-
摘要: 为了优化汽车行驶性能, 制定了反映中国实际道路行驶状况的测试工况, 以轻型汽车道路实测数据为数据源, 提出了城市道路汽车行驶工况构建方法; 数据采集覆盖主要时段和道路, 剔除了异常数据, 并引入多尺度小波变换对车速降噪; 利用3层小波分解过滤地面扰动的影响, 保留车速关键信息; 基于9种与行驶特性密切相关且具有代表性的特征参数建立汽车运动学片段特征体系; 分别利用主成分分析和自编码器对特征降维处理, 使用K-means++聚类算法确定运动学片段, 并引入Silhouette函数筛选聚类结果以替代人工选择, 确定聚类类别为2类; 以与相应聚类中心的距离为指标, 筛选出各类别中最能反映本类别特性的200个运动学片段, 作为候选运动学片段, 最终以基于最小性能值的评估方法确定代表性运动学片段, 完成了汽车行驶工况的构建, 分别得到主成分分析和自编码器2种降维处理对应的汽车行驶工况曲线。计算结果表明: 以主成分分析和自编码器2种处理方法为基础构建的汽车行驶工况对数据源均体现了较高的代表性与合理性, 基于主成分分析降维最终得到的数据与数据源的相对误差绝对值多数低于10%, 其中平均速度、平均行驶速度、怠速时间比、加速时间比、减速时间比、平均加速度、加速度标准差、平均减速度的相对误差分别为0.75%、5.50%、9.14%、9.80%、9.98%、8.45%、6.17%、7.73%, 仅速度标准差的相对误差较大, 为24.31%, 与自编码器方法得到的结果相比具有更强的综合代表性, 更适合用于汽车行驶工况的构建。Abstract: In order to optimize vehicle driving performance, test cycles reflecting actual road driving cycles in China were constructed. Taking the measured road data of light-duty vehicles as the data source, the vehicle driving cycle construction method of urban road was proposed. Data collection covered the main period and roads, the abnormal data were eliminated, and the multi-scale wavelet transform was introduced to reduce the noise of vehicle speed. Three-layer wavelet decomposition was used to filter the impact of ground disturbance, and the key information of vehicle speed was retained. The car kinematics segment feature system based on 9 representative characteristic parameters closely related to the driving characteristics was established. Principal component analysis and auto-encoder were used to reduce the dimension of features. K-means++clustering algorithm was used to determine the kinematics segments and the Silhouette function was introduced to filter the clustering results to replace manual selection, and determine the number of clusters of 2 categories. The distance from the corresponding cluster center was used as an indicator, 200 kinematic segments in each category that can best reflect the characteristics of the category were selected as the candidate kinematic segments. Finally, the representative kinematic segments were determined based on the minimum performance value evaluation method, the construction of vehicle driving construction was finished, and the corresponding vehicle driving cycles curves based on principal component analysis and auto-encoder were obtained respectively. Calculation results show that vehicle driving cycle construction based on principal component analysis and auto-encoder is highly representative and reasonable according to the data source. The absolute valves of relative errors between the data based on principal component analysis and the data source are mostly less than 10%. The relative errors of average speed, average driving speed, idle time ratio, acceleration time ratio, deceleration time ratio, average acceleration, acceleration standard difference, and average deceleration are 0.75%, 5.50%, 9.14%, 9.80%, 9.98%, 8.45%, 6.17% and 7.73%, respectively. Only the relative error of velocity standard deviation reaches 24.31%. Therefore, the principal component analysis has stronger comprehensive advantages than the results obtained by the auto-encoder method, and it is more suitable for vehicle driving condition construction.
