Data-driven virtual sensor for powertrains based on transfer learning

• Autorzy: Karhinen Aku , Hämäläinen Aleksanteri , Manngård Mikael , Miettinen Jesse , Viitala Raine

Identyfikatory

DOI

10.24425/bpasts.2023.147061

• Języki publikacji: EN

Abstrakty

EN

Variation in powertrain parameters caused by dimensioning, manufacturing and assembly inaccuracies may prevent model-based virtual sensors from representing physical powertrains accurately. Data-driven virtual sensors employing machine learning models offer a solution for including variations in the powertrain parameters. These variations can be efficiently included in the training of the virtual sensor through simulation. The trained model can then be theoretically applied to real systems via transfer learning, allowing a data-driven virtual sensor to be trained without the notoriously labour-intensive step of gathering data from a real powertrain. This research presents a training procedure for a data-driven virtual sensor. The virtual sensor was made for a powertrain consisting of multiple shafts, couplings and gears. The training procedure generalizes the virtual sensor for a single powertrain with variations corresponding to the aforementioned inaccuracies. The training procedure includes parameter randomization and random excitation. That is, the data-driven virtual sensor was trained using data from multiple different powertrain instances, representing roughly the same powertrain. The virtual sensor trained using multiple instances of a simulated powertrain was accurate at estimating rotating speeds and torque of the loaded shaft of multiple simulated test powertrains. The estimates were computed from the rotating speeds and torque at the motor shaft of the powertrain. This research gives excellent grounds for further studies towards simulation-to-reality transfer learning, in which a virtual sensor is trained with simulated data and then applied to a real system.

Słowa kluczowe

EN

powertrain; torsional vibration; long short-term memory; virtual sensor; transfer learning

PL

układ napędowy; drgania skrętne; pamięć krótkotrwała; czujnik wirtualny; transfer nauki

• Wydawca: Polska Akademia Nauk, Wydział IV Nauk Technicznych
• Czasopismo: Bulletin of the Polish Academy of Sciences. Technical Sciences
• Rocznik: 2023
• Tom: Vol. 71, nr 6
• Strony: art. no. e147061
• Opis fizyczny: Bibliogr. 35 poz., rys., tab.

Twórcy

autor

Karhinen Aku

• Department of Mechanical Engineering, Aalto University, 02150, Espoo, Finland

• https://orcid.org/0009-0002-3936-4357

autor

Hämäläinen Aleksanteri

• Department of Mechanical Engineering, Aalto University, 02150, Espoo, Finland

autor

Manngård Mikael

• Novia University of Applied Sciences, Juhana Herttuan puistokatu 21, 20100 Turku, Finland

