Abstract
To contract a more representative vehicle driving cycle, real-world driving data of a motor vehicle in Fuzhou area for 20 days are obtained. A total of 14 characteristic parameters were selected to represent the kinematic fragment information, principal component analysis, and K-means clustering were applied for clustering the divided kinematic fragment, and the candidate fragments were selected according to the distance of the clustering center and randomly combined to construct the condition set. A total of 11 characteristic parameters were selected to calculate the error of the construction driving cycle, we selected the driving state with the slightest error in the set as the construction driving condition. The improved autoencoder is used to build the driving cycle optimization model, the parameter calibration methods is proposed, and finally the average error is reduced from 2.97 to 2.39%. The analysis result and validation show that the optimization strategy can avoid the error uncertainty caused by the random selection effectively. The rationality of the proposed driving cycle construction process is verified, the accuracy of the driving cycle prediction is improved, and the recommended values of the model parameters are obtained. In addition, the characteristics and application significance of the construction driving cycle in different periods, road types, and data acquisition methods are analyzed.
Similar content being viewed by others
References
Achour H, Olabi AG (2016) Driving cycle developments and their impacts on energy consumption of transportation. J Clean Prod 112:1778–1788. https://doi.org/10.1016/j.jclepro.2015.08.007
Ahmed I, Xu D, Rouphail N et al (2019) Lane change rates at freeway weaving sites: trends in HCM6 and from NGSIM trajectories. Transp Res Rec. https://doi.org/10.1177/0361198119841281
Brady J, O’Mahony M (2016) Development of a driving cycle to evaluate the energy economy of electric vehicles in urban areas. Appl Energy 177:165–178. https://doi.org/10.1016/j.apenergy.2016.05.094
Ceylan A, Aytac V (2020) Convolutional auto encoders for sentence representation generation. Turk J Electr Eng Comput Sci 28(2):1135–1148. https://doi.org/10.3906/elk-1907-13
Chen F, Zhou S, Hua Y et al (2021) A novel method of developing driving cycle for electric vehicles to evaluate the private driving habits. IEEE Access 9:46476–46486. https://doi.org/10.1109/ACCESS.2021.3049411
Esteves-Booth A, Muneer T, Kirby H et al (2001) The measurement of vehicular driving cycle within the City of Edinburgh. Transp Res Part D Transp Environ 6(3):209–220. https://doi.org/10.1016/S1361-9209(00)00024-9
FHWA (2004) Next generation simulation (NGSIM). https://ops.fhwa.dot.gov/trafficanalysistools/ngsim.htm
Fotouhi A, Montazeri GM (2013) Tehran driving cycle development using the k-means clustering method. Scientia Iranica 20(2):286–293. https://doi.org/10.1016/j.scient.2013.04.001
Hao S, Yang L, Shi Y (2018) Data-driven car-following model based on rough set theory. IET Intel Transp Syst 12(1):49–57. https://doi.org/10.1049/iet-its.2017.0006
He H, Guo J, Peng J et al (2018) Real-time global driving cycle construction and the application to economy driving pro system in plug-in hybrid electric vehicles. Energy 152:95–107. https://doi.org/10.1016/j.energy.2018.03.061
Hou B, Yang J, Wang P et al (2020) LSTM-based auto-encoder model for ECG arrhythmias classification. IEEE Trans Instrum Meas 69(4):1232–1240. https://doi.org/10.1109/TIM.2019.2910342
Hui Q, Zhang K, Kemei J (2020) Research on water quality prediction method based on AE-LSTM. In: Proceedings of 5th international conference on automation, control and robotics engineering (CACRE 2020). Ed. IEEE Express Conference Publishing, pp 627–631. https://doi.org/10.1109/CACRE50138.2020.9230316