-
图 5 车速数据文件1小波分解系数
Figure 5. Wavelet decomposition coefficients of vehicle speed data file 1
表 1 运动学片段数量
Table 1. Number of kinematic clips
文件编号 文件1 文件2 文件3 总数 运动学片段数量 1 268 1 788 1 298 4 354 
下载: 导出CSV
表 2 各主成分贡献率与累计贡献率
Table 2. Contribution rates and cumulative contribution rates of each principal component
主成分序号 特征值 贡献率/% 累计贡献率/% 1 3.54 39.32 39.32 2 2.44 27.06 66.38 3 1.74 19.31 85.69 4 0.61 6.74 92.43 5 0.33 3.72 96.14 6 0.15 1.67 97.81 7 0.11 1.20 99.01 8 0.07 0.79 99.81 9 0.02 0.19 100.00
下载: 导出CSV
表 3 主成分载荷系数
Table 3. Load factors of each principal component
原始特征 M1 M2 M3 平均速度/(km·h-1) 0.46 -0.23 -0.16 平均行驶速度/(km·h-1) 0.43 -0.18 -0.38 怠速时间比/% -0.39 0.17 -0.34 加速时间比/% 0.35 0.12 0.42 减速时间比/% 0.24 0.08 0.57 速度平均偏差/(km·h-1) 0.42 -0.17 -0.35 平均加速度/(m·s-2) 0.08 0.54 -0.17 加速度标准偏差/(m·s-2) 0.26 0.53 0.04 平均减速度/(m·s-2) -0.14 -0.51 0.26
下载: 导出CSV
表 4 主成分分量值
Table 4. Component values of each principal component
序号 M1 M2 M3 1 41.07 -5.05 -7.38 2 39.76 -0.21 8.43 3 41.05 -6.39 -17.09 ︙ ︙ ︙ ︙ 2 176 -25.36 15.03 -21.59 2 177 -27.81 16.74 -21.68 2 178 -23.69 13.82 -27.01 ︙ ︙ ︙ ︙ 4 352 -10.32 12.57 -45.23 4 353 19.51 -0.46 -30.84 4 354 76.81 -21.45 -21.01
下载: 导出CSV
表 5 AE降维所得特征值
Table 5. Eigenvalues obtained after dimension reduction of AE
运动学片段序号 隐含层节点1数值 隐含层节点2数值 隐含层节点3数值 1 95.96 263.52 18.57 2 76.54 250.75 34.53 3 117.99 281.37 -2.03 ︙ ︙ ︙ ︙ 2 176 149.62 203.93 -109.34 2 177 159.89 216.69 -116.97 2 178 156.32 210.12 -113.59 ︙ ︙ ︙ ︙ 4 352 201.36 274.89 -111.06 4 353 132.52 274.89 -46.84 4 354 149.03 351.07 56.87
下载: 导出CSV
表 7 基于PCA的特征参数数据对比
Table 7. Comparison of characteristic parameters data based on PCA
特征参数 所采集数据源 基于PCA的数据 数据相对误差绝对值/% 平均速度/(km·h-1) 23.36 23.18 0.75 平均行驶速度/(km·h-1) 36.22 34.22 5.50 怠速时间比/% 35.52 32.26 9.14 加速时间比/% 59.51 65.35 9.80 减速时间比/% 21.16 23.27 9.98 速度标准差/(km·h-1) 25.45 19.26 24.31 平均加速度/(m·s-2) 0.54 0.49 8.45 加速度标准差/(m·s-2) 2.51 2.35 6.17 平均减速度/(m·s-2) -0.66 -0.71 7.73
下载: 导出CSV
表 8 基于AE的特征参数数据对比
Table 8. Comparison of characteristic parameters data based on AE
特征参数 所采集数据源 基于AE的数据 数据相对误差绝对值/% 平均速度/(km·h-1) 23.36 25.55 9.39 平均行驶速度/(km·h-1) 36.22 42.40 17.07 怠速时间比/% 35.51 39.73 11.91 加速时间比/% 59.51 55.91 6.06 减速时间比/% 21.16 21.54 1.82 速度标准差/(km·h-1) 25.45 23.35 8.23 平均加速度/(m·s-2) 0.54 0.65 21.38 加速度标准差/(m·s-2) 2.51 2.47 1.42 平均减速度/(m·s-2) -0.66 -0.55 16.64
下载: 导出CSV
-
[1] HUERTAS J I, DIAZ J, CORDERO D, et al. A new methodology to determine typical driving cycles for the design of vehicles power trains[J]. International Journal on Interactive Design and Manufacturing, 2018, 12(1): 319-326. doi: 10.1007/s12008-017-0379-y [2] ACHOUR H, OLABI A G. Driving cycle developments and their impacts on energy consumption of transportation[J]. Journal of Cleaner Production, 2016, 112: 1778-1788. doi: 10.1016/j.jclepro.2015.08.007 [3] 石琴, 郑与波, 姜平. 基于运动学片段的城市道路行驶工况的研究[J]. 汽车工程, 2011, 33(3): 256-261. https://www.cnki.com.cn/Article/CJFDTOTAL-QCGC201103017.htmSHI Qin, ZHENG Yu-bo, JIANG Ping. A research on driving cycle of city roads based on microtrips[J]. Automotive Engineering, 2011, 33(3): 256-261. