Target State Optimization: Drivability Improvement for Vehicles with Dual Clutch Transmissions
Source abstract
Abstract
Vehicles with dual clutch transmissions (DCT) are well known for their comfortable drivability since gear shifts can be performed jerklessly. The ability of blending the torque during gear shifts from one clutch to the other, making the type of automated transmission a perfect alternative to torque converters, which also comes with a higher efficiency. Nevertheless, DCT also have some drawbacks. The actuation of two clutches requires an immense control effort, which is handled in the implementation of a wide range of software functions on the transmission control unit (TCU). These usually contain control parameters, which makes the behavior adaptable to different vehicle and engine platforms. The adaption of these parameters is called calibration, which is usually an iterative time-consuming process. The calibration of the embedded software solutions in control units is a widely known problem in the automotive industry. The calibration of any vehicle subsystem (e.g., engine, transmission, suspension, driver assistance systems for autonomous driving, etc.) requires costly test trips in different ambient conditions. To reduce the calibration effort and the accompanying use of professionals, several approaches to automize the calibration process are proposed. Due to the fact that a solution is desired which can optimize different calibration problems, a generic metaheuristic approach is aimed. Regardless, the scope of the current research is the optimization of the launch behavior for vehicles equipped with DCT since, particularly at low speeds, the transmission behavior must meet the intention of the driver (drivers tend to be more perceptive at low speeds). To clarify the characteristics of the launch, several test subject studies are performed. The influence factors, such as engine sound, maximal acceleration, acceleration build-up (mean jerk), and the reaction time, are taken into account. Their influence on the evaluation of launch with relation to the criteria of sportiness, comfort, and jerkiness, are examined based on the evaluation of the test subject studies. According to the results of the study, reference values for the optimization of the launch behavior are derived. The research contains a study of existing approaches for optimizing driving behavior with metaheuristics (e.g., genetic algorithms, reinforcement learning, etc.). Since the existing approaches have different drawbacks (in scope of the optimization problem) a new approach is proposed, which outperforms existing ones. The approach itself is a hybrid solution of reinforcement learning (RL) and supervised learning (SL) and is applied in a software in the loop environment, and in a test vehicle.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Electric and Hybrid Vehicle Technologies · Vehicle emissions and performance · Advanced Combustion Engine Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Magna PT B.V. & Co. KG, Hermann-Hagenmeyer-Straße 1, 74199 Untergruppenbach, Germany
Institute for Mechatronic Systems, Technical University of Darmstadt, Otto-Berndt-Straße 2, 64287 Darmstadt, Germany
Funding
Deutsche Forschungs- gemeinschaft (DFG—German Research Foundation) · Open Access Publishing Fund of Technical University of Darmstadt
References (75)
Show source-provided references
1. AI-based parameter optimization method-applied for vehicles with dual clutch transmissions
2. Automatic calibration process for optimal control of clutch engagement during launch10.1080/15397734.2016.1250221 ↗
3. Model-based and model-free learning strategies for wet clutch control10.1016/j.mechatronics.2014.03.006 ↗
4. Sun, Z., and Hebbale, K. (2005, January 8–10). Challenges and opportunities in automotive transmission control. Proceedings of the 2005 American Control Conference, Portland, OR, USA.
5. Fischer, R., Kücükay, F., Jürgens, G., and Pollak, B. (2016). Das Getriebebuch, Der Fahrzeugantrieb; Springer Vieweg. [2nd ed.].10.1007/978-3-658-13104-3 ↗
6. Simon, D. (2021, March 05). Entwicklung Eines Effizienten Verfahrens zur Bewertung des Anfahrverhaltens von Fahrzeugen. Available online: http://rosdok.uni-rostock.de/file/rosdok_disshab_0000000705/rosdok_derivate_0000004687/Dissertation__Simon_2011.pdf.
7. Bertram, T., Corves, B., Janschek, K., and Rinderknecht, S. (2022, January 23–24). Objektivierung subjektiver Kriterien für die Bewertung von Anfahrvorgängen. Proceedings of the Digital-Fachtagung VDI-MECHATRONIK, Darmstad Germany.
