移动源排放遥测主要影响因素分析及预测

大气与环境光学学报 ›› 2022, Vol. 17 ›› Issue (2): 220-229.

移动源排放遥测主要影响因素分析及预测

许镇义1;2, 王瑞宾1;3, 康宇1;2;4;5∗, 曹洋2, 张聪6, 王仁军1;3

1合肥综合性国家科学中心人工智能研究院, 安徽合肥 230088; 2 中国科学技术大学自动化系, 安徽合肥 230036; 3 安徽大学计算机科学与技术学院, 安徽合肥 230601; 4 中国科学技术大学先进技术研究院, 安徽合肥 230088; 5 中国科学技术大学火灾科学国家重点实验室, 安徽合肥 230027; 6 合肥市生态环境局, 安徽合肥 230601

收稿日期:2020-12-29 修回日期:2022-02-23 出版日期:2022-03-28 发布日期:2022-03-28
通讯作者: E-mail: kangduyu@ustc.edu.cn E-mail:kangduyu@ustc.edu.cn
作者简介:许镇义 (1993 - ), 江苏宿迁人, 博士, 特任副研究员, 主要从事移动源污染监测、城市计算、时空数据挖掘方面的研究。 E-mail: xuzhenyi@mail.ustc.edu.cn
基金资助:
Supported by Major Science and Technology Project of Anhui Province (安徽省科技重大专项, 201903a07020012, 202003a07020009), National Natural Science Foundation of China (国家自然科学基金, 62033012, 61725304, 61673361, 62103124), National Key Research and Development Project of China (国家重点研发计划项目, 2018YFE0106800, 2018YFC0213104), Fundamental Research Funds for the Central Universities (中央高校基本科研业务费专项资金, WK2100000013, WK2380000001), Special Fund for Transformation of Scientific and Technological Achievements of Smart City Research Institute (Wuhu) of University of Science and Technology of China (中国科学技术大学智慧城市研究院 (芜湖) 科技成果转化专项资金, 2019ZX04)

Analysis and prediction of main influencing factors in mobile source remote sensing

XU Zhenyi1;2, WANG Ruibin1;3, KANG Yu1;2;4;5∗, CAO Yang2, ZHANG Cong6, WANG Renjun1;3

1 Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei 230088, China; 2 Department of Automation, University of Science and Technology of China, Hefei 230036, China; 3 School of Computer Science and Technology, Anhui University, Hefei 230601, China; 4 Institute of Advanced Technology, University of Science and Technology of China, Hefei 230088, China; 5 State Key Laboratory of Fire Science, University of Science and Technology of China, Hefei 230027, China; 6 Hefei Municipal Environmental Protection Bureau, Hefei 230601, China

Received:2020-12-29 Revised:2022-02-23 Published:2022-03-28 Online:2022-03-28
Contact: Yu Kang E-mail:kangduyu@ustc.edu.cn

摘要/Abstract

摘要： 由于移动源污染遥感监测受到复杂外部环境影响, 难以通过传统统计方法建立车辆行驶工况与污染排放之间的相关性模型, 为此开展了基于移动源遥感监测的影响因素分析及排放预测的研究。首先利用 Spearman 相关性分析排除与移动源污染物主要排放气体 CO、 HC、 NO 气体浓度无相关性的因素; 其次使用 Lasso 算法确定各成分的关键影响因子, 并采用神经网络构建污染物排放预测模型; 最后在测试集上验证该模型用于移动源污染排放主要成分预测的有效性。模型预测的结果表明, 基于特征筛选的移动源污染排放数据预测神经网络模型具有较高的预测精度, 可以降低城市移动源污染排放检测成本并为相关部门制定相关政策提供数据支持。

关键词: 移动源污染, 遥感监测, 排放预测, 特征筛选, 神经网络

Abstract: As remote sensing monitoring of mobile source exhaust can be affected by the complex external environment, it is difficult to establish a correaltion model between vehicle driving conditions and pollution emissions through traditional statistical methods. For this reason, the research on the analysis of influencing factors and emission prediction based on remote sensing monitoring of mobile sources is carried out. Firstly, Spearman correlation is used to exclude the factors that have no correlation with CO, HC and NO, the main components in emission of mobile source pollution. Secondly, Lasso algorithm is used to choose the principal influencing factors. And after principal components analysis and the selection of algorithm and architecture, the Back-Propagation (BP) neural network model is established as the optimal algorithm. Finally, the validity of the model for predicting the main components of emission of mobile source pollution is verified on the test set. The results of model prediction show that the prediction models based on feature selection and BP has high prediction accuracy, which can reduce the cost of mobile source pollution emission detection and provide theoretical basis for policy making.

