Development of a Typical Urban Driving Cycle for Battery Electric Vehicles Based on Kernel Principal Component Analysis and Random Forest

Great concerns have been raised on the driving cycle due to its critical importance in vehicle design, energy management strategy, and energy consumption forecast of new energy vehicles. Taking Xi’an city as a case, a novel method of driving cycle development for battery electric vehicles is proposed in this paper. First, the chase car method and on-board measurement method are combined to collect sufficient real driving data, which are randomly divided into two parts for developing and validating the target cycle. Then the nonlinear dimension reduction of characteristic parameters with respect to the micro-trips is achieved by employing kernel principal component analysis, and an improved clustering method is developed for constructing candidate cycles, in which the K-means clustering algorithm is applied in the training of random forest. The target cycle is selected from the candidate cycles by determining the assessment criteria with consideration of the characteristic parameters and the speed-acceleration distribution probability. Finally, a comparative study of different methods is implemented to illustrate the effectiveness of the proposed method. The typicality of the target cycle is revealed by analyzing the discrepancies between the target cycle and other legislative cycles.

[1]  Gwo-Hshiung Tzeng,et al.  Developing A Taipei motorcycle driving cycle for emissions and fuel economy , 1998 .

[2]  Qin Shi,et al.  A genetic ant colony algorithm-based driving cycle generation approach for testing driving range of battery electric vehicle , 2020 .

[3]  Fengchun Sun,et al.  Generation of a driving cycle for battery electric vehicles：A case study of Beijing , 2018 .

[4]  Xuan Zhao,et al.  Construction of electric vehicle driving cycle for studying electric vehicle energy consumption and equivalent emissions , 2020, Environmental Science and Pollution Research.

[5]  Wei Yan,et al.  A Novel k-MPSO Clustering Algorithm for the Construction of Typical Driving Cycles , 2020, IEEE Access.

[6]  Chih-Hung Wu,et al.  A Novel Big Data Modeling Method for Improving Driving Range Estimation of EVs , 2015, IEEE Access.

[7]  Xu Chao,et al.  Statistical inference-based research on sampling time of vehicle driving cycle experiments , 2017 .

[8]  Xiaoyang Tan,et al.  Enhanced Local Texture Feature Sets for Face Recognition Under Difficult Lighting Conditions , 2007, AMFG.

[9]  Hassan Ismkhan,et al.  I-k-means-+: An iterative clustering algorithm based on an enhanced version of the k-means , 2018, Pattern Recognit..

[10]  H. Korkmaz,et al.  Development of a driving cycle for Istanbul bus rapid transit based on real-world data using stratified sampling method , 2019, Transportation Research Part D: Transport and Environment.

[11]  Abdul-Ghani Olabi,et al.  Driving cycle developments and their impacts on energy consumption of transportation , 2016 .

[12]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[13]  Zhang Xiao,et al.  A Synthesis of Methodologies and Practices for Developing Driving Cycles , 2012 .

[14]  Yongxing Wang,et al.  Estimating remaining driving range of battery electric vehicles based on real-world data: A case study of Beijing, China , 2019, Energy.

[15]  Xiaoyang Tan,et al.  Enhanced Local Texture Feature Sets for Face Recognition Under Difficult Lighting Conditions , 2007, IEEE Transactions on Image Processing.

[16]  Marco Pierini,et al.  Development of driving cycles for electric vehicles in the context of the city of Florence , 2016 .

[17]  Yan Wu,et al.  Developing an electric vehicle urban driving cycle to study differences in energy consumption , 2018, Environmental Science and Pollution Research.

[18]  Antanas Verikas,et al.  Mining data with random forests: A survey and results of new tests , 2011, Pattern Recognit..

[19]  Yang Yang,et al.  Time dimension analysis: Comparison of Nanjing local driving cycles in 2009 and 2017 , 2020 .

[20]  Zahir Tari,et al.  A Survey of Clustering Algorithms for Big Data: Taxonomy and Empirical Analysis , 2014, IEEE Transactions on Emerging Topics in Computing.

[21]  T. Lumley,et al.  PRINCIPAL COMPONENT ANALYSIS AND FACTOR ANALYSIS , 2004, Statistical Methods for Biomedical Research.

[22]  Jian Ma,et al.  Development of a Representative EV Urban Driving Cycle Based on a k-Means and SVM Hybrid Clustering Algorithm , 2018, Journal of Advanced Transportation.

[23]  Margaret O'Mahony,et al.  Development of a driving cycle to evaluate the energy economy of electric vehicles in urban areas , 2016 .

[24]  Xiaodong Liu,et al.  Study on Driving Cycle Synthesis Method for City Buses considering Random Passenger Load , 2020 .

[25]  H. Y. Tong,et al.  A Framework for Developing Driving Cycles with On‐Road Driving Data , 2010 .

[26]  José Ignacio Huertas,et al.  Comparison of Three Methods for Constructing Real Driving Cycles , 2019, Energies.

[27]  Yiik Diew Wong,et al.  Developing Singapore Driving Cycle for passenger cars to estimate fuel consumption and vehicular emissions , 2014 .

[28]  Hong Huo,et al.  Characterization of vehicle driving patterns and development of driving cycles in Chinese cities , 2008 .

[29]  Wing-tat Hung,et al.  Development of a driving cycle for Hong Kong , 1999 .

[30]  Tom V. Mathew,et al.  Development of real-world driving cycle: Case study of Pune, India , 2009 .

[31]  Ali Ashtari,et al.  Using Large Driving Record Samples and a Stochastic Approach for Real-World Driving Cycle Construction: Winnipeg Driving Cycle , 2014, Transp. Sci..

[32]  Bernhard Schölkopf,et al.  Nonlinear Component Analysis as a Kernel Eigenvalue Problem , 1998, Neural Computation.

[33]  Yiming Ye,et al.  Development of a representative urban driving cycle construction methodology for electric vehicles: A case study in Xi’an , 2020 .

[34]  José Ignacio Huertas,et al.  Driving Cycles Based on Fuel Consumption , 2018, Energies.

[35]  Andrzej Cichocki,et al.  Kernel PCA for Feature Extraction and De-Noising in Nonlinear Regression , 2001, Neural Computing & Applications.

[36]  Chi Ma,et al.  Fault diagnosis of nonlinear processes using multiscale KPCA and multiscale KPLS , 2011 .

[37]  Biagio Ciuffo,et al.  Development of the World-wide harmonized Light duty Test Cycle (WLTC) and a possible pathway for its introduction in the European legislation , 2015 .

[38]  J. Mercer.  Functions of Positive and Negative Type, and their Connection with the Theory of Integral Equations , 1909 .

[39]  Nak-Tak Jeong,et al.  Urban driving cycle for performance evaluation of electric vehicles , 2016 .

[40]  Anh-Tuan Le,et al.  Development of the typical driving cycle for buses in Hanoi, Vietnam , 2018, Journal of the Air & Waste Management Association.

[41]  Mohammad Khalilia,et al.  Predicting disease risks from highly imbalanced data using random forest , 2011, BMC Medical Informatics Decis. Mak..

[42]  C. P. Lee,et al.  Development of a practical driving cycle construction methodology: A case study in Hong Kong , 2007 .

[43]  S. M. Shiva Nagendra,et al.  Development of driving cycles for passenger cars and motorcycles in Chennai, India , 2017 .

[44]  Guolin Wang,et al.  Building Tianjin driving cycle based on linear discriminant analysis , 2017 .