8. Skoda, S., Steffens, J., and Becker-Schweitzer, J. (2012). Einfluss von Fahrzeuggeräuschen auf die Subjektive Bewertung von Beschleunigung, Fortschritte der Akustik—DAGA 2012.
9. Kingma, H. (2005). Thresholds for perception of direction of linear acceleration as a possible evaluation of the otolith function. BMC Ear Nose Throat Disord., 5.10.1186/1472-6815-5-5 ↗
10. The role of acceleration and jerk in perception of above-threshold surge motion10.1007/s00221-020-05745-7 ↗
11. Spering, M., and Schmidt, T. (2017). Wahrnehmung, Aufmerksamkeit, Denken, Sprache, Beltz. [3rd ed.]. Allgemeine Psychologie kompakt.
12. Haycock, B., and Grant, P.R. (2007, January 12–14). The influence of jerk on perceived simulator motion strength. Proceedings of the Driving Simulation Conference, Iowa City, IA, USA.
13. A fast and elitist multiobjective genetic algorithm: NSGA-II10.1109/4235.996017 ↗
14. Darwin, C., and Bynum, W.F. (1894). The Origin of Species by Means of Natural Selection: Or the Preservation of Favored Races in the Struggle for Life, AL Burt New York.10.5962/bhl.title.56969 ↗
15. Knippers, R. (2006). Molekulare Genetik, Georg Thieme Verlag.10.1055/b-002-25587 ↗
16. Janning, W., and Knust, E. (2008). Genetik: Allgemeine Genetik-Molekulare Genetik-Entwicklungsgenetik, Thieme. [2nd ed.].10.1055/b-002-7264 ↗
17. An Overview of Evolutionary Algorithms for Parameter Optimization10.1162/evco.1993.1.1.1 ↗
18. Multi-Objective Optimization of Vehicle Passive Suspension System Using NSGA-II, SPEA2 and PESA-II10.1016/j.protcy.2016.03.038 ↗
19. Koziolek, A., Koziolek, H., Becker, S., and Reussner, R.H. (2010, January 28–30). Automatically improve software architecture models for performance, reliability, and cost using evolutionary algorithms. Proceedings of the First Joint WOSP/SIPEW International Conference on Performance Engineering, New York, NY, USA.
20. Kahlbau, S. (2021, February 01). Mehrkriterielle Optimierung des Schaltablaufs von Automatikgetrieben. Available online: https://opus4.kobv.de/opus4-btu/frontdoor/index/index/year/2013/docId/2751.
21. Optimal Shift Control for Automatic Transmission#10.1080/15397734.2012.756719 ↗
22. Desai, C. (2021, December 07). Design and Optimization of Hybrid Electric Vehicle Drivetrain and Control Strategy Parameters Using Evolutionary Algorithms. Available online: https://spectrum.library.concordia.ca/id/eprint/7496/.
23. Bachinger, M., Knauder, B.J., and Stolz, M. (2012, January 1–5). Automotive vehicle launch optimization based on differential evolution (DE) approach for increased driveability. Proceedings of the International Conference on Engineering Optimization, Rio de Janeiro, Brazil.
24. Zaglauer, S. (2021, February 01). Methode zur Multikriteriellen Optimierung des Motorverhaltens Anhand Physikalisch Motivierter Modelle. Available online: https://opus4.kobv.de/opus4-fau/frontdoor/index/index/docId/5248.
25. Huang, H. (2021, February 01). Model-Based Calibration of Automated Transmissions. Available online: https://pdfs.semanticscholar.org/7b9f/7ca311a304de065e05121958e3ade249c1a0.pdf.
26. Zhong, Y., Wyns, B., De Keyser, R., Pinte, G., and Stoev, J. (2011, January 7–10). An implementation of genetic-based learning classifier system on a wet clutch system. Proceedings of the Applied Stochastic Models and Data Analysis Conference, 14th, Rome, Italy.
