This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Classification of Time Series Measurement Data for Shift Control of Automatic Transmission of Vehicles Using Machine Learning Techniques
Technical Paper
2020-01-0260
ISSN: 0148-7191, e-ISSN: 2688-3627
This content contains downloadable datasets
Annotation ability available
Sector:
Language:
English
Abstract
An efficient approach to classify time series physical measurement data of shift control of automatic transmission for vehicles is presented. Comfortable acceleration is the essential factor of today’s vehicles. Shift control of automatic transmission of vehicles directly contributes to the comfortable acceleration. Since calibration of automatic transmission of vehicles is time consuming task for expert engineers, the development of autonomous calibration is desired to reduce product development period in today’s competitive automobile market. In the stage of product development, it is difficult to obtain a large amount of physical measurement data. Therefore, we need to develop machine learning method for limited amount of data. For this purpose, we develop the method to classify time series measurement data of shift control of automatic transmission of vehicles. We use support vector machine (SVM) as a machine learning technique. Features, used by SVM, of time series measurement data of shift control of automatic transmission of vehicles is selected by expert engineers. In addition, the computation is too heavy to explore the optimal value of the high dimensional parameter space for our classification problem with grid search. To remedy this problem, we employ Bayesian optimization. Bayesian optimization is known to be much more efficient than brute force grid search, because it is a sequential parameter search strategy for global optimization. Combining SVM and Bayesian optimization, we successfully built a high accuracy classification scheme. As the consequence, our proposed method enables highly efficient calibration of automatic transmission of vehicles in the stage of the product development. We demonstrate the performance of proposed method for classification problem of shift control of AISIN AW’s automatic transmission of vehicles. The results of our experimentation show the expected average accuracy of 0.940 for upshift and 0.939 for downshift, those are promising enough in an actual use.
Recommended Content
Authors
- Yusuke Morikawa - Aisin AW Co., Ltd.
- Yasuhiro Ishihara - Aisin AW Co., Ltd.
- Taku Akita - Aisin AW Co., Ltd.
- Takanori Ide - Aisin AW Co., Ltd.
- Noriyuki Miyake - Aisin AW Co., Ltd.
- Eiji Moriyama - Aisin AW Co., Ltd.
- Hiroshi Nakagawa - RIKEN AIP
- Yasuo Tabei - RIKEN AIP
- Takehito Utsuro - University of Tsukuba
Topic
Citation
Morikawa, Y., Ishihara, Y., Akita, T., Ide, T. et al., "Classification of Time Series Measurement Data for Shift Control of Automatic Transmission of Vehicles Using Machine Learning Techniques," SAE Technical Paper 2020-01-0260, 2020, https://doi.org/10.4271/2020-01-0260.Data Sets - Support Documents
| Title | Description | Download |
|---|---|---|
| Unnamed Dataset 1 | ||
| Unnamed Dataset 2 | ||
| Unnamed Dataset 3 |
Also In
References
- Kampouraki , A. , Manis , G. , and Nikoi , C. Heartbeat Time Series Classification with Support Vector Machines IEEE Trans Inf Tech Biomedicine 2009 13 512 518 2009 10.1109/TITB.2008.2003323
- Tripoliti , E.E. , Fotiadis , D.I. , Argyropoulou , M. , and Manis , G. A Six Stage Approach for the Diagnosis of the Alzheimer’s Disease Based on fMRI Data Journal of Biomedical Informatics 43 2 307 320 2010
- Li Sun , K. , Li , S. , Sun , L. , Lu , Y. , and Yang , K. ECG Analysis Using Multiple Instance Learning for Myocardial Infarction Detection IEEE Transactions on Biomedical Engineering 2012 59 12 2012
- Wang , J. , Liu , P. , She , F.H.M. , Nahavandi , S. et al. Bag-of-Words Representation for Biomedical Time Series Classification Biomedical Signal Processing and Control 8 6 634 644 2013 10.1016/j.bspc.2013.06.004
- Rajkomar , A. , Oren , E. , Chen , K. , Dai , A. et al. Scalable and Accurate Deep Learning with Electronic Health Records NPJ Digital Medicine 1 18 2018 10.1038/s41746-018-0029-1
- Wang , J. , Chen , Y. , Hao , S. , Peng , X. , and Hu , L. Deep Learning for Sensor-Based Activity Recognition: A Survey Pattern Recognition Letters 2017
- Nweke , H.F. , The , Y.W. , Al-garadi , M.A. , and Alo , U.R. Deep Learning Algorithms for Human Activity Recognition Using Mobile and Wearable Sensor Networks: State of the Art and Research Challenges Expert Systems with Applications 105 233 261 2018
- Jian , W. , Konghui , G. , Yulong , L. , and Hua , T. Support Vector Machine Theory Based Shift Control Quality Assessment for Automated Mechanical Transmission (AMT) SAE Technical Paper 2007-01-1588 2007 https://doi.org/10.4271/2007-01-1588
- Kawakami , T. , Ide , T. , Tomita , K. , Moriyama , E. et al. Classification of Time Series Measurement Data for Lock-Up Clutch of Automatic Transmission of Vehicles Using Deep Convolutional Neural Networks SAE Technical Paper 2018-01-0399 2018 https://doi.org/10.4271/2018-01-0399
- Kawakami , T. , Ide , T. , Tomita , K. , Moriyama , H. et al. Recognizing Similarities in Automatic Transmission of Vehicles by Using Time Series Data and Autoencoders SAE Technical Paper 2019-01-0343 2019 https://doi.org/10.4271/2018-01-0343
- Bagheri , M. , Gao , Q. , and Escalera , S. Support Vector Machines with Time Series Distance Kernels for Action Classification Applications of Computer Vision (WACV), 2016 IEEE Winter Conference on 1 7 2016 10.1109/WACV.2016.7477591
- Bergstra , J. , Bardenet , R. , Bengio , Y. , and Kégl , B. Algorithms for Hyper-Parameter Optimization Advances in Neural Information Processing Systems 24 2546 2554 2011
- Snoek , J. , Larochelle , H. , and Adams , R. Practical Bayesian Optimization of Machine Learning Algorithms Advances in Neural Information Processing Systems 25 2951 2959 2012
- Czarnecki , W. , Podlewska , S. , and Bojarski , A. Robust Optimization of SVM Hyperparameters in the Classification of Bioactive Compounds Journal of Cheminformatics 2015 7 1 2015 10.1186/s13321-015-0088-0
- Chang , C. , Lin , C. 2001 http://www.csie.ntu.edu.tw/~cjlin/libsvm
- 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
- Akiba , T. , Sano , S. , Yanase , T. , Ohta , T. , Koyama , M. Optuna: A Next-Generation Hyperparameter Optimization Framework Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD’19 2623 2631 2019