This content is not included in your SAE MOBILUS subscription, or you are not logged in.
Using Machine Learning to Guide Simulations Over Unique Samples from Trip Profiles
ISSN: 0148-7191, e-ISSN: 2688-3627
Published April 03, 2018 by SAE International in United States
This content contains downloadable datasetsAnnotation ability available
Electric vehicles are highly sensitive to variations in environmental factors (like temperature, drive style, grade, etc.). The distribution of real-world range of electric vehicles due to these environmental factors is an important consideration in target setting. This distribution can be obtained by running several simulations of an electric vehicle for a number of high-frequency velocity, grade, and temperature real-world trip profiles. However, in order to speed up simulation time, a unique set of drive profiles that represent the entire real-world data set needs to be developed.
In this study, we consider 40,000 unique velocity and grade profiles from various real-world applications in EU. We generate metadata that describes these profiles using trip descriptor variables. Due to the large number of descriptor variables when considering second order effects, we normalize each descriptor and use principal component analysis to reduce the dimensions of our dataset to six components. This is based on achieving a high explained variance ratio. Clustering is then performed on this dataset using the k-means algorithm implemented in Scikit-learn. We select sample representative trips by optimizing between the inertia obtained from the k-means algorithm and the explained variance ratio of principal component analysis. The number of representative trips selected is also driven by the performance of simulations for real-world range calculations. Range simulations can now be performed on these select representative trips to obtain a distribution of expected real-world range.
|Technical Paper||Breadth-First Search-Based Remaining Range Estimation and Representation for Electric Vehicle|
|Technical Paper||The Development of Powertrain Control Unit (PCU) for Parallel Hybrid Electric Vehicle (PHEV)|
CitationAhmed, N. and Kapadia, J., "Using Machine Learning to Guide Simulations Over Unique Samples from Trip Profiles," SAE Technical Paper 2018-01-1202, 2018, https://doi.org/10.4271/2018-01-1202.
Data Sets - Support Documents
|Unnamed Dataset 1|
- Global EV https://www.iea.org/publications/freepublications/publication/GlobalEVOutlook2017.pdf
- Miller , J. 2004
- Carlson , R. Duoba , M. , Bohn T.P. , and Vyas A.D. Testing and Analysis of Three Plug-in Hybrid Electric Vehicles Technical Paper No. 2007-01-0283 2007
- Ahmed , N. and Kapadia , J. Seasonality Effect on Electric Vehicle Miles Traveled in Electrified Vehicles SAE Int. J. Alt. Power. 6 1 47 53 2017 10.4271/2017-01-1146
- Ehsani , M. , Gao , Y. , and Emadi , A. Modern Electric, Hybrid Electric, and Fuel Cell Vehicles: Fundamentals, Theory, and Design CRC press 2009
- Python Software Foundation http://www.python.org
- McKinney , W. Python for Data Analysis: Data Wrangling with Pandas, NumPy, and IPython O'Reilly Media, Inc. 2012
- Van Der Walt , Stefan , S.C.C. , and Varoquaux , G. The NumPy Array: A Structure for Efficient Numerical Computation Computing in Science & Engineering 13 2 22 30 2011
- Pedregosa , F. , Varoquaux , G. , Gramfort , A. , Michel , V. et al. Scikit-learn: Machine learning in Python Journal of Machine Learning Research 12 2825 2830 2011
- Zaharia , M. , Chowdhury , M. , Franklin , M.J. , Shenker , S. , and Stoica , I. Spark: Cluster Computing with Working Sets HotCloud 10 10-10 95 2010
- Ahmed , N.
- Koza , J.R. , Bennett , F.H. , Andre , D. , and Keane , M.A. Automated Design of both the Topology and Sizing of Analog Electrical Circuits Using Genetic Programming. Artificial Intelligence in Design ‘96 Dordrecht Springer 1996 151 170 10.1007/978-94-009-0279-4_9
- Mitchell , T. 1997 Machine Learning McGraw Hill 2 0-07-042807-7
- Mametjanov , Azamat , Prasanna Balaprakash , Chekuri Choudary , Paul D. Hovland , Stefan M. Wild , and Gerald Sabin 2015
- Längkvist , M. , Karlsson , L. , and Loutfi , A. A Review of Unsupervised Feature Learning and Deep Learning for Time-Series Modeling Pattern Recognition Letters 42 11 24 2014