|本期目录/Table of Contents|

[1]楼杨帆,张振营.基于机器学习算法的城市生活垃圾修正主压缩指数预测模型[J].浙江理工大学学报,2025,53-54(自科一):88-95.
 LOU Yangfan,ZHANG Zhenying.A prediction model for the modified primary compression index of  municipal solid waste based on machine learning algorithms[J].Journal of Zhejiang Sci-Tech University,2025,53-54(自科一):88-95.
点击复制

基于机器学习算法的城市生活垃圾修正主压缩指数预测模型()
分享到:

浙江理工大学学报[ISSN:1673-3851/CN:33-1338/TS]

卷:
第53-54卷
期数:
2025年自科第一期
页码:
88-95
栏目:
出版日期:
2025-01-10

文章信息/Info

Title:
A prediction model for the modified primary compression index of  municipal solid waste based on machine learning algorithms
文章编号:
1673-3851 (2025) 01-0088-08
作者:
楼杨帆张振营
浙江理工大学建筑工程学院,杭州 310018
Author(s):
LOU Yangfan ZHANG Zhenying
School of Civil Engineering and Architecture, Zhejiang Sci-Tech University, Hangzhou 310018, China
关键词:
城市生活垃圾基本土工参数修正主压缩指数机器学习预测模型SHAP值法
分类号:
X799-3
文献标志码:
A
摘要:
为准确预测老垃圾填埋场竖向扩容设计中城市生活垃圾的修正主压缩指数,首先采集西安江村沟垃圾填埋场不同填埋龄期的垃圾试样,通过室内试验测定120组试样的基本土工参数和修正主压缩指数,并利用决策树、随机森林、人工神经网络和极端梯度提升树这4种机器学习算法建立修正主压缩指数预测模型;其次收集国内外其他生活垃圾填埋场的试验数据,将其与24组试验数据组合,构建测试集;再次选取均方根误差、平均绝对误差以及判定系数作为评价指标,得到最佳预测效果的模型,并将该模型与文献预测模型的预测结果进行对比;最后采用SHAP(SHapley Additive exPlanations)值法对最佳预测效果的模型进行参数影响分析。结果表明:在4种机器学习算法中,人工神经网络的预测效果最佳,且具有更好的泛化能力;与文献预测模型相比,人工神经网络预测模型的预测效果更好;干重度对修正主压缩指数的影响程度最显著,且与修正主压缩指数呈负相关关系。该研究构建的预测模型,可以直接使用容易获取的基本土工参数来预测修正主压缩指数,不需要费时费力的压缩试验。研究结果可为老垃圾填埋场的竖向扩容设计提供参考依据。

参考文献/References:

[1]Feng S J, Gao K W, Chen Y X, et al. Geotechnical properties of municipal solid waste at Laogang Landfill, China[J]. Waste Management, 2017, 63: 354-365.
[2]He H J, Wu T, Wang X G, et al. Study on compressibility and settlement of a landfill with aged municipal solid waste: a case study in Taizhou[J]. Sustainability, 2021, 13(9): 4831.
[3]Chen Y M, Xu W J, Zhan L T, et al. Geoenvironmental issues in high-food-waste-content municipal solid waste landfills[J]. Journal of the Indian Institute of Science, 2021, 101(4): 603-623.
[4]Simes G F, Catapreta C A A. Monitoring and modeling of long-term settlements of an experimental landfill in Brazil[J]. Waste Management, 2013, 33(2): 420-430.
[5]Shariatmadari N, Sadeghpour A, Mokhtari M. Aging effect on physical properties of municipal solid waste at the Kahrizak Landfill, Iran[J]. International Journal of Civil Engineering, 2015, 13(1): 126-136.
[6]Zekkos D, Fei X, Grizi A, et al. Response of municipal solid waste to mechanical compression[J]. Journal of Geotechnical and Geoenvironmental Engineering, 2017, 143(3): 04016101.
[7]Zhu X R, Jin J M, Fang P F. Geotechnical behavior of the MSW in Tianziling landfill[J]. Journal of Zhejiang University: Science A, 2003, 4(3): 324-330.
[8]Zhan T L T, Chen Y M, Ling W A. Shear strength characterization of municipal solid waste at the Suzhou landfill, China[J]. Engineering Geology, 2008, 97(3/4): 97-111.
[9]Jo Y S, Jang Y S. Comparison of waste settlement characteristics for two landfills disposed in long sequential periods[J]. Waste Management, 2021, 131: 433-442.
[10]Mokhtari M, Heshmati Rafsanjani A A, Shariatmadari N. The effect of aging on the compressibility behavior and the physical properties of municipal solid wastes: a case study of Kahrizak landfill, Tehran[J]. Environmental Earth Sciences, 2019, 78(16): 519.

相似文献/References:

[1]俞金灵,彭明清,徐辉,等.生活垃圾填埋场开采再利用碳排放模型及其应用[J].浙江理工大学学报,2024,51-52(自科二):245.
 YU Jinling,PENG Mingqing,XU Hui,et al.A carbon emission model for domestic waste landfill mining and reuse and its applications[J].Journal of Zhejiang Sci-Tech University,2024,51-52(自科一):245.
[2]王成豪,张振营.城市生活垃圾中纤维素与木质素随龄期变化的规律[J].浙江理工大学学报,2024,51-52(自科六):832.
 WANG Chenghao,ZHANG Zhenying.Study on the changes of cellulose and lignin in  municipal solid waste with age[J].Journal of Zhejiang Sci-Tech University,2024,51-52(自科一):832.

备注/Memo

备注/Memo:
收稿日期: 2024-05-21
网络出版日期: 网络出版日期2024-09-13
基金项目: 国家自然科学基金项目(51978625,51678532)
作者简介: 楼杨帆(1996—),男,浙江义乌人,硕士研究生,主要从事环境岩土工程方面的研究。
通信作者: 张振营,E-mail:zhangzhenyinga@163.com
更新日期/Last Update: 2025-01-07