autor

Miettinen Jesse

• Department of Mechanical Engineering, Aalto University, 02150, Espoo, Finland

autor

Viitala Raine

• Department of Mechanical Engineering, Aalto University, 02150, Espoo, Finland

Bibliografia

• [1] J. Bai, X. Wu, F. Gao, and H. Li, “Analysis of powertrain loading dynamic characteristics and the effects on fatigue damage,” Appl. Sci., vol. 7, no. 10, p. 1027, 2017.
• [2] Q. Sun and Z. Ge, “A survey on deep learning for data-driven soft sensors,” IEEE Trans. Ind. Inform., vol. 17, no. 9, pp. 5853–5866, 2021, doi: 10.1109/TII.2021.3053128.
• [3] P. Kadlec, B. Gabrys, and S. Strandt, “Data-driven soft sensors in the process industry,” Comput. Chem. Eng., vol. 33, no. 4, pp. 795–814, 2009, doi: 10.1016/j.compchemeng.2008.12.012.
• [4] S. Gillijns and B. De Moor, “Unbiased minimum-variance input and state estimation for linear discrete-time systems,” Automatica, vol. 43, no. 1, pp. 111–116, 2007.
• [5] K. Tiwari, A. Shaik, and A. N, “Tool wear prediction in end milling of ti-6al-4v through kalman filter based fusion of texture features and cutting forces,” Procedia Manuf., vol. 26, pp. 1459–1470, 2018, 46th SME North American Manufacturing Research Conference, NAMRC 46, Texas, USA.
• [6] J. Škach and I. Punˇcocháˇr, “Input design for fault detection using extended kalman filter and reinforcement learning,” IFAC-PapersOnLine, vol. 50, no. 1, pp. 7302–7307, 2017, 20th IFAC World Congress.
• [7] M. Manngård et al., “Torque estimation in marine propulsion systems,” Jun. 2022.
• [8] U. Lagerblad, H. Wentzel, and A. Kulachenko, “Study of a fixed-lag kalman smoother for input and state estimation in vibrating structures,” Inverse Probl. Sci. Eng., vol. 29, no. 9, pp. 1260–1281, 2021.
• [9] R. De Waal, A. Bekker, and P.S. Heyns, “Indirect load case estimation for propeller-ice moments from shaft line torque measurements,” Cold Reg. Sci. Tech., vol. 151, pp. 237–248, 2018.
• [10] T. Ikonen, O. Peltokorpi, and J. Karhunen, “Inverse ice-induced moment determination on the propeller of an ice-going vessel,” Cold Reg. Sci. Tech., vol. 112, pp. 1–13, 2015.
• [11] J.C.B. Gonzaga, L.A.C. Meleiro, C. Kiang, and R. Maciel Filho, “Ann-based soft-sensor for real-time process monitoring and control of an industrial polymerization process,” Comput. Chem. Eng., vol. 33, no. 1, pp. 43–49, 2009, doi: 10.1016/j.compchemeng.2008.05.019.
• [12] W. Yan, H. Shao, and X. Wang, “Soft sensing modeling based on support vector machine and bayesian model selection,” Comput. Chem. Eng., vol. 28, no. 8, pp. 1489–1498, 2004, doi: 10.1016/j.compchemeng.2003.11.004.
• [13] S. Sharma, M. Diwakar, P. Singh, A. Tripathi, C. Arya, and S. Singh, “A review of neural machine translation based on deep learning techniques,” in 2021 IEEE 8th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON), 2021, pp. 1–5, doi: 10.1109/UP-CON52273.2021.9667560.
• [14] J. Su, B. Xu, and H. Yin, “A survey of deep learning approaches to image restoration,” Neurocomputing, vol. 487, pp. 46–65, 2022, doi: 10.1016/j.neucom.2022.02.046.
• [15] S. Tang, S. Yuan, and Y. Zhu, “Deep learning-based intelligent fault diagnosis methods toward rotating machinery,” IEEE Access, vol. 8, pp. 9335–9346, 2020, doi: 10.1109/ACCESS.2019.2963092.
• [16] C. Shang, F. Yang, D. Huang, and W. Lyu, “Data-driven soft sensor development based on deep learning technique,” J. Process Control, vol. 24, no. 3, pp. 223–233, 2014, doi: 10.1016/j.jprocont.2014.01.012.
• [17] R. Zhao, R. Yan, Z. Chen, K. Mao, P. Wang, and R. X. Gao, “Deep learning and its applications to machine health monitoring,” Mech. Syst. Signal Proc., vol. 115, pp. 213–237, 2019, doi: 10.1016/j.ymssp.2018.05.050.
