Development of steel-slag-based cementitious material and optimization of slurry ratio based on genetic algorithm and support vector machine (GA?SVM)
-
摘要: 針對某露天轉地下礦山充填成本高的問題，充分利用礦山周邊的工業廢棄物開發滿足嗣后充填采礦法所要求的充填膠凝材料，并對充填料漿的配比進行了優化。首先，分析了材料的物化特性，采用不同的激發配方進行了室內試驗，構建了用于鋼渣基膠凝材料配方預測的GA?SVM模型，確定了鋼渣基膠凝材料的最佳配方（質量分數）為：鋼渣30%、脫硫石膏4%、水泥熟料12%、芒硝1%；其次采用XRD和SEM分析了鋼渣基膠凝材料的水化機理；最后基于灰靶多目標決策模型對料漿配比進行優化實驗，以強度（7 d和28 d）、工作特性（坍落度、泌水率）、成本為指標優化料漿配比。結果表明，采用新型鋼渣基膠凝材料，充填料漿的最佳配比參數為：灰砂比1∶4，固相質量分數為72%。并進行了驗證實驗，得到相應強度參數和工作特性參數分別為1.74 MPa、3.61 MPa、24.2 cm和5.91%，均滿足嗣后充填的要求，此配比條件下的充填成本為每立方米113元，較水泥充填成本降低了38.92%。Abstract: To address the problem of high filling cost in an open pit to an underground mine, based on the machine learning method, the filling cementitious material needed for subsequent backfill mining method was developed using the available industrial wastes around the mine, and the ratio of filling slurry was optimized. First, the physical and chemical properties of the materials were analyzed. Unconfined compressive strength tests were conducted with different activator formulations to analyze the influence of each component on the strength of the backfill body. A genetic algorithm and support vector machine (GA?SVM) model was established to predict the steel-slag-based cementitious material formula using the experimental data, and the optimal ratio was determined based on the model prediction results. X-ray diffraction (XRD) and scanning electron microscope (SEM) were used to analyze the hydration products and microstructure characteristics of steel-slag-based cementitious materials at different curing ages and slag dosage conditions and determine the hydration mechanism of steel-slag-based cementitious materials. Finally, the slurry proportion was optimized by strength (i.e., 7 and 28 days) and working characteristics (i.e., slump and bleeding rate) based on the principle of gray target decision. Results revealed that the relative errors of the GA?SVM model for predicting the steel-slag-based cementitious materials strength at 7 and 28 days are 3.6%–12.62% and 6.9%–10.19%, respectively, thereby indicating high prediction accuracy. The optimal proportion of steel-slag-based cementitious materials determined by prediction analysis is steel slag content of 30%, desulfurized gypsum content of 4%, cement clinker content of 12%, and mirabilite content of 1%. The main hydration products of steel-slag-based cementitious materials are amorphous C?S?H gel, ettringite, tricalcium aluminate hydrate, Ca(OH)2, and CaCO3. The calcium hydroxide content increases with the steel slag content, which generates a large number of pores and deteriorates the structure and strength of the sample. When the new steel-slag-based cementitious material is applied to the actual backfilling of the mine, the optimal ratio parameters of filling slurry are obtained through the optimization of the model of the gray target decision (i.e., cement?sand ratio of 1∶4 and mass concentration of 72%). Corresponding verification experiments were conducted, and the corresponding strength and working characteristic parameters were 1.74 MPa, 3.61 MPa, 24.2 cm, and 5.91%, which all met the requirements of subsequent filling. With this proportion, the filling cost is 113 ￥·m?3, which is 38.92% lower than that of the cement filler. The research results will benefit the comprehensive utilization of solid waste and provide support for safe, clean, and efficient mining.
