基于遗传优化算法-反向传播神经网络的机制砂聚合物改性砂浆力学性能预测

田浩正; 乔宏霞; 张云升; 冯琼; 王鹏辉; 谢晓扬

基于遗传优化算法-反向传播神经网络的机制砂聚合物改性砂浆力学性能预测

田浩正^{1, 2},
乔宏霞^{1, 2},
张云升^{1, 2, ,},
冯琼^{1, 2},
王鹏辉³,
谢晓扬^{1, 2}

1.
兰州理工大学　土木工程学院, 兰州 730050
2.
兰州理工大学　西部土木工程防灾减灾教育部工程研究中心, 兰州 730050
3.
深圳大学广东省海洋土木工程耐久性重点实验室, 深圳 518060

基金项目: 国家自然科学基金 (51868044；52008196；U21A20150；52178216)；甘肃省科技计划资助(23JRRA799；23JRRA813)

详细信息

通讯作者:
张云升，博士，教授，博士生导师，研究方向为土木工程材料　E-mail: zhangyunsheng2011@163.com

中图分类号: TU528.41
计量
- 文章访问数: 39
- HTML全文浏览量: 21
- 被引次数: 0
出版历程
- 收稿日期: 2024-04-22
- 修回日期: 2024-05-22
- 录用日期: 2024-06-05
- 网络出版日期: 2024-06-29

Prediction of mechanical properties of manufactured sand polymer-modified mortar based on genetic optimization algorithm - backpropagation neural network

TIAN Haozheng^{1, 2},
QIAO Hongxia^{1, 2},
ZHANG Yunsheng^{1, 2
, ,},
FENG Qiong^{1, 2},
WANG Penghui³,
XIE Xiaoyang^{1, 2}

1.
School of Civil Engineering, Lanzhou University of Technology, Lanzhou 730050, China
2.
Western Center of Disaster Mitigation in Civil Engineering of Ministry of Education, Lanzhou University of Technology, Lanzhou 730050, China
3.
College of Civil and Transportation Engineering, Guangdong Provincial Key Laboratory of Durability for Marine Civil Engineering, Shenzhen University, Shenzhen 518060, China

Funds: National Natural Science Foundation of China (51868044; 52008196; U21A20150; 52178216); Supported by Gansu Provincial Science and Technology Plan (23JRRA799; 23JRRA813)

摘要

摘要: 对聚合物改性砂浆(PMM)进行力学性能评价是保证安全使用的必要条件。为快速准确的获得具有优异力学性能的PMM，设计了拓扑结构为6-14-2的反向传播的神经网络(BPNN)预测模型，并使用遗传优化算法(GA)进行优化。GA-BPNN模型的输入层为水泥、纤维素醚、可再分散乳胶粉、消泡剂、凝灰岩石粉和粉煤灰的含量，输出层为抗压强度和粘结强度。数据集为520个，其中60%的数据用于建立模型，40%的数据用于验证模型。以实测抗折强度、抗压强度和粘结强度作为PMM的力学性能评价指标，通过相关性矩阵分析和主成分分析确定原材料与PMM力学性能之间的关系，同时对力学性能评价指标进行对比分析。结果表明：在7d和28d时，可再分散乳胶粉和消泡剂与PMM力学性能发展呈正相关；7 d时，石粉、粉煤灰与抗压、抗折强度呈负相关，纤维素醚与粘结强度呈正相关；28d时，水泥与抗压、粘结和抗折强度负相关，与石粉、粉煤灰呈正相关。GA优化算法可以显著提升BPNN模型的预测精度，GA-BPNN对抗压强度和粘结强度的预测性能评价指标分别为R² = 0.918、R_MAE = 17.507、R_MAPE = 0.299、R_RMSE = 7.849；R² = 0.922、R_MAE = 17.101、R_MAPE = 0.282、R_RMSE = 8.077。因此，GA-BPNN可以为PMM在力学性能方面提供精确的预测并对其配合比设计进行指导，对于工程实践具有重要意义。
- 聚合物改性砂浆 /
- 力学性能 /
- 反向传播神经网络 /
- 遗传优化算法 /
- 配合比优化 /
- 机制砂
Abstract: Evaluating the mechanical performance of polymer modified mortar (PMM) is essential to ensure safe usage. To efficiently and accurately obtain PMM with excellent mechanical properties, a backpropagation neural network (BPNN) prediction model with a topology structure of 6-14-2 was designed and optimized using a genetic algorithm (GA). The input layer of the GA-BPNN model comprised cement, cellulose ether, dispersible polymer powder, antifoam, limestone powder, and fly ash content, with the output layer encompassing compressive strength and bond strength. The dataset consisted of 520 data points, of which 60% was used to build the model and 40% to validate the model. Experimental flexural strength, compressive strength, and bond strength were taken as the evaluation indicators for PMM's mechanical properties. The relationship between raw materials and PMM mechanical properties was determined through correlation matrix analysis and principal component analysis, along with comparative analysis of mechanical performance indicators. The results indicate that at 7 d and 28 d, the development of PMM mechanical properties is positively correlated with dispersible polymer powder and antifoam. At 7 d, limestone powder and fly ash are negatively correlated with compressive and flexural strength, while cellulose ether is positively correlated with bond strength. At 28 d, cement is negatively correlated with compressive, bond, and flexural strength, and positively correlated with limestone powder and fly ash. The GA optimization algorithm can significantly enhance the prediction accuracy of the BPNN model. The predictive performance indicators of GA-BPNN for compressive strength and bond strength are R² = 0.918、R_MAE = 17.507、R_MAPE = 0.299、R_RMSE = 7.849; R² = 0.922、R_MAE = 17.101、R_MAPE = 0.282、R_RMSE = 8.077. Thus, GA-BPNN can provide accurate predictions for the mechanical performance of PMM and guide its mix design, which is of great significance for engineering practice.
- polymer-modified mortar /
- mechanical properties /
- backpropagation neural network /
- genetic optimization algorithm /
- mix design optimization /
- manufactured sand