• [18] J. Miettinen, T. Tiainen, R. Viitala, K. Hiekkanen, and R. Viitala, “Bidirectional lstm-based soft sensor for rotor displacement trajectory estimation,” IEEE Access, vol. 9, pp. 167 556–167 569, 2021, doi: 10.1109/ACCESS.2021.3136155.
• [19] S. Vijaya Raghavan, T. Radhakrishnan, and K. Srinivasan, “Soft sensor based composition estimation and controller design for an ideal reactive distillation column,” ISA Trans., vol. 50, no. 1, pp. 61–70, 2011, doi: 10.1016/j.isatra.2010.09.001.
• [20] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Comput., vol. 9, pp. 1735–1780, 12 1997, doi: 10.1162/neco.1997.9.8.1735.
• [21] Q. Sun and Z. Ge, “Probabilistic sequential network for deep learning of complex process data and soft sensor application,” IEEE Trans. Ind. Inform., vol. 15, no. 5, pp. 2700–2709, 2019, doi: 10.1109/TII.2018.2869899.
• [22] F. Galati, W. Wang, B. Bielenberg et al., “Gear-bearing fault detection based on deep learning,” in AIAC18: 18th Australian International Aerospace Congress (2019): HUMS-11th Defence Science and Technology (DST) International Conference on Health and Usage Monitoring (HUMS 2019): ISSFD-27th International Symposium on Space Flight Dynamics (ISSFD). Engineers Australia, Royal Aeronautical Society., 2019, p. 916.
• [23] C.A. Duchanoy, M.A. Moreno-Armendáriz, L. Urbina, C.A. Cruz-Villar, H. Calvo, and J. de J.Rubio, “A novel recurrent neural network soft sensor via a differential evolution training algorithm for the tire contact patch,” Neurocomputing, vol. 235, pp. 71–82, 2017, doi: 10.1016/j.neucom.2016.12.060.
• [24] X. Chen, F. Gao, and G. Chen, “A soft-sensor development for melt-flow-length measurement during injection mold filling,” Mater. Sci. Eng. A, vol. 384, no. 1, pp. 245–254, 2004, doi: 10.1016/j.msea.2004.06.039.
• [25] T.T. Nguyen, N. D. Nguyen, and S. Nahavandi, “Deep reinforcement learning for multiagent systems: A review of challenges, solutions, and applications,” IEEE Trans. Cybern., vol. 50, no. 9, pp. 3826–3839, 2020, doi: 10.1109/TCYB.2020.2977374.
• [26] W. Zhao, J.P. Queralta, and T. Westerlund, “Sim-to-real transfer in deep reinforcement learning for robotics: a survey,” in 2020 IEEE Symposium Series on Computational Intelligence (SSCI), 2020, pp. 737–744, doi: 10.1109/SSCI47803.2020.9308468.
• [27] F. Muratore, C. Eilers, M. Gienger, and J. Peters, “Data-efficient domain randomization with bayesian optimization,” IEEE Robot. Autom. Lett., vol. 6, no. 2, pp. 911–918, 2021.
• [28] F. Muratore, F. Ramos, G. Turk, W. Yu, M. Gienger, and J. Peters, “Robot learning from randomized simulations: A review,” Front. Robot. AI, p. 31, 2022.
• [29] O.M. Andrychowicz et al., “Learning dexterous in-hand manipulation,” Int. J. Robot. Res., vol. 39, no. 1, pp. 3–20, 2020, doi: 10.1177/0278364919887447.
• [30] J. Tobin, R. Fong, A. Ray, J. Schneider, W. Zaremba, and P. Abbeel, “Domain randomization for transferring deep neural networks from simulation to the real world,” in 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2017, pp. 23–30, doi: 10.1109/IROS.2017.8202133.
• [31] M. Manngård et al., “Torque estimation in marine propulsion systems,” Mech. Syst. Signal Proc., vol. 172, p. 108969, 2022.
• [32] S. Haikonen, I. Koene, J. Keski-Rahkonen, and R. Viitala, “Small-scale test bench of maritime thruster for digital twin research,” in 2022 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), 2022, pp. 1–6, doi: 10.1109/I2MTC48687.2022.9806563.
• [33] T. TSA, “Maritime safety regulation. ice class regulations and the application thereof,” 2010.
• [34] S. Ruder, “An overview of gradient descent optimization algorithms,” CoRR, vol. abs/1609.04747, 2016. [Online]. Available: http://arxiv.org/abs/1609.04747
• [35] D.P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2014

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).