Key words: mobile source emission, exhaust remote sensing, emission prediction, feature selection, neural network

中图分类号:

X831

许镇义, 王瑞宾, 康宇, ∗, 曹洋, 张聪, 王仁军, . 移动源排放遥测主要影响因素分析及预测[J]. 大气与环境光学学报, 2022, 17(2): 220-229.

XU Zhenyi, WANG Ruibin, KANG Yu, ∗, CAO Yang, ZHANG Cong, WANG Renjun, . Analysis and prediction of main influencing factors in mobile source remote sensing[J]. Journal of Atmospheric and Environmental Optics, 2022, 17(2): 220-229.

参考文献 28

[1]	Guo Y H, Wang Z F, Kang H, et al. Impact of automobile vehicles exhaust emissions on metropolitan air quality: analysis
	study on the air pollution change before and after the Spring Festival in Urumqi City, China [J]. Acta Scientiae Circumstantiae,
20	14, 34(5): 1109-1117.
	郭宇宏, 王自发, 康宏, 等. 机动车尾气排放对城市空气质量的影响研究: 以乌鲁木齐市春节前后对比分析 [J]. 环境科
	学学报, 2014, 34(5): 1109-1117.
[2]	Zhang Q. Vehicle Emission Estimation Algorithms Based on Remote Sensing Data [D]. Hefei: University of Science and
	Technology of China, 2019.
	张强. 基于遥感监测数据的机动车尾气排放估计算法研究 [D]. 合肥: 中国科学技术大学, 2019.
[3]	He C Y, Wang Q D. Vehicle emission factors determination using CMEM in Beijing [J]. Research of Environmental Sciences,
20	06, 19(1): 109-112.
	何春玉, 王歧东. 运用 CMEM 模型计算北京市机动车排放因子 [J]. 环境科学研究, 2006, 19(1): 109-112.
[4]	Yu K, Dong H Z, Li J W, et al. Research on prediction of vehicle exhaust based on measurement by PEMS [J]. Computer
	Measurement & Control, 2016, 24(9): 58-60.
	于坤, 董红召, 李家文, 等. 基于 PEMS 测量的机动车尾气预测研究 [J]. 计算机测量与控制, 2016, 24(9): 58-60.
[5]	Hao L J, Chen W, Li L, et al. Modeling and predicting low-speed vehicle emissions as a function of driving kinematics [J].
	Journal of Environmental Sciences, 2017, 55: 109-117.
[6]	Wang Z H, Qin K, Yin D D, et al. Prediction of heavy duty diesel vehicle emission based on GA-BP neural network with
	double hidden layer [J]. Journal of Hefei University of Technology (Natural Science), 2019, 42(6): 735-740.
	王志红, 秦可, 尹冬冬, 等. 基于双隐含层 GA-BP 神经网络的重型柴油车排放预测 [J]. 合肥工业大学学报 (自然科学
版)	, 2019, 42(6): 735-740.
[7]	Zuo F S, Li Z Y, Lv X, et al. Prediction of gasoline engine exhaust emission based on BP neural network [J]. Journal of Jiangsu
	University (Natural Science Edition), 2020, 41(3): 307-313.
	左付山, 李政原, 吕晓, 等. 基于 BP 神经网络的汽油机尾气排放预测 [J]. 江苏大学学报 (自然科学版), 2020, 41(3):
30	7-313.
[8]	Li C Q, Xie X P. Emission prediction of large buses based on portable emission mesurement systems and BP neural network
[J]	Automobile Technology, 2021, (1): 57-62.
	李昌庆, 谢小平. 基于便携式排放测试系统与 BP 神经网络的大型客车排放预测 [J]. 汽车技术, 2021, (1): 57-62.
[9]	Xu Z Y, Wang R J, Zhang C, et al. Automatic identification of high-emitting vehicle based on deep feature clustering [J].