HTML全文

图 1 PMM的制备及测试过程

Figure 1. Preparation and testing process of PMM

下载: 全尺寸图片幻灯片

图 2 BPNN结构示意图

Figure 2. Schematic representation of the BPNN structure

下载: 全尺寸图片幻灯片

图 3 遗传优化算法的操作流程

Figure 3. Operation flow of GA

下载: 全尺寸图片幻灯片

图 4 PMM相关性矩阵图：(a)7 d；(b)28 d

Figure 4. PMM correlation matrix plots: (a) 7 d; (b) 28 d

OPC–cement; CE–cellulose ether; DPP–dispersible polymer powder; AF–antifoam; SP–stone powder; FA–fly ash; CS–compressive strength; BS–bond strength; FS–flexural strength

下载: 全尺寸图片幻灯片

图 5 不同配合比主成分得分：(a)各组主成分得分；(b)综合主成分得分

Figure 5. Principal component scores for different mix ratios: (a) Principal component scores for each group; (b) Composite principal component score

下载: 全尺寸图片幻灯片

图 6 特征重要性排序

Figure 6. Ranking of principal components’ importance

下载: 全尺寸图片幻灯片

图 7 BPNN预测模型的建立：(a)模型训练；(b)模型验证；(c)模型测试；(d)总体建立阶段

Figure 7. BPNN prediction model building: (a) Model training; (b) Model validation; (c) Model testing; (d) Overall building phase

下载: 全尺寸图片幻灯片

图 8 GA-BPNN预测模型的建立：(a)模型训练；(b)模型验证；(c)模型测试；(d)总体建立阶段

Figure 8. GA-BPNN prediction model building: (a) Model training; (b) Model validation; (c) Model testing; (d) Overall building phase

下载: 全尺寸图片幻灯片

图 9 预测模型的评价指标：(a)训练阶段；(b)测试阶段

Figure 9. Evaluation indicators of the predictive model: (a) Training stage; (b) Testing phase

下载: 全尺寸图片幻灯片

图 10 预测模型预测值与实际值的误差范围：(a)抗压强度；(b)粘结强度

Figure 10. Error range between predicted and actual values of the prediction model: (a) Compressive strength; (b) Bond strength

下载: 全尺寸图片幻灯片

图 11 预测模型的验证指标：(a)抗压强度；(b)粘结强度

Figure 11. Validation metrics for predictive modeling: (a) Compressive strength; (b) Bond strength

下载: 全尺寸图片幻灯片

表 1 水泥、石粉和粉煤灰的化学组成和比表面积

Table 1. Chemical composition and specific surface area of stone powder and fly ash