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-QCGC201103017.htm [4] BRADY J, O'MAHON M. Development of a driving cycle to evaluate the energy economy of electric vehicles in urban areas[J]. Applied Energy, 2016, 177: 165-178. doi: 10.1016/j.apenergy.2016.05.094 [5] CHAUHAN B P, JOSHI G J, PARIDA P. Driving cycle analysis to identify intersection influence zone for urban intersections under heterogeneous traffic condition[J]. Sustainable Cities and Society, 2018, 41: 180-185. doi: 10.1016/j.scs.2018.05.039 [6] 张建伟, 李孟良, 艾国和, 等. 车辆行驶工况与特征的研究[J]. 汽车工程, 2005, 27(2): 220-224, 245. doi: 10.3321/j.issn:1000-680X.2005.02.023ZHANG Jian-wei, LI Meng-liang, AI Guo-he, et al. A study on the features of existing typical vehicle driving cycles[J]. Automotive Engineering, 2005, 27(2): 220-224, 245. (in Chinese). doi: 10.3321/j.issn:1000-680X.2005.02.023 [7] HE Hong-wen, GUO Jin-quan, PENG Jian-kun, et al. Real-time global driving cycle construction and the application to economy driving pro system in plug-in hybrid electric vehicles[J]. Energy, 2018, 152: 95-107. doi: 10.1016/j.energy.2018.03.061 [8] GONG Hui-ming, ZOU Yuan, YANG Qing-kai, et al. Generation of a driving cycle for battery electric vehicles: a case study of Beijing[J]. Energy, 2018, 150: 901-912. doi: 10.1016/j.energy.2018.02.092 [9] WANG Zhen-po, ZHANG Jin, LIU Peng, et al. Driving cycle construction for electric vehicles based on Markov chain and Monte Carlo method: a case study in Beijing[J]. Energy Procedia, 2019, 158: 2494-2499. doi: 10.1016/j.egypro.2019.01.389 [10] YANG Ying, ZHANG Qing, WANG Zhen, et al. Markov chain-based approach of the driving cycle development for electric vehicle application[J]. Energy Procedia, 2018, 152: 502-507. doi: 10.1016/j.egypro.2018.09.201 [11] ZHANG Jin, WANG Zhen-po, LIU Peng, et al. Driving cycles construction for electric vehicles considering road environment: a case study in Beijing[J]. Applied Energy, 2019, 253: 113514-1-14. doi: 10.1016/j.apenergy.2019.113514 [12] TONG H Y. Development of a driving cycle for a supercapacitor electric bus route in Hong Kong[J]. Sustainable Cities and Society, 2019, 48: 101588-1-10. doi: 10.1016/j.scs.2019.101588 [13] SHEN Pei-hong, ZHAO Zhi-guo, LI Jing-wei, et al. Development of a typical driving cycle for an intra-city hybrid electric bus with a fixed route[J]. Transportation Research Part D: Transport and Environment, 2018, 59: 346-360. doi: 10.1016/j.trd.2018.01.032 [14] ZHAO Jing-yuan, GAO Yin-han, GUO Jian-hua, et al. The creation of a representative driving cycle based on intelligent transportation system (ITS) and a mathematically statistical algorithm: a case study of Changchun (China)[J]. Sustainable Cities and Society, 2018, 42: 301-313. doi: 10.1016/j.scs.2018.05.031 [15] QIU Duo-guan, LI Yuan, QIAO Da-peng. Recurrent neural network based driving cycle development for light duty vehicles in Beijing[J]. Transportation