Huzayyin OA, Saleh H, Hassan MA (2021) A representative urban driving cycle for passenger vehicles to estimate fuel consumption and emission rates under real-world driving conditions. Urban Clim 36:100810. https://doi.org/10.1016/j.uclim.2021.100810
Komorska I, Puchalski A, Niewczas A et al (2021) Adaptive driving cycles of EVs for reducing energy consumption. Energies. https://doi.org/10.3390/en14092592
Lin J, Niemeier DA (2003a) Regional driving characteristics, regional driving cycles. Transp Res Part D Transp Environ 8(5):361–381. https://doi.org/10.1016/S1361-9209(03)00022-1
Lin J, Niemeier DA (2003b) Estimating regional air quality vehicle emission inventories: constructing robust driving cycles. Transp Sci 37(3):330–346. https://doi.org/10.1287/trsc.37.3.330.16045
Liu XD, Ma J, Zhao X et al (2020) Study on driving cycle synthesis method for City buses considering random passenger load. J Adv Transp 2:1–21. https://doi.org/10.1155/2020/3871703
Mayakuntla SK, Verma A (2018) A novel methodology for construction of driving cycles for Indian cities. Transp Res Part D Transp Environ 65:725–735. https://doi.org/10.1016/j.trd.2018.10.013
Nouri P, Morency C (2017) Evaluating microtrip definitions for developing driving cycles. Transp Res Rec. https://doi.org/10.3141/2627-10
Pan CF, Tao YX, Wang L et al (2021) Fuzzy energy management strategy for electric vehicle combining driving cycle construction and air-conditioning load identification. Adv Mech Eng. https://doi.org/10.1177/1687814021994381
Purkayastha S, Mondal I, Sarkar S et al (2019) Drug–drug interactions prediction based on drug embedding and graph auto-encoder. In: 2019 IEEE 19th international conference on bioinformatics and bioengineering (BIBE), pp 547–552. https://doi.org/10.1109/BIBE.2019.00104
Ralašić I, Damir S, Sarkar S (2020) Perceptual autoencoder for compressive sensing image reconstruction. Informatica. https://doi.org/10.15388/20-INFOR421
Ramya M, Desineedi S, Mahesh GR (2020) Developing driving cycles using k-means clustering and determining their optimal duration. Transp Res Procedia. https://doi.org/10.1016/j.trpro.2020.08.268
Wei W, Wu H, Ma H (2019) An autoencoder and LSTM-based traffic flow prediction method. Sensors 19(13):2946
Xiao Z, Xu X, Zhang H et al (2021a) A new multi-process collaborative architecture for time series classification. Knowl-Based Syst 220(3):106934. https://doi.org/10.1016/j.knosys.2021.106934
Xiao Z, Xu X, Xing HL et al (2021b) RTFN: a robust temporal feature network for time series classification. Inf Sci 571:65–86. https://doi.org/10.1016/j.ins.2021.04.053
Xuan ZA, Xz B, Qiang YA et al (2020) Development of a representative urban driving cycle construction methodology for electric vehicles: a case study in Xi’an. Transp Res Part D. https://doi.org/10.1016/j.trd.2020.102279
Yang Y, Tiezhu L, Hongfei H et al (2019) Development and emissions performance analysis of local driving cycle for small-sized passenger cars in Nanjing, China. Atmos Pollut Res. https://doi.org/10.1016/j.apr.2019.04.009
Zhang J, Wang ZP, Liu P et al (2019) Driving cycles construction for electric vehicles considering road environment: a case study in Beijing. Appl Energy. https://doi.org/10.1016/j.apenergy.2019.113514
Acknowledgements
This research is supported by National Natural Science Foundation of China (41771182), Science and Technology Program of the Ministry of Housing and Urban-Rural Development (2016-K2-034), Beijing Municipal Natural Science Foundation (8184066) and Beijing Social Science Foundation (21GLB034).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Lin, J., Liu, B. & Zhang, L. Autoencoder-based optimization method for driving cycle construction: a case study in Fuzhou, China. J Ambient Intell Human Comput 14, 12635–12650 (2023). https://doi.org/10.1007/s12652-022-04317-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-022-04317-7