Materials	SiO₂/wt%	Fe₂O₃/wt%	Al₂O₃/wt%	CaO/wt%	MgO/wt%	SO₃/wt%	K₂O/wt%	LOI/wt%	Specific surface area /(m²·kg⁻¹)
Cement	26.36	4.49	10.62	49.27	3.24	2.01	1.27	3.71	853
Fly ash	45.19	2.19	24.43	4.59	0.78	0.49	1.35	2.62	1220
Stone powder	60.32	3.29	20.14	5.38	4.59	0.06	3.04	4.29	1440
Note: LOI–Loss on ignition.

下载: 导出CSV

表 2 凝灰岩机制砂主要的性能指标

Table 2. Main indicators of tuff manufactured sand

Fineness modulus	Stone powder content /%	Apparent density/(kg·m⁻³)	Packing density /(kg·m⁻³)	Voidage/%	Crushing index/%	Methylene blue value/(g·kg⁻¹)
2.4	9	2690	1710	39	9	2.1

下载: 导出CSV

表 3 聚合物改性砂浆配合比

Table 3. PMM mixing ratio (kg·m⁻³)

Item NO.	Cement	Cellulose ether	Dispersible polymer powder	Antifoam	Stone powder	GradeⅡ fly ash
O	460.00	-	-	-	-	-
A_1-CE	460.00	0.23	-	-	-	-
A_2-CE	460.00	0.46	-	-	-	-
A_3-CE	460.00	0.69	-	-	-	-
A_4-CE	460.00	0.92	-	-	-	-
B_1-DPP	460.00	0.46	4.6	-	-	-
B_2-DPP	460.00	0.46	9.2	-	-	-
B_3-DPP	460.00	0.46	13.8	-	-
B_4-DPP	460.00	0.46	18.4	-	-	-
C_1-AF	460.00	0.46	13.8	0.092	-	-
C_2-AF	460.00	0.46	13.8	0.184	-	-
C_3-AF	460.00	0.46	13.8	0.368	-	-
C_4-AF	460.00	0.46	13.8	0.736	-	-
D_1-SP	437.00	0.46	13.8	0.184	23.0	-
D_2-SP	414.00	0.46	13.8	0.184	46.0	-
D_3-SP	391.00	0.46	13.8	0.184	69.0	-
D_4-SP	368.00	0.46	13.8	0.184	92.0	-
D_5-SP	345.00	0.46	13.8	0.184	115.0	-
E_1-FA	437.00	0.46	13.8	0.184	-	23.0
E_2-FA	414.00	0.46	13.8	0.184	-	46.0
E_3-FA	391.00	0.46	13.8	0.184	-	69.0
E_4-FA	368.00	0.46	13.8	0.184	-	92.0
E_5-FA	345.00	0.46	13.8	0.184	-	115.0
F_1-SPFA	368.00	0.46	13.8	0.184	36.8	55.2
F_2-SPFA	368.00	0.46	13.8	0.184	46.0	46.0
F_3-SPFA	368.00	0.46	13.8	0.184	55.2	36.8
Notes: A_-CE–Various amounts of cellulose ether; B_-DPP–Various amounts of dispersible polymer powder; C_-AF–Various amounts of antifoam; D_-SP–Various amounts of stone powder; E_-FA–Various amounts of fly ash; F_-SPFA–Combined addition of stone powder and fly ash.

