Journal of the Korea Society of Computer and Information (한국컴퓨터정보학회논문지)

Korean Society of Computer Information (한국컴퓨터정보학회)
권호 표지
DOI QR코드

DOI QR Code

Deep Learning-based PID Control for ETB with Parameter Variation and Nonlinear Torque

  • Kap Rai Lee (Dept. of Smart Mobility, Pyeongtaek University)
  • Received : 2024.10.07
  • Accepted : 2024.11.01
  • Published : 2024.11.29
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, an approach based on deep learning and parameter dependent control is proposed for electronic throttle body(ETB) control which has variable parameters and nonlinear torques. Firstly we present parameter estimation method for ETB system using deep neural network. To estimate parameters of ETB, we design deep neural networks and train by use time response characteristic such as rise time, overshoot and settling time. Parameters of ETB are estimated through trained neural networks by using time response data. Secondly we design parameter dependent PID controller which is adjusted automatically with the estimated system parameter of ETB. To design optimal parameter dependent gain of PID controller, we use ITAE(Integral of time multiplied by absolute error) criteria. In addition, we design feed-forward controller to reject nonlinear torque. Finally we present simulation results of ETB syatem with parameter variation and nonlinear torque to verify controller design method.

본 연구에서는 파라미터 변이 및 비선형 토크를 갖는 차량 전자식 스로틀 바디 시스템(ETB)의 딥러닝 기반의 파라미터 종속적인 PID 제어기 설계 방법을 나타낸다. 시스템 변화 및 부하용량 변화로 인하여 변이된 시스템의 주요 파라미터 값을 딥러닝을 이용하여 추정한다. 파라미터를 추정하기 위하여 심층 신경망을 설계하고, 시스템의 시간응답 특성(상승시간, 오버슈트, 정착시간)을 특성값으로 하여 신경망을 훈련한다. 훈련된 신경망으로부터 시간응답 특성값 이용하여 파라미터는 추정된다. 또한 추정된 파라미터에 동조되어 자동 조정되는 파라미터 종속 PID 제어기를 설계한다. PID 제어기의 최적 이득값은 ITAE 판별법에 의하여 찾아지며, 추정된 파라미터의 함수로 나타내어진다. 또한 비선형 토크의 영향을 감쇄하기 위하여 추정된 비선형 토크값을 상쇄시켜 줄 피드 포워드 제어기를 추가적으로 설계한다. 설계된 제어기의 제어 성능을 나타내기 위하여, 시뮬레이션을 통한 파라미터 변화 및 비선형 토크를 갖는 ETB 시스템의 제어 성능 결과를 나타낸다.

Keywords

References

  1. H. T. Dorissen and K. Durkopp, "Mechatronics and Drive-by-Wire Systems Advanced Non-contacting Position Sensors," Control Engineering Practice, Vol. 11, No. 2, pp. 191-197, Feb. 2003. DOI: 10.1016/S0967-0661(02)00146-6
  2. C. Rossi, A. Tilli and A. Tonielli "Robust Control of a Throttle Body for Drive by Wire Operation of Automotive Engines," IEEE Trans. on Control Systems Technology, Vol. 8, No. 6, pp. 993-1002 Nov. 2000. DOI: 10.1109/87.880604.
  3. Y. J. Kim, A Fault-tolerant Throttle Valve Using Sliding Mode Control, M. S. Thesis, Kyungpook National University, 2009.
  4. S. T. Jin, J. J. Kang and W. T. Lee, "Electronic Throttle Body Model Allowing for Non-linearity of DC Motor Driver," Trans. of KSAE, Vol. 16, No. 1, pp. 71-77, Feb. 2008.
  5. U. Ozguner, S. Hong and Y. Pan, "Discrete-time Sliding Mode Control of Electronic Throttle Valve," Proc. of the 40th IEEE Conf. Decision and Control, pp. 1819-1824, 2001. DOI: 10.1109/CDC.2001.981169.
  6. I. S. Yangg, M.G. Song and D. I. Lee, "Nonlinear Dynamic Inversion Based Control for Electronic Throttle" Transaction of KSAE. vol 20. No. 2, pp. 8-14, March 2012. DOI: 10.7467/KSAE.2012.20.2.008.
  7. J. Georgie and J. Valasek, "Evaluation of Longitudinal Desired Dynamics for Dynamic-inversion Controlled Generic Recentry Vehicles," J. Guid. Cont. Dyna. Vol. 26, No. 5, pp. 811-819, Sept. 2003. DOI: 10.2514/2.5116
  8. H. Zhang, L. Xie, Y. C. Soh and W. Wang "Optimal and self-tuning State estimation for singular stochastic systems: a polynomial equation approach" IEEE Trans. on Circuits and Systems, Vol. 51, No. 6, pp. 327-333, June. 2004. DOI: 10.1109/TCSII.2004.829573
  9. C. S. Jeon, D. S. Kim and J. M. Lee "PID Gain Auto Tuning of ETB by using RLS" The Journal of Korea Robotics Society, Vol. 2, No. 1, pp. 1-8, March 2007.
  10. M. Baric, I. Petrovic and N. Peric, "Neural network-based sliding mode control of electronic throttle," Eng. Appl. of Artifi. Intell. Vol. 18, No. 8, pp. 951-961, Dec. 2005. DOI: 10.1016/j.engappai.2005.03.008
  11. D. V. Prokhorov, "Training Recurrent Neurocontrollers for Real-Time Applications," IEEE Trans. on Neural Networks. Vol. 18 No. 4, pp. 1003-1015, July 2007. DOI: 10.1109/TNN.2007.899521
  12. X. Yuan and Y. Wang, "Neural networks based self-learning PID control of electronic throttle," Nonlinear Dynamics, Vol. 55, No. 4, pp 385-393, June 2008.
  13. X. R. Hernandez-Alvarado, L. G. Garcia-Valdovinos, T. Salgado-Jimenez, A.Gomez-Espinosa and F. Fonseca-Navarro ,"Neural Network-Based Self-Tuning PID Control for Underwater Vehicles". Sensors, Vol 16, No. 9, pp. 1429. Sept. 2016. DPI: 10.3390/s16091429
  14. S. Bari, S. S. Z. Hamdani, H. U. Khan, M. ur Rehman and K. Haroon, "Artificial Neural Network Based Self-Tuned PID Controller for Flight Control of Quadcopter," 2019 International Conference on Engineering and Emerging Technologies, pp. 1-5, 2019.
  15. A. Mohammadi and JC. Ryu, "Neural network-based PID compensation for nonlinear systems: ball-on-plate example," Int. J. of Dynamics and Control, Vol. 8, pp. 178-188, Mar. 2020. DOI: 10.1007/s40435-018-0480-5
  16. R. Conatser, J. Wagner, S. Ganta and J. Walker, "Diagnosis of automotive electronic throttle control systems," Control Engineering Practice, Vol. 12, No. 1, pp. 23-30, Jan. 2004. DOI: 10.1016/S0967-0661(02)00281-2
  17. Richard C. Dorf and Robert H. Bishop, "Modern Control Systems" Pearson press, pp. 254-263, 2017.