This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Using Deep Reinforcement Learning for Hybrid Electric Vehicle Energy Management under Consideration of Dynamic Emission Models
Technical Paper
2020-01-2258
ISSN: 0148-7191, e-ISSN: 2688-3627
This content contains downloadable datasets
Annotation ability available
Sector:
Language:
English
Abstract
Hybrid electric vehicles (HEV) contribute to reduce emissions from transportation. The energy management controls the powertrain components in HEVs. In addition to minimizing fuel consumption, improving air quality is a major opportunity for hybrid vehicles. Pollutant emissions can only be mapped with sufficient accuracy using dynamic models. The introduced nitrogen oxide model is created using a supervised learning approach based on recorded measurement data. This dynamic model requires input data from previous time steps to ensure sufficient model quality. Classical algorithms such as Dynamic Programming are not able to find solutions for such high-dimensional problems in reasonable computing times. A promising approach to solve the resulting problem is Deep Reinforcement Learning (Deep RL), which has recently been introduced in the field of HEV energy management. Due to the significantly shorter computing times of the Deep RL it is possible to train the energy management with extensive stochastic driving cycles and additionally to consider other relevant system variables such as battery temperature or battery derating. Since the use of the dynamic emission model involves the violation of the Markov condition, the contribution shows an approach to solve the emerging Partially Observable Markov Decision Process (POMDP) using a DDPG agent. The paper thus presents a new multi-criteria optimization algorithm for the design of a diesel hybrid energy management observing fuel consumption and nitrogen oxide emissions. The results show a great potential concerning the reduction of the regarded exhaust gas components in real traffic situations.
Authors
Citation
Fechert, R., Lorenz, A., Liessner, R., and Bäker, B., "Using Deep Reinforcement Learning for Hybrid Electric Vehicle Energy Management under Consideration of Dynamic Emission Models," SAE Technical Paper 2020-01-2258, 2020, https://doi.org/10.4271/2020-01-2258.Data Sets - Support Documents
| Title | Description | Download |
|---|---|---|
| Unnamed Dataset 1 | ||
| Unnamed Dataset 2 | ||
| Unnamed Dataset 3 | ||
| Unnamed Dataset 4 |
Also In
References
- Zhu , D. , and Pritchard , E. NCSU Year Three Final Technical Report SAE Technical Paper 2014-01-2907 2014 10.4271/2014-01-2907
- Helbing , M. , Uebel , S. , Tempelhahn , C. , and Bäker , B. An Evaluated Review of Powertrain Control Strategies for Hybrid Electrical Vehicles ATZelektronik Worldwide 4 2015 10.1007/s38314-015-0537-6
- Bellman , R. The Theory of Dynamic Programming Bulletin of the American Mathematical Society 60 6 1954 0002-9904
- Pontryagin , L.S. , Boltyanskii , V.G. , Gamkrelidze , R.V. , and Mishchenko , E.F. The Mathematical Theory of Optimal Processes New York Interscience Publishers 1962 9780470693810
- Paganelli , G. , Guerra , T.M. , Delprat , S. , Santin , J.-J. , et al. Simulation and Assessment of Power Control Strategies for a Parallel Hybrid Car Proceedings of the Institution of Mechanical Engineers, Journal of Automobile Engineering 214 7 2000 0954-4070
- Bovee , K. , Hyde , A. , Yard , M. , Gallo , E. , et al. Fabrication of a Parallel-Series PHEV for the EcoCAR 2 Competition SAE Technical Paper 2013-01-2491 2013 https://doi.org/10.4271/2013-01-2491
- Nüesch , T. 2014
- Barth , M. , An , F. , Norbeck , J. , and Ross , M. Modal Emissions Modeling: A Physical Approach Transportation Research Record 1520 1996 10.3141/1520-10
- Hirsch , M. , Oppenauer , K. , and Del Re , L. Automotive Model Predictive Control London Springer 2010 73 87 10.1007/978-1-84996-071-7
- Ließner , R. 2020
- Fechert , R. , Bäker , B. , Gereke , S. , and Atzler , F. Using Machine Learning Methods to Develop Virtual NOx Sensors for Vehicle Applications 20. Internationales Stuttgarter Symposium Springer Vieweg 2020 978-3-658-29943-9
- Lorenz , A. 2020
- Engelhardt , T. 2016 10.1007/978-3-658-18207-6
- Bohn , C. , and Unbehauen , H. Identifikation dynamischer Systeme Wiesbaden Springer Vieweg 2016 10.1007/978-3-8348-2197-3
- Nelles , O. LOLIMOT-Lokale, lineare Modelle zur Identifikation nichtlinearer, dynamischer Systeme Automatisierungstechnik 45.4 De Gruyter 2010 163 174 10.1524/auto.1997.45.4.163
- Hametner , C. , Mayr , C. , and Jakubek , S. Dynamic NOx Emission Modelling Using Local Model Networks International Journal of Research 1.5 8 928 933 2014 10.1177/1468087414523281
- Sutton , R. and Barto , A. Reinforcement Learning: An Introduction MIT Press 2018 978-0-262-03924-6
- Lillicrap , T. , Hunt , J. , Pritzel , A. , Heess , N. , et al. 2015
- Hausknecht , M. and Stone , P. 2015
- Mnih , V. , Kavukcuoglu , K. , Silver , D. , Rusu , A. , et al. Human-Level Control through Deep Reinforcement Learning Nature 518 529 533 2015 10.1038/nature14236
- Marotta , A. , Tutuainu , M. Martini , G. 2012 10.2790/53651
- Tutuainu , M. , Marotta , A. , Steven , H. , Ericsson , E. , et al. 2014
- Samek , W. , Montavon , G. , Vedaldi , A. , Hamsen , L. , and et-al. Explainable AI: Interpreting, Explaining and Visualizing Deep Learning Springer International Publishing 2019 10.1007/978-3-030-28954-6