Research Procedia, 2018, 34: 147-154. doi: 10.1016/j.trpro.2018.11.026 [16] ARUN N H, MAHESH S, RAMADURAI G, et al. Development of driving cycles for passenger cars and motorcycles in Chennai, India[J]. Sustainable Cities and Society, 2017, 32: 508-512. doi: 10.1016/j.scs.2017.05.001 [17] GUNTHER R, WENZEL T, WEGNER M, et al. Big data driven dynamic driving cycle development for busses in urban public transportation[J]. Transportation Research Part D: Transport and Environment, 2017, 51: 276-289. doi: 10.1016/j.trd.2017.01.009 [18] JING Zhe-cheng, WANG Guo-lin, ZHANG Shu-pei, et al. Building Tianjin driving cycle based on linear discriminant analysis[J]. Transportation Research Part D: Transport and Environment, 2017, 53: 78-87. doi: 10.1016/j.trd.2017.04.005 [19] ZHANG Fei, GUO Fen, HUANG Hong. A study of driving cycle for electric special-purpose vehicle in Beijing[J]. Energy Procedia, 2017, 105: 4884-4889. doi: 10.1016/j.egypro.2017.03.967 [20] LI Yue-cheng, PENG Jian-kun, HE Hong-wen, et al. The study on multi-scale prediction of future driving cycle based on Markov chain[J]. Energy Procedia, 2017, 105: 3219-3224. doi: 10.1016/j.egypro.2017.03.709 [21] MAYAKUNTLA S K, VERMA A. A novel methodology for construction of driving cycles for Indian cities[J]. Transportation Research Part D: Transport and Environment, 2018, 65: 725-735. doi: 10.1016/j.trd.2018.10.013 [22] BERZI L, DELOGU M, PIERINI M. Development of driving cycles for electric vehicles in the context of the city of Florence[J]. Transportation Research Part D: Transport and Environment, 2016, 47: 299-322. doi: 10.1016/j.trd.2016.05.010 [23] SEERS P, NACHIN G, GLAUS M. Development of two driving cycles for utility vehicles[J]. Transportation Research Part D: Transport and Environment, 2015, 41: 377-385. doi: 10.1016/j.trd.2015.10.013 [24] ZHOU Wen-yu, XU Ke, YANG Ying, et al. Driving cycle development for electric vehicle application using principal component analysis and k-means cluster: with the case of Shenyang, China[J]. Energy Procedia, 2017, 105: 2831-2836. doi: 10.1016/j.egypro.2017.03.620 [25] AMIRJAMSHIDI G, ROORDA M J. Development of simulated driving cycles for light, medium, and heavy duty trucks: case of the Toronto Waterfront Area[J]. Transportation Research Part D: Transport and Environment, 2015, 34: 255-266. doi: 10.1016/j.trd.2014.11.010 [26] ACHOUR H, OLABI A G. Driving cycle developments and their impacts on energy consumption of transportation[J]. Journal of Cleaner Production, 2016, 112: 1778-1788. doi: 10.1016/j.jclepro.2015.08.007 [27] 张宏, 姚延钢, 杨晓勤. 城市道路轻型汽车行驶工况构建[J]. 西南交通大学学报, 2019, 54(6): 1139-1146, 1154. https://www.cnki.com.cn/Article/CJFDTOTAL-XNJT201906003.htmZHANG Hong, YAO Yan-gang, YANG Xiao-qin. Light-duty vehicles driving cycle construction based on urban roads[J]. Journal of Southwest Jiaotong University, 2019, 54(6): 1139-1146, 1154. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-XNJT201906003.htm [28] 彭育辉, 杨辉宝, 李孟良, 等. 