Development of a representative driving cycle for urban buses based on the K-means cluster method
- 487 Downloads
To establish a representative driving cycle for public urban buses in Fuzhou city, real-world driving data of 18 buses’ routes was gathered. Based on acquisition of the real operational data, about 2.2 million seconds of valid data was divided into 8262 micro trips and an evaluation metric comprised of 15 characteristic parameters was established. Next, principal component analysis was applied for dimensionality reduction of the characteristic parameters and all micro trips were classified into different clusters by K-means clustering. Subsequently, the Silhouette equation was introduced as part of the cluster selection procedure. Finally, the target driving cycle, containing a 1227 second speed-time series, was developed according to a comprehensive estimation of six characteristic parameters and a maximum of the speed-acceleration frequency distribution. The experimental results verified the effectiveness and accuracy of the proposed method.
KeywordsDriving cycle Micro trip Principal component analysis K-means clustering Silhouette equation
The author would like to thank the generous support of the research project of China Automotive Test Cycles and the research program of Collaborative Innovation Center for R&D of Coach and Special Vehicle.
- 4.Wi, H., Park, J., Lee, J., Kim, W. et al.: Development of a city bus driving cycle in Seoul based on the actual patterns of urban bus driving. SAE Technical Paper, 2009-01-2914. (2009). https://doi.org/10.4271/2009-01-2914
- 7.Fotouhi, A., Montazeri-Gh, M.: Tehran driving cycle development using the K-means clustering method. Sci. Iran. 20(2), 286–293 (2013)Google Scholar
- 8.Tamsanya, N., Chungpaibulpattana, S., Atthajariyakul, S.: Development of automobile Bangkok driving cycle for emissions and fuel consumption assessment. In: Proceedings of the 2nd Joint International Conference on Sustainable Energy and Environment, Bangkok, 21–23, November 2006 (2006)Google Scholar
- 10.Datong, Q., Sen, Z., Zhenggang, Q., Shujiang, C.: Driving cycle construction using K-means clustering method. J. Jilin Univ. Eng. Technol. 46(2), 383–389 (2016)Google Scholar
- 14.Singh, A., Yadav, A., Rana, A.: K-means with three different distance metrics. Int. J. Comput. Appl. (0975–8887) 67(10), 13–17 (2013)Google Scholar
- 16.Fernandes, S.L., Gurupur, V.P., Sunder, N.R., Arunkumar, N., Kadry, S.: A novel nonintrusive decision support approach for heart rate measurement. Pattern Recognit. Lett. (2017). https://doi.org/10.1016/j.patrec.2017.07.002