nach oben

Erschienen in:

2023 | OriginalPaper | Buchkapitel

The Establishment of a Vehicle Climate System Model Based on a Data-Driven Method

verfasst von : Xiangxian Zhu, Yilun Lou, Zhao Jiang, Xin Lin, Hong Zhou

Erschienen in: Proceedings of China SAE Congress 2022: Selected Papers

Verlag: Springer Nature Singapore

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

A mathematical model of a vehicle climate system can facilitate the development of a vehicle climate control module and reduce costs. In this paper, we present a data-driven method to model the vehicle climate dynamics. The data used for model identification is collected from actual road tests, and a long-short term memory (LSTM) network is applied to sequence modeling. An output projector is added to the LSTM model to isolate the LSTM state and system output. Since the data collected has inconsistent initial working conditions, we design an initial value mapping method to endow the LSTM model with different initial states for different data sequences. Training sequence segmentation and loss weight assignment are introduced to further enhance the training process and improve performance. On the validation set, the mean absolute error (MAE) of predicted temperature from the proposed LSTM model is only 0.4 ℃, while the fit value reaches 97%. Extreme values at the beginning of sequences are suppressed. When the initial value mapping and weight assignment are used, the maximum temperature error is only 3.0 ℃, which is substantially smaller than the errors in other methods. The results indicate the feasibility of using this model to develop and calibrate the vehicle climate control model at low costs.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Vorheriges Kapitel Simulation Analysis of Impact Damage of Automotive Coatings

Nächstes Kapitel Simulation and Optimization of Membrane Air Suspension Failure

Wu, J., Chen, J.: Numerical simulation of HVAC & vent in vehicle air conditioning system. FLUID Mach. 433(07), 59–62+54 (2008)

Guan, J., Zhao, Y., Zhan, Y., et al.: A Stochastic model predictive control algorithm for electric vehicle air-conditioning system. Trans. Beijing Inst. Technol. 41(05), 480–486 (2021). https://doi.org/10.15918/j.tbit1001-0645.2020.091CrossRef

Afram, A., Janabi-Sharifi, F.: Black-box modeling of residential HVAC system and comparison of gray-box and black-box modeling methods. Energy Build. 94, 121–149 (2015). https://doi.org/10.1016/j.enbuild.2015.02.045CrossRef

Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016)

Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015). https://doi.org/10.1016/j.neunet.2014.09.003CrossRef

Nelles, O.: Neural Networks. Nonlinear System Identification: From Classical Approaches to Neural Networks, Fuzzy Models, and Gaussian Processes, pp. 279–344. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-47439-3

Hewamalage, H., Bergmeir, C., Bandara, K.: Recurrent neural networks for time series forecasting: current status and future directions. Int. J. Forecast. 37(1), 388–427 (2021). https://doi.org/10.1016/j.ijforecast.2020.06.008CrossRef

Weerakody, P.B., Wong, K.W., Wang, G., et al.: A review of irregular time series data handling with gated recurrent neural networks. Neurocomputing 441, 161–178 (2021). https://doi.org/10.1016/j.neucom.2021.02.046CrossRef

Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997). https://doi.org/10.1162/neco.1997.9.8.1735CrossRef

10.

Greff, K., Srivastava, R.K., Koutník, J., et al.: LSTM: a search space Odyssey. IEEE Trans. Neural Netw. Learn. Syst. 28(10), 2222–2232 (2017). https://doi.org/10.1109/TNNLS.2016.2582924MathSciNetCrossRef

11.

Sherstinsky, A.: Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network. Phys. D 404, 132306 (2020). https://doi.org/10.1016/j.physd.2019.132306MathSciNetCrossRefMATH

12.

Narayanan, A., Prabhavalkar, R., Chiu, C.-C., et al.: Recognizing long-form speech using streaming end-to-end models. In: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) (2019). https://doi.org/10.1109/ASRU46091.2019.9003913

13.

Zhao, J., Mao, X., Chen, L.: Speech emotion recognition using deep 1D & 2D CNN LSTM networks. Biomed. Signal Process. Control 47, 312–323 (2019). https://doi.org/10.1016/j.bspc.2018.08.035CrossRef

14.

