods, 2009, 14(4): 323-348.
[18] SHINKEVICH A I, ERSHOVA I G, GALIMULINA F F, et al. Innovative mesosystems algorithm for sustainable development priority areas identification in industry based on decision trees construction[J]. Mathematics, 2021, 9(23): 3055.
[19] 庄锐, 张浩. 基于平均特征重要性和集成学习的异常检测[J]. 计算机系统应用, 2023, 32(6): 60-69.
ZHUANG R, ZHANG H. Anomaly detection based on average feature importance and ensemble learning[J]. Computer Systems and Applications, 2023, 32(6): 60-69 (in Chinese).