下载: 导出CSV

[1]	高乙博, 罗健林, 李治庆, 等. 正交优化纤维聚合物修补防护砂浆配比及其综合性能实现机制[J]. 复合材料学报, 2023, 40(9): 5258-5275. GAO Yibo, LUO Jianlin, LI Zhiqing, et al. Orthogonal optimization mix ratio of fiber polymer repair protect mortar and its comprehensive performance realization mechanism[J]. Acta Materiae Compositae Sinica, 2023, 40(9): 5258-5275(in Chinese).
[2]	ZHANG X, DU M, FANG H, et al. Polymer-modified cement mortars: Their enhanced properties, applications, prospects, and challenges[J]. Construction and Building Materials, 2021, 299: 124290. doi: 10.1016/j.conbuildmat.2021.124290
[3]	AATTACHE A, SOLTANI R. Durability - related properties of early-age and long-term resistant laboratory elaborated polymer-based repair mortars[J]. Construction and Building Materials, 2020, 235: 117494. doi: 10.1016/j.conbuildmat.2019.117494
[4]	ILLAMPAS R, RIGOPOULOS I, IOANNOU I. Influence of microencapsulated Phase Change Materials (PCMs) on the properties of polymer modified cementitious repair mortar[J]. Journal of Building Engineering, 2021, 40: 102328. doi: 10.1016/j.jobe.2021.102328
[5]	ZHAO Z G, QU X L, LI J H. Application of polymer modified cementitious coatings (PCCs) for impermeability enhancement of concrete[J]. Construction and Building Materials, 2020, 249: 118769. doi: 10.1016/j.conbuildmat.2020.118769
[6]	FAN L D, XU F, WANG S R, et al. A review on the modification mechanism of polymer on cement-based materials[J]. Journal of Materials Research and Technology- Jmr& T, 2023, 26: 5816-5837.
[7]	ZHAO K, QIAO Y, ZHANG P, et al. Experimental and numerical study on chloride transport in cement mortar during drying process[J]. Construction and Building Materials, 2020, 258: 119655. doi: 10.1016/j.conbuildmat.2020.119655
[8]	WOZNIAK Z Z, CHAJEC A, SADOWSKI L. Effect of the partial replacement of cement with waste granite powder on the properties of fresh and hardened mortars for masonry applications[J]. Materials, 2022, 15(24): 9066. doi: 10.3390/ma15249066
[9]	YANG J, LIU L, LIAO Q, et al. Effect of superabsorbent polymers on the drying and autogenous shrinkage properties of self-leveling mortar[J]. Construction and Building Materials, 2019, 201: 401-407. doi: 10.1016/j.conbuildmat.2018.12.197
[10]	ZHAO F Q, LI H, LIU S J, et al. Preparation and properties of an environment friendly polymer-modified waterproof mortar[J]. Construction and Building Materials, 2011, 25(5): 2635-2638. doi: 10.1016/j.conbuildmat.2010.12.012
[11]	YANG H, LIANG D, DENG Z, et al. Effect of limestone powder in manufactured sand on the hydration products and microstructure of recycled aggregate concrete[J]. Construction and Building Materials, 2018, 188: 1045-1049. doi: 10.1016/j.conbuildmat.2018.08.147
[12]	LIU W, DU H, YI P, et al. The early hydration and rheological characteristics of cement paste containing co-combustion fly ash[J]. Journal of Building Engineering, 2023, 78: 107736. doi: 10.1016/j.jobe.2023.107736
[13]	李苗苗, 陈平, 李建超. 粉煤灰微珠含量与粒径级配比对环氧树脂基复合材料弯曲性能的影响[J]. 复合材料学报, 2017, 34(2): 345-351. LI Miaomiao, CHEN Ping, LI Jianchao. Effect of content and grading ratios of fly ash cenospheres on the flexural properties of the epoxy resin composites[J]. Acta Materiae Compositae Sinica, 2017, 34(2): 345-351(in Chinese).
[14]	YANG R, YU R, SHUI Z, et al. Environmental and economical friendly ultra-high performance-concrete incorporating appropriate quarry-stone powders[J]. Journal of Cleaner Production, 2020, 260: 121112. doi: 10.1016/j.jclepro.2020.121112
[15]	WANG D, SHI C, FARZADNIA N, et al. A review on use of limestone powder in cement-based materials: Mechanism, hydration and microstructures[J]. Construction and Building Materials, 2018, 181: 659-672. doi: 10.1016/j.conbuildmat.2018.06.075