-
圖 2 遺傳算法優化示意圖. (a) 遺傳算法; (b) 試驗流程
Figure 2. Schematic of genetic algorithm optimization: (a) genetic algorithm; (b) test process
圖 3 單因素影響下鋼渣基膠凝材料強度試驗的極差分析結果. (a) 熟料及脫硫石膏摻量（7 d）; (b) 熟料及脫硫石膏摻量（28 d）; (c) 芒硝摻量; (d) 鋼渣摻量
Figure 3. Range analysis results of the strength test of steel-slag-based cementitious materials under the single factor: (a) clinker and desulfurization gypsum content (7 d); (b) clinker and desulfurization gypsum content (7 d); (c) mirabilite content; (d) steel slag content
圖 5 GA?SVM模型訓練集測試結果對比
Figure 5. Comparison of the test results of the GA?SVM model training set
圖 6 28 d強度預測結果. (a)固定熟料摻量12%、芒硝摻量0.5%; (b)固定鋼渣摻量30%、脫硫石膏摻量4%
Figure 6. Results of 28 d strength prediction: (a) fixed clinker content of 12% and mirabilite content of 0.5%; (b) fixed steel slag content of 30% and desulfurized gypsum content of 4%
圖 7 7 d強度預測結果. (a) 固定脫硫石膏摻量4%、芒硝摻量1.0%; (b) 固定鋼渣摻量30%、熟料摻量12%
Figure 7. Results of 7 d strength prediction: (a) fixed desulfurized gypsum content of 4% and mirabilite content of 1.0%; (b) fixed steel slag content of 30% and clinker content of 12%
圖 8 水化產物X射線衍射分析. (a)不同養護齡期的水化產物; (b)不同鋼渣摻量的28 d水化產物
Figure 8. X-ray diffraction analysis of hydration products: (a) hydration products with different curing ages; (b) 28 d hydration products with different steel slag contents
圖 9 不同鋼渣摻量試塊的28 d水化產物微觀形貌
Figure 9. Microstructure of 28 d hydration products of test blocks with different steel slag contents
圖 10 固相質量分數對料漿性能的影響. (a) 7 d強度; (b) 28 d 強度; (c) 塌落度; (d) 泌水率
Figure 10. Effect of solid concentration on paste properties: (a) 7 d curing age; (b) 28 d curing age; (c) slump; (d) bleeding rate
表 1 實驗材料化學成分組成（質量分數）
Table 1. Main chemical components of the backfill material
% TFe FeO SiO2 CaO MgO Al2O3 MnO S P Ignition loss 8.92 6.26 67.75 3.44 4.78 1.48 0.31 0.25 0.074 1.12 
下載: 導出CSV
表 2 活性材料的化學成分組成（質量分數）
Table 2. Main chemical components of the active material
% Active materials SiO2 CaO MgO Al2O3 Fe2O3 S SO3 MFe Steel slag 16.52 42.74 9.96 12.72 16.30 0 — 0.02 Slag 35.15 43.46 7.57 12.15 — 1.24 —
下載: 導出CSV
表 3 水泥熟料的化學成分組成（質量分數）
Table 3. Main chemical components of the cement clinker
% SiO2 CaO MgO Al2O3 Fe2O3 FeO SO3 Na2O Other Ignition loss 22.5 66.3 0.83 4.86 3.43 0.02 0.31 0 0.79 0.96
下載: 導出CSV
表 4 激發劑配方試驗結果
Table 4. Test results of the activator formulations
Formulation No. Clinker mass fraction/% Desulfurization gypsum mass fraction /% Mirabilite mass fraction /% Active material mass fraction /% Uniaxial compressive strength (UCS)/MPa Steel slag Slag 7 d 28 d More clinker less salt 1 12 2 0 10 76 1.83 3.47 2 12 4 0.5 20 63.5 1.57 3.19 3 12 6 1 30 51 1.34 2.65 4 14 2 0.5 30 53.5 1.06 2.93 5 14 4 1 10 71 1.59 3.98 6 14 6 0 20 60 1.45 3.15 7 16 2 1 20 61 1.24 3.46 8 16 4 0 30 50 1.04 3.02 9 16 6 0.5 10 67.5 1.42 4.25 More salt less clinker 10 2 8 0 10 80 1.12 2.83 11 2 12 0.5 20 65.5 0.88 2.12 12 2 16 1 30 