基于K-均值聚类分析的城市道路汽车行驶工况构建方法研究[J]. 汽车技术, 2017(11): 13-18. doi: 10.3969/j.issn.1000-3703.2017.11.003PENG Yu-hui, YANG Hui-bao, LI Meng-liang, et al. Research on the construction method of driving cycle for the city car based on K-means cluster analysis[J]. Automobile Technology, 2017(11): 13-18. (in Chinese). doi: 10.3969/j.issn.1000-3703.2017.11.003 [29] 胡志远, 秦艳, 谭丕强, 等. 基于大样本的上海市乘用车行驶工况构建[J]. 同济大学学报(自然科学版), 2015, 43(10): 1523-1527. doi: 10.11908/j.issn.0253-374x.2015.10.011HU Zhi-yuan, QIN Yan, TAN Pi-qiang, et al. Large-sample-based car-driving cycle in Shanghai City[J]. Journal of Tongji University (Natural Science), 2015, 43(10): 1523-1527. (in Chinese). doi: 10.11908/j.issn.0253-374x.2015.10.011 [30] 姜平, 石琴, 陈无畏, 等. 基于小波分析的城市道路行驶工况构建的研究[J]. 汽车工程, 2011, 33(1): 70-73, 51. https://www.cnki.com.cn/Article/CJFDTOTAL-QCGC201101019.htmJIANG Ping, SHI Qin, CHEN Wu-wei, et al. A research on the construction of city road driving cycle based on wavelet analysis[J]. Automotive Engineering, 2011, 33(1): 70-73, 51. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-QCGC201101019.htm [31] 姜平, 石琴, 陈无畏. 聚类和马尔科夫方法结合的城市汽车行驶工况构建[J]. 中国机械工程, 2010, 21(23): 2893-2897. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGJX201023026.htmJIANG Ping, SHI Qin, CHEN Wu-wei. Driving cycle construction method of city motors based on clustering method and Markov process[J]. China Mechanical Engineering, 2010, 21(23): 2893-2897. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-ZGJX201023026.htm [32] LIN Jie, NIEMEIER D A. An exploratory analysis comparing a stochastic driving cycle to California's regulatory cycle[J]. Atmospheric Environment, 2002, 36(38): 5759-5770. doi: 10.1016/S1352-2310(02)00695-7 [33] ROY M, KUMAR V R, KULKARNI B D, et al. Simple denoising algorithm using wavelet transform[J]. AIChE Journal, 1999, 45(11): 2461-2466. doi: 10.1002/aic.690451120 [34] BHATTACHARYYA A, PACHORI R B, RAJENDRA ACHARYA U. Tunable-Q wavelet transform based multivariate sub-band fuzzy entropy with application to focal EEG signal analysis[J]. Entropy, 2017, 19: 1-14. [35] El B'CHARRI O, LATIF R, ELMANSOURI K, et al. ECG signal performance de-noising assessment based on threshold tuning of dual-tree wavelet transform[J]. Biomedical Engineering Online, 2017, 16: 1-18. [36] OTTO S E, ROWLEY C W. Linearly recurrent autoencoder networks for learning dynamics[J]. SIAM Journal on Applied Dynamical Systems, 2019, 18(1): 558-593. doi: 10.1137/18M1177846 [37] DENG Jun, ZHANG Zi-xing, EYBEN F, et al. Autoencoder-based unsupervised domain adaptation for speech emotion recognition[J]. IEEE Signal Processing Letters, 2014, 21(9): 1068-1072. doi: 10.1109/LSP.2014.2324759 [38] TEWARI A, ZOLLHOFER M, KIM H, et al. Mofa: model-based deep convolutional face autoencoder for unsupervised monocular reconstruction[C]//IEEE. 16th IEEE International Conference on Computer Vision. New York: IEEE, 2017: 1274-1283. -
点击查看大图
图(12) / 表(8)
计量
- 文章访问数: 957
- HTML全文浏览量: 150
- PDF下载量: 194
- 被引次数: 0