[16]	NAKAYENGA J, INUI M, HATA T. Study on the effect of amorphous silica from waste granite powder on the strength development of cement-treated clay for soft ground improvement[J]. Sustainability, 2022, 14(7): 4073. doi: 10.3390/su14074073
[17]	LIU S H, FANG P P, WANG H L, et al. Effect of tuff powder on the hydration properties of composite cementitious materials[J]. Powder Technology, 2021, 380: 59-66. doi: 10.1016/j.powtec.2020.11.029
[18]	LI H, HUANG F, CHENG G, et al. Effect of granite dust on mechanical and some durability properties of manufactured sand concrete[J]. Construction and Building Materials, 2016, 109: 41-46. doi: 10.1016/j.conbuildmat.2016.01.034
[19]	DE WEERDT K, KJELLSEN K O, SELLEVOLD E, et al. Synergy between fly ash and limestone powder in ternary cements[J]. Cement & Concrete Composites, 2011, 33(1): 30-38.
[20]	ASADZADEH S, KHOSHBAYAN S, Multi-objective optimization of influential factors on production process of foamed concrete using Box-Behnken approach[J]. Construction and Building Materials, 2018, 170: 101-110.
[21]	WU H, YANG D, WANG C, et al. , Effects of construction waste powder on micro-macro properties of green high-strength cement paste with low water-to-binder ratio[J]. Construction and Building Materials, 2023, 385: 131493. doi: 10.1016/j.conbuildmat.2023.131493
[22]	WANG P, QIAO H, XUE C, et al. Prediction of water resistance of magnesium oxychloride cement concrete based upon Hybrid-BP neural network[J]. Materials, 2023, 16(9): 3371. doi: 10.3390/ma16093371
[23]	BADAGHA D, MODHERA C, VASANWALA S, Mix proportioning and strength prediction of high performance concrete including waste using artificial neural network. International Journal of Civil and Environmental Engineering, 2018, 12(2): 169-172.
[24]	HUANG L, CHEN J, TAN X, BP-ANN based bond strength prediction for FRP reinforced concrete at high temperature. Engineering Structures, 2022, 257: 114026.
[25]	ZHONG W, DING H, ZHAO X, et al. Mechanical properties prediction of geopolymer concrete subjected to high temperature by BP neural network[J]. Construction and Building Materials, 2023, 409: 133780. doi: 10.1016/j.conbuildmat.2023.133780
[26]	HAQUE A, CHEN B, JAVED M F, et al. , Evaluating the mechanical strength prediction performances of fly ash-based MPC mortar with artificial intelligence approaches[J]. Journal of Cleaner Production, 2022, 355: 131815. doi: 10.1016/j.jclepro.2022.131815
[27]	SUN L, KOOPIALIPOOR M, JAHED ARMAGHANI D, et al. , Applying a meta-heuristic algorithm to predict and optimize compressive strength of concrete samples[J]. Engineering with Computers, 2021, 37: 1133-1145. doi: 10.1007/s00366-019-00875-1
[28]	WANG S, XIA P, WANG Z, et al. Intelligent mix design of recycled brick aggregate concrete based on swarm intelligence[J]. Journal of Building Engineering, 2023, 71: 106508. doi: 10.1016/j.jobe.2023.106508
[29]	胡春幸, 侯玉亮, 铁瑛, 等. 基于遗传算法的碳纤维增强树脂复合材料层合板单搭胶接结构的多目标优化[J]. 复合材料学报, 2021, 38(6): 1847-1858. HU Chunxing, HOU Yuliang, TIE Ying, et al. Multi-objective optimization of adhesively bonded single-lap joints of carbon fiber reinforced polymer laminates based on genetic algorithm[J]. Acta Materiae Compositae Sinica, 2021, 38(6): 1847-1858(in Chinese).
[30]	陈庆, 马瑞, 蒋正武, 等. 基于GA-BP神经网络的UHPC抗压强度预测与配合比设计[J]. 建筑材料学报, 2020, 23(1): 176-183+191. doi: 10.3969/j.issn.1007-9629.2020.01.027 CHEN Qing, MA Rui, JIANG Zhengwu et al. Compressive strength prediction and mix proportion design of UHPC based on GA-BP neural network[J]. Journal of Building Materials, 2020, 23(1): 176-183+191(in Chinese). doi: 10.3969/j.issn.1007-9629.2020.01.027
[31]	周中, 邓卓湘, 陈云, 等. 基于GA-BP神经网络的泡沫轻质土强度预测[J]. 华南理工大学学报(自然科学版), 2022, 50(11): 125-132. ZHOU Zhong, DENG Zhuoxiang, CHEN Yun, et al. Strength prediction of foamed light soil based on GA-BP neural network[J]. Journal of South China University of Technology (Natural Science Edition), 2022, 50(11): 125-132(in Chinese).