51 0.95 1.29 13 4 8 0.5 30 57.5 0.75 2.12 14 4 12 1 10 73 1.29 2.72 15 4 16 0 20 60 0.92 2.04 16 6 8 1 20 65 0.94 2.62 17 6 12 0 30 52 0.61 1.69 18 6 16 0.5 10 67.5 1.32 3.46 More salt more clinker 19 9 6 0 10 75 1.28 3.32 20 9 8 0.5 20 62.5 1.11 3.45 21 9 10 1 30 50 0.91 2.51 22 11 6 0.5 30 52.5 1.15 2.82 23 11 8 1 10 70 1.45 3.61 24 11 10 0 20 59 1.34 2.83 25 13 6 1 20 60 1.36 3.13 26 13 8 0 30 49 1.19 2.89 27 13 10 0.5 10 66.5 1.52 3.51
下載: 導出CSV
表 5 測試集預測結果的相對誤差
Table 5. Relative error of the test set prediction results
No. 7 d strength 28 d strength Forecast result/MPa Test results/MPa Relative error/% Forecast result/MPa Test results/MPa Relative error/% 5 1.77 1.59 11.1 4.39 3.98 10.19 10 1.22 1.12 8.81 3.04 2.83 7.41 11 0.99 0.88 12.62 2.31 2.12 8.79 15 0.95 0.92 3.6 2.15 2.04 5.61 18 1.42 1.32 7.63 3.70 3.46 6.9 22 1.07 1.15 7.28 3.07 2.82 8.8
下載: 導出CSV
表 6 充填料漿配比試驗結果
Table 6. Test results of the filling slurry
No. Cement–sand ratio Solid concentration/% Uniaxial compressive strength/MPa Slump/cm Bleeding rate/% Cost/￥ 7 d 28 d A1 1∶4 68 1.16 2.66 26.2 9.4 109 A2 70 1.34 2.95 24.9 7.2 111 A3 72 1.82 3.53 23.6 6.3 113 A4 1∶6 68 0.85 2.36 26.4 10.8 86 A5 70 1.14 2.53 25.3 9.5 88 A6 72 1.29 3.12 24.1 7.4 90 A7 1∶8 68 0.51 2.15 27.1 12.3 71 A8 70 0.63 2.25 26.2 11.6 73 A9 72 0.83 2.72 25.1 9.1 75
下載: 導出CSV
表 7 充填料漿配比方案灰靶決策結果
Table 7. Grey target decision-making results of filling slurry ratio plan
Scheme e A1 2.9 A2 1.17 A3 0.238 A5 1.783 A6 0.44
下載: 導出CSV
www.77susu.com<span id="fpn9h"><noframes id="fpn9h"><span id="fpn9h"></span> <span id="fpn9h"><noframes id="fpn9h"> <th id="fpn9h"></th> <strike id="fpn9h"><noframes id="fpn9h"><strike id="fpn9h"></strike> <th id="fpn9h"><noframes id="fpn9h"> <span id="fpn9h"><video id="fpn9h"></video></span> <ruby id="fpn9h"></ruby> <strike id="fpn9h"><noframes id="fpn9h"><span id="fpn9h"></span> -
參考文獻
[1] Li X B, Zhou J, Wang S F, et al. Review and practice of deep mining for solid mineral resources. Chin J Nonferrous Met, 2017, 27(6): 1236 doi: 10.19476/j.ysxb.1004.0609.2017.06.021李夕兵, 周健, 王少鋒, 等. 深部固體資源開采評述與探索. 中國有色金屬學報, 2017, 27(6):1236 doi: 10.19476/j.ysxb.1004.0609.2017.06.021 [2] Kesimal A, Yilmaz E, Ercikdi B. Evaluation of paste backfill mixtures consisting of sulphide-rich mill tailings and varying cement contents. Cem Concr Res, 2004, 34(10): 1817 doi: 10.1016/j.cemconres.2004.01.018 [3] Yin S H, Liu J M, Chen W, et al. Optimization of the effect and formulation of different coarse aggregates on performance of the paste backfill condensation. Chin J Eng, 2020, 42(7): 829尹升華, 劉家明, 陳威, 等. 不同粗骨料對膏體凝結性能的影響及配比優化. 工程科學學報, 2020, 42(7):829 [4] Yang X B, Xiao B L, Gao Q, et al. Determining the pressure drop of cemented Gobi sand and tailings paste backfill in a pipe flow. Constr Build Mater, 2020, 255: 119371 doi: 10.1016/j.conbuildmat.2020.119371 [5] Zhang L F, Wu A X, Wang H J. Effects and mechanism of pumping agent on rheological properties of highly muddy paste. Chin J Eng, 2018, 40(8): 918張連富, 吳愛祥, 王洪江. 