27. A hybrid real-parameter genetic algorithm for function optimization10.1016/j.aei.2005.09.001 ↗
28. A review on genetic algorithm: Past, present, and future10.1007/s11042-020-10139-6 ↗
29. Piszcz, A., and Soule, T. (2006, January 8–12). Genetic programming: Optimal population sizes for varying complexity problems. Proceedings of the 8th Annual Conference on Genetic and Evolutionary Computation, New York, NY, USA.10.1145/1143997.1144166 ↗
30. Hassanat, A., Almohammadi, K., Alkafaween, E., Abunawas, E., Hammouri, A., and Prasath, V.B.S. (2019). Choosing Mutation and Crossover Ratios for Genetic Algorithms—A Review with a New Dynamic Approach. Information, 10.10.3390/info10120390 ↗
31. Deep learning10.1038/nature14539 ↗
32. Sutton, R.S., and Barto, A.G. (2018). Reinforcement Learning: An Introduction, A Bradford Book. [2nd ed.].
33. Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., and Riedmiller, M. (2013). Playing Atari with Deep Reinforcement Learning. arXiv.
34. Bello, I., Pham, H., Le, Q.V., Norouzi, M., and Bengio, S. (2017). Neural Combinatorial Optimization with Reinforcement Learning. arXiv.
35. Prieditis, A., and Russell, S. (1995, January 9–12). Ant-Q: A Reinforcement Learning approach to the traveling salesman problem. Proceedings of the Machine Learning, Tahoe City, CA, USA.
36. Xiaohui, L., Bingzhao, G., and Hong, C. (2012, January 25–27). Q-learning based adaptive PID controller design for AMT clutch engagement during start-up process. Proceedings of the 31st Chinese Control Conference, Hefei, China.
37. Gagliolo, M., Van Vaerenbergh, K., Rodríguez, A., Nowé, A., Goossens, S., Pinte, G., and Symens, W. (2011, January 14–16). Policy search reinforcement learning for automatic wet clutch engagement. Proceedings of the 15th International Conference on System Theory, Control and Computing, Sinaia, Romania.
38. Van Vaerenbergh, K., Rodríguez, A., Gagliolo, M., Vrancx, P., Nowé, A., Stoev, J., Goossens, S., Pinte, G., and Symens, W. (2012, January 10–15). Improving wet clutch engagement with reinforcement learning. Proceedings of the 2012 International Joint Conference on Neural Networks (IJCNN), Brisbane, Australia.10.1109/IJCNN.2012.6252825 ↗
39. Brys, T., Moffaert, K.V., Vaerenbergh, K.V., and Nowé, A. (2013, January 4–7). On the Behaviour of Scalarization Methods for the Engagement of a Wet Clutch. Proceedings of the 2013 12th International Conference on Machine Learning and Applications, Miami, FL, USA.10.1109/ICMLA.2013.52 ↗
40. Artificial Intelligence in Transmission Control Clutch Engagement with Reinforcement Learning
41. Genders, W., and Razavi, S. (2016). Using a Deep Reinforcement Learning Agent for Traffic Signal Control. arXiv.
42. Virtuelle Fahrerprobungen von Antriebssystemen im Fahrsimulator10.1007/s35148-020-0652-4 ↗
43. Erler, P. (2020). Untersuchung von Vorausschauenden Motion-Cueing-Algorithmen in Einem Neuartigen Längsdynamischen Fahrsimulator, Shaker.
44. Backhaus, K., Erichson, B., Plinke, W., and Weiber, R. (2016). Multivariate Analysemethoden: Eine anwendungsorientierte Einführung, Springer. [14th ed.].
45. Objective metrics of comfort: Developing a driving style for highly automated vehicles10.1016/j.trf.2016.05.005 ↗
46. In the passenger seat: Investigating ride comfort measures in autonomous cars10.1109/MITS.2015.2405571 ↗
47. Multitronic—Das neue Automatikgetriebe von Audi10.1007/BF03224308 ↗
48. Hirzel, C. (2021, March 02). Ein Beitrag zur Synthese und Analyse Elektrifizierter Fahrzeuggetriebestrukturen aus Einer Kombination von Stirnrad-Und Planetengetrieben Mit Fokus auf die Systematische Realisierung Einer Hinreichenden Gangverteilung. Available online: https://opendata.uni-halle.de/bitstream/1981185920/13503/1/Hirzel_Cathleen_Dissertation_2018.pdf.