[32]	REN H S, QIAN Z D, LIN B, et al. Effect of recycled concrete aggregate features on adhesion properties of asphalt mortar-aggregate interface[J]. Construction and Building Materials, 2022, 353: 129097. doi: 10.1016/j.conbuildmat.2022.129097
[33]	中国建筑科学研究院. 普通混凝土用砂、石质量及检验方法标准: JGJ/T 52-2006[S]. 北京: 中国建材工业出版社, 2006. China Academy of Building Research. Standard for technical requirements and test method of sand and crushed stone (or gravel) for ordinary concrete: JGJ/T 52-2006[S] Beijing: China Building Materials Industry Press, 2006 (in Chinese).
[34]	陕西省建筑科学研究院. 建筑砂浆基本性能试验方法: JGJ/T 70-2009[S]. 北京: 中国建筑工业出版社, 2009. Shaanxi Academy of Building Science. Standard for testmethod of performance on building mortar: JGJ/T 70-2009[S]. Beijing: China Architecture & Building Press, 2009 (in Chinese).
[35]	中国国家标准化管理委员会. 水泥胶砂强度检验方法(ISO法): GB/T 17671-2021[S]. 北京: 中国标准出版社, 2021. Standardization Administration of China. Method of testing cements—Determination of strength: GB/T 17671-2021[S]. Beijing: Standards Press of China, 2021 (in Chinese).
[36]	BAJPAI P, KUMAR M. Genetic Algorithm - an Approach to Solve Global Optimization Problems[J]. Indian Journal of Computer Science and Engineering, 2010, 1: 199-206.
[37]	KUO H C, LIN C H. A Directed Genetic Algorithm for global optimization[J]. Applied Mathematics and Computation, 2013, 219(14): 7348-7364. doi: 10.1016/j.amc.2012.12.046
[38]	ABIODUN O I, JANTAN A, OMOLARA A E, et al. Comprehensive review of artificial neural network applications to pattern recognition[J]. IEEE access, 2019, 7: 158820-158846. doi: 10.1109/ACCESS.2019.2945545
[39]	WANG P, DONG B, ZHANG Y, et al. Evaluation and characteristic analysis of compressive strength and resistivity of EG cement conductive mortar based upon hybrid-BP neural network[J]. Construction and Building Materials, 2023, 394: 132203. doi: 10.1016/j.conbuildmat.2023.132203
[40]	LIU W, DU H, YI P, et al. The early hydration and rheological characteristics of cement paste containing co-combustion fly ash[J]. Journal of Building Engineering, 2023, 78: 107736. doi: 10.1016/j.jobe.2023.107736
[41]	LI J, WANG R, LI L, et al. Influence of cellulose ethers structure on mechanical strength of calcium sulphoaluminate cement mortar[J]. Construction and Building Materials, 2021, 303: 124514. doi: 10.1016/j.conbuildmat.2021.124514
[42]	BRUMAUD C, BAUMANN R, SCHMITZ M, et al. Cellulose ethers and yield stress of cement pastes[J]. Cement and Concrete Research, 2014, 55: 14-21. doi: 10.1016/j.cemconres.2013.06.013
[43]	POURCHEZ J, GROSSEAU P, RUOT B, et al. Changes in C₃S hydration in the presence of cellulose ethers[J]. Cement and Concrete Research, 2010, 40(2): 179-188. doi: 10.1016/j.cemconres.2009.10.008
[44]	QIAO M, WU J Z, GAO N X, et al. Preparation and properties of different polyether-type defoamers for concrete[J]. Materials, 2022, 15(21): 7492. doi: 10.3390/ma15217492
[45]	HUANG Y S, SHEN L, LIU H. Grey relational analysis, principal component analysis and forecasting of carbon emissions based on long short-term memory in China[J]. Journal of Cleaner Production, 2019, 209: 415-423. doi: 10.1016/j.jclepro.2018.10.128
[46]	XU M, ZHANG Y Z, ZHAO P H, et al. , Study on aging behavior and prediction of SBS modified asphalt with various contents based on PCA and PLS analysis[J]. Construction and Building Materials, 2020, 265: 120732. doi: 10.1016/j.conbuildmat.2020.120732
[47]	SUN Z, LI Y L, LI Y Q, et al. Investigation on compressive strength of coral aggregate concrete: Hybrid machine learning models and experimental validation[J]. Journal of Building Engineering, 2024, 82: 108220. doi: 10.1016/j.jobe.2023.108220