泵送劑對高含泥膏體流變特性影響及機理. 工程科學學報, 2018, 40(8):918 [6] Tilmaz E, Belem T, Benzaazoua M, et al. Assessment of the modified CUAPS apparatus to estimate in situ properties of cemented paste backfill. Geotech Test J, 2010, 33(5): 351 [7] Wei H B, Ba L, Wen Z J, et al. Development of magnesium slag binder and optimization of slurry ratio based on entropy weight multi-attribute decision. Chin J Nonferrous Met,https://kns.cnki.net/kcms/detail/43.1238.tg.20210902.1616.009.html韋寒波, 巴蕾, 溫震江, 等. 基于熵權多屬性決策的鎂渣膠結料開發及料漿配比優化. 中國有色金屬學報,https://kns.cnki.net/kcms/detail/43.1238.tg.20210902.1616.009.html [8] Yang X B. Study on the Collaborative Preparation of Filling Materials with Low Quality and Multi-Solid Wastes and Their Pressure Drop in Pipeline Transportation [Dissertation]. Beijing: University of Science and Technology Beijing, 2020楊曉炳. 低品質多固廢協同制備充填料漿及其管輸阻力研究[學位論文]. 北京: 北京科技大學, 2020 [9] Shi C J, Qian J S. High performance cementing materials from industrial slags—a review. Resour Conserv Recycl, 2000, 29(3): 195 doi: 10.1016/S0921-3449(99)00060-9 [10] Flatt R J, Roussel N, Cheeseman C R. Concrete: An eco material that needs to be improved. J Eur Ceram Soc, 2012, 32(11): 2787 doi: 10.1016/j.jeurceramsoc.2011.11.012 [11] Gijbels K, Iacobescu R I, Pontikes Y, et al. Alkali-activated binders based on ground granulated blast furnace slag and phosphogypsum. Constr Build Mater, 2019, 215: 371 doi: 10.1016/j.conbuildmat.2019.04.194 [12] Jiang H Q, Qi Z J, Yilmaz E, et al. Effectiveness of alkali-activated slag as alternative binder on workability and early age compressive strength of cemented paste backfills. Constr Build Mater, 2019, 218: 689 doi: 10.1016/j.conbuildmat.2019.05.162 [13] Gorai B, Jana R K, Premchand. Characteristics and utilisation of copper slag—a review. Resour Conserv Recycl, 2003, 39(4): 299 doi: 10.1016/S0921-3449(02)00171-4 [14] Wu F, Yang F G, Xiao B L, et al. Influence of steel slag dosage on early age strength and rheological properties of paste. Mater Rep, 2021, 35(3): 3021 doi: 10.11896/cldb.20050029吳凡, 楊發光, 肖柏林, 等. 鋼渣摻量對膏體早期強度及流變特性的影響. 材料導報, 2021, 35(3):3021 doi: 10.11896/cldb.20050029 [15] Teng S, Lim T Y D, Sabet Divsholi B. Durability and mechanical properties of high strength concrete incorporating ultra fine Ground Granulated Blast-furnace Slag. Constr Build Mater, 2013, 40: 875 doi: 10.1016/j.conbuildmat.2012.11.052 [16] Xiao B L, Miao S J, Gao Q, et al. Study on solidification characteristics of metallurgical slag binder materials for ultra-fine tailings backfill. Chin J Nonferrous Met,http://kns.cnki.net/kcms/detail/43.1238.TG.20210820.1435.011.html肖柏林, 苗勝軍, 高謙, 等. 冶金渣膠結材料對超細全尾砂的固化特性研究. 