49. Hoberock, L.L. (1976). A Survey of Longitudinal Acceleration Comfort Studies in Ground Transportation Vehicles, Council for Advanced Transportation Studied; University of Texas at Austin.
50. Can you feel the difference? The just noticeable difference of longitudinal acceleration10.1177/1541931213571271 ↗
51. Deng, G., and Cahill, L.W. (1993, January 31). An adaptive Gaussian filter for noise reduction and edge detection. Proceedings of the 1993 IEEE Conference Record Nuclear Science Symposium and Medical Imaging Conference, San Francisco, CA, USA.
52. Junghanns, A., Mauss, J., and Seibt, M. (2014). Faster Development of AUTOSAR Compliant ECUs through Simulation, Embedded Real Time Software and Systems (ERTS2014).
53. Fast and smooth clutch engagement control for dual-clutch transmissions10.1016/j.conengprac.2013.09.010 ↗
54. Lillicrap, T.P., Hunt, J.J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., and Wierstra, D. (2015). Continuous control with deep reinforcement learning. arXiv.
55. Schulman, J., Wolski, F., Dhariwal, P., Radford, A., and Klimov, O. (2017). Proximal Policy Optimization Algorithms. arXiv.
56. Mnih, V., Badia, A.P., Mirza, M., Graves, A., Lillicrap, T.P., Harley, T., Silver, D., and Kavukcuoglu, K. (2016). Asynchronous Methods for Deep Reinforcement Learning. arXiv.
57. Haarnoja, T., Zhou, A., Abbeel, P., and Levine, S. (2018). Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor. arXiv.
58. Genetic Algorithms10.1038/scientificamerican0792-66 ↗
59. Control of exploitation–exploration meta-parameter in reinforcement learning10.1016/S0893-6080(02)00056-4 ↗
60. Human-level control through deep reinforcement learning10.1038/nature14236 ↗
61. On hyperparameter optimization of machine learning algorithms: Theory and practice10.1016/j.neucom.2020.07.061 ↗
62. Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT press.
63. Pedregosa, F. (2016, January 20–22). Hyperparameter optimization with approximate gradient. Proceedings of the 33rd International Conference on Machine Learning PMLR, New York, NY, USA.
64. Koutsoukas, A., Monaghan, K.J., Li, X., and Huan, J. (2017). Deep-learning: Investigating deep neural networks hyper-parameters and comparison of performance to shallow methods for modeling bioactivity data. J. Cheminformatics, 9.10.1186/s13321-017-0226-y ↗
65. Effective hyperparameter optimization using Nelder-Mead method in deep learning10.1186/s41074-017-0030-7 ↗
66. Bousquet, O., von Luxburg, U., and Rätsch, G. (2004). Gaussian Processes in Machine Learning. Advanced Lectures on Machine Learning: ML Summer Schools 2003, Canberra, Australia, February 2–14, 2003, Tübingen, Germany, August 4–16, 2003, Revised Lectures, Springer. Lecture Notes in Computer Science.
67. Analysis of different activation functions using back propagation neural networks
68. Neural networks and their applications10.1063/1.1144830 ↗
69. Wang, Y., Li, Y., Song, Y., and Rong, X. (2020). The Influence of the Activation Function in a Convolution Neural Network Model of Facial Expression Recognition. Appl. Sci., 10.10.3390/app10051897 ↗
70. Nonparametric regression using deep neural networks with ReLU activation function
71. Radiuk, P.M. (2017). Impact of Training Set Batch Size on the Performance of Convolutional Neural Networks for Diverse Datasets. Inf. Technol. Manag. Sci., 20.10.1515/itms-2017-0003 ↗
72. Keskar, N.S., Mudigere, D., Nocedal, J., Smelyanskiy, M., and Tang, P.T.P. (2017). On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima. arXiv.
73. Biological robustness10.1038/nrg1471 ↗
74. Research on drivability control in P2.5 hybrid system10.1016/j.egyr.2021.09.065 ↗
75. Systemansatz für einen dedizierten Hybridantrieb10.1007/s35148-019-0038-7 ↗