Xu, J., Yao, T., Zhang, Y., et al.: Learning multimodal attention LSTM networks for video captioning. In: Proceedings of the 25th ACM International Conference on Multimedia. New York, NY, USA: Association for Computing Machinery, 2017, pp. 537–545 8 Aug 2022. https://doi.org/10.1145/3123266.3123448

15.

Ge, H., Yan, Z., Yu, W., Sun, L.: An attention mechanism based convolutional LSTM network for video action recognition. Multim. Tools Appl. 78(14), 20533–20556 (2019). https://doi.org/10.1007/s11042-019-7404-zCrossRef

16.

Livieris, I.E., Pintelas, E., Pintelas, P.: A CNN–LSTM model for gold price time-series forecasting. Neural Comput. Appl. 32(23), 17351–17360 (2020). https://doi.org/10.1007/s00521-020-04867-xCrossRef

17.

Liu, Y., Yang, C., Huang, K., et al.: Non-ferrous metals price forecasting based on variational mode decomposition and LSTM network. Knowl.-Based Syst. 188, 105006 (2020). https://doi.org/10.1016/j.knosys.2019.105006CrossRef

18.

Ljung, L., Andersson, C., Tiels, K., et al.: Deep learning and system identification. IFAC-PapersOnLine 53(2), 1175–1181 (2020). https://doi.org/10.1016/j.ifacol.2020.12.1329CrossRef

19.

Yuan, X., Li, L., Wang, Y.: Nonlinear dynamic soft sensor modeling with supervised long short-term memory network. IEEE Trans. Industr. Inf. 16(5), 3168–3176 (2020). https://doi.org/10.1109/TII.2019.2902129CrossRef

20.

Song, X., Yang, F., Wang, D., et al.: Combined CNN-LSTM network for state-of-charge estimation of lithium-ion batteries. IEEE Access 7, 88894–88902 (2019). https://doi.org/10.1109/ACCESS.2019.2926517CrossRef

21.

Yang, Z.: Dynamic modelling of automotive air-conditioning systems with a data-driven method. Shanghai Jiao Tong University, 2017 (27 July 2022)

22.

Ribeiro, A.H., Tiels, K., Umenberger, J., et al.: On the smoothness of nonlinear system identification. Automatica 121, 109158 (2020). https://doi.org/10.1016/j.automatica.2020.109158MathSciNetCrossRefMATH

23.

Tanaka, H., Ikeda, K.: Closed-loop subspace identification taking initial state into account. IFAC-PapersOnLine 51(15), 604–609 (2018). https://doi.org/10.1016/j.ifacol.2018.09.229CrossRef

24.

Hu, X.-L., Welsh, J.S.: Continuous-time model identification from filtered sampled data: error analysis. IEEE Trans. Autom. Control 65(10), 4005–4015 (2020). https://doi.org/10.1109/TAC.2020.3006354MathSciNetCrossRefMATH

25.

Elsworth, S., Güttel, S.: Time series forecasting using LSTM networks: a symbolic approach. arXiv, 2020(2020–03–12)[2022–08–09]. https://doi.org/10.48550/arXiv.2003.05672

26.

Ellis, M.J., Chinde, V.: An encoder–decoder LSTM-based EMPC framework applied to a building HVAC system. Chem. Eng. Res. Des. 160, 508–520 (2020). https://doi.org/10.1016/j.cherd.2020.06.008CrossRef

Titel: The Establishment of a Vehicle Climate System Model Based on a Data-Driven Method
verfasst von: Xiangxian Zhu
Yilun Lou
Zhao Jiang
Xin Lin
Hong Zhou
Verlag: Springer Nature Singapore
Buch: Proceedings of China SAE Congress 2022: Selected Papers
Print ISBN: 978-981-9913-64-0

Electronic ISBN: 978-981-9913-65-7

Copyright-Jahr: 2023
DOI: https://doi.org/10.1007/978-981-99-1365-7_71

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Premium Partner