中國有色金屬學報,http://kns.cnki.net/kcms/detail/43.1238.TG.20210820.1435.011.html [17] Qi C C, Fourie A, Chen Q S, et al. A strength prediction model using artificial intelligence for recycling waste tailings as cemented paste backfill. J Clean Prod, 2018, 183: 566 doi: 10.1016/j.jclepro.2018.02.154 [18] Yang X, Yang Z Q, Gao Q, et al. Cemented filling strength test and optimal proportion decision of mixed filling aggregate. Rock Soil Mech, 2016, 37(Suppl 2): 635楊嘯, 楊志強, 高謙, 等. 混合充填骨料膠結充填強度試驗與最優配比決策研究. 巖土力學, 2016, 37(增刊2): 635 [19] Ma X Y, Duan Y F, Liu M, et al. Prediction of pressure drop of coke water slurry flowing in pipeline by PSO-BP neural network. Proc CSEE, 2012, 32(5): 54 doi: 10.13334/j.0258-8013.pcsee.2012.05.005馬修元, 段鈺鋒, 劉猛, 等. 基于PSO-BP神經網絡的水焦漿管道壓降預測. 中國電機工程學報, 2012, 32(5):54 doi: 10.13334/j.0258-8013.pcsee.2012.05.005 [20] Pourbasheer E, Riahi S, Ganjali M R, et al. Application of genetic algorithm-support vector machine (GA-SVM) for prediction of BK-channels activity. Eur J Med Chem, 2009, 44(12): 5023 doi: 10.1016/j.ejmech.2009.09.006 [21] Ma L, Zhang P Y, Guo R Z, et al. GA-SVM model for prediction flue gas temperature of roadway fire under sealing process. J China Univ Min Technol, 2021, 50(4): 641 doi: 10.13247/j.cnki.jcumt.001309馬礪, 張鵬宇, 郭睿智, 等. 巷道火災密閉過程煙氣溫度預測的GA-SVM模型. 中國礦業大學學報, 2021, 50(4):641 doi: 10.13247/j.cnki.jcumt.001309 [22] Bi J, Li X J. Comprehensive evaluation of coal mine safety based on grey target model with combination weighting of game theory. J Saf Sci Technol, 2019, 15(7): 113 doi: 10.11731/j.issn.1673-193x.2019.07.018畢娟, 李希建. 基于博弈論組合賦權灰靶模型的煤礦安全綜合評價. 中國安全生產科學技術, 2019, 15(7):113 doi: 10.11731/j.issn.1673-193x.2019.07.018 [23] Wen Z J, Gao Q, Wang Z H, et al. Optimization of compound activator ratio of the ground granulated blast furnace slag powder cementitious material based on RSM-DF. Chin J Rock Mech Eng, 2020, 39(Suppl 1): 3103溫震江, 高謙, 王忠紅, 等. 基于RSM-DF的礦渣膠凝材料復合激發劑配比優化. 巖石力學與工程學報, 2020, 39(增刊1): 3103 [24] Li M H, Yang Z Q, Wang Y T, et al. Experiment study of compressive strength and mechanical property of filling body for fly ash composite cementitious materials. J China Univ Min Technol, 2015, 44(4): 650 doi: 10.13247/j.cnki.jcumt.000365李茂輝, 楊志強, 王有團, 等. 粉煤灰復合膠凝材料充填體強度與水化機理研究. 中國礦業大學學報, 2015, 44(4):650 doi: 10.13247/j.cnki.jcumt.000365 [25] Dong Y, Yang Z Q, Gao Q. Effect of steel slag substitution on the properties of composite cementitious backfill material. Bull Chin Ceram Soc, 2016, 35(9): 2967 doi: 10.16552/j.cnki.issn1001-1625.2016.09.048董越, 楊志強, 高謙. 鋼渣取代量對復合充填膠凝材料性能的影響. 硅酸鹽通報, 2016, 35(9):2967 doi: 10.16552/j.cnki.issn1001-1625.2016.09.048 [26] Cui X W, Ni W, Ren C. Hydration mechanism of all solid waste cementitious materials based on steel slag and blast furnace slag. Chin J Mater Res, 2017, 31(9): 687 doi: 10.11901/1005.3093.2016.741崔孝煒, 倪文, 任超. 鋼渣礦渣基全固廢膠凝材料的水化反應機理. 材料研究學報, 2017, 31(9):687 doi: 10.11901/1005.3093.2016.741 -
點擊查看大圖
計量
- 文章訪問數: 457
- HTML全文瀏覽量: 175
- PDF下載量: 29
- 被引次數: 0