	Journal of Transportation Systems Engineering and Information Technology, 2021, 21(6): 298-309.
	许镇义, 王仁军, 张聪, 等. 基于深度特征聚类的高排放移动污染源自动识别 [J]. 交通运输系统工程与信息, 2021, 21(6):
29	8-309.
[10]	Xu Z Y. Research on Comprehensive Supervision of Urban Mobile Source Emissions Based on Spatiotemporal Data Mining
[D]	Hefei: University of Science and Technology of China, 2020.
	许镇义. 基于时空数据挖掘的城市移动源污染综合监管问题研究 [D]. 合肥: 中国科学技术大学, 2020.
[11]	Zhang X C, Qiu J D, Qu X M, et al. Characteristics and influencing factors of traffic pollutant emission concentration in
	Shenzhen City [J]. Journal of Shenzhen University (Science and Engineering), 2020, 37(2): 178-186.
	张晓春, 丘建栋, 屈新明, 等. 深圳市交通排放污染物浓度特征与影响因素 [J]. 深圳大学学报 (理工版), 2020, 37(2):
17	8-186.
[12]	Lu Y J, Ni S Y, Wang H H, et al. Estimation of vehicle emission based on traffic flow on national and provincial roads in Hebei
	Province [J]. Acta Scientiae Circumstantiae, 2020, 40(12): 4483-4491.
	陆雅静, 倪爽英, 王洪华, 等. 河北省国道和省道机动车基于交通流量的尾气排放量估算 [J]. 环境科学学报, 2020,
40	(12): 4483-4491.
[13]	Robert T. Regression shrinkage and selection via the lasso [J]. Journal of the Royal Statistical Society: Series B (Methodological), 1996, 58(1): 267-288.
[14]	Shen S Y. Variable Selection of Complex Data Joint Model Based on Improved Lasso Method [D]. Wuhan: Huazhong University of Science and Technology, 2019.
	沈曙昀. 基于 Lasso 改进方法的复杂数据联合模型变量选择 [D]. 武汉: 华中科技大学, 2019.
[15]	Zhang X L. Research on Influence Factors of Taxi Emission Factors Based on Random Forest Regression [D]. Shenyang:
	Liaoning University, 2020.
	张馨露. 基于随机森林回归的出租车排放因子影响因素研究 [D]. 沈阳: 辽宁大学, 2020.
[16]	Xu Z Y, Kang Y, Lv W J. Analysis and prediction of vehicle exhaust emission using ANN [C]. 2017 36th Chinese Control
	Conference (CCC), July 26-28, 2017, Dalian, China. IEEE, 2017: 4029-4033.
[17]	Wang J J, Xu Z B. Approximation method of multivariate polynomials by feedforward neural networks [J]. Chinese Journal of
	Computers, 2009, 32(12): 2482-2488.
	王建军, 徐宗本. 多元多项式函数的三层前向神经网络逼近方法 [J]. 计算机学报, 2009, 32(12): 2482-2488.
[18]	Wang Q, Yu Y F, Zhang H J. Function approximation using artificial nueral networks [J]. Computer Simulation, 2002, 19(5):
44	-47.
	王强, 余岳峰, 张浩炯. 利用人工神经网络实现函数逼近 [J]. 计算机仿真, 2002, 19(5): 44-47.
[19]	Li J. Apparel Inventory Control and Neural Network Forecast Algorithm Research [D]. Wuxi: Jiangnan University, 2009.
	李娟. 服装库存控制及神经网络预测算法研究 [D]. 无锡: 江南大学, 2009.
[20]	Yao Y, Rosasco L, Caponnetto A. On early stopping in gradient descent learning [J]. Constructive Approximation, 2007, 26(2):
28	9-315.