In this paper, a feed-forward deep neural network (DNN) and automated search method for optimum network structure are developed to control an active suspension system (ASS). The network was trained through supervised learning using the backpropagation algorithm. The training data were generated from an optimal proportional–integral–derivative controller tuned based on a full state feedback optimal controller. The trained network was implemented in an ASS test rig for a quarter-car model and was initially tested in simulation under parameter uncertainties. Experimental results showed that the developed DNN controller outperforms the optimal controller under uncertainties in terms of reducing the sprung mass acceleration and actuator energy consumption, with a 4% and 14% reduction, respectively.
AlexandruCAlexandruP (2011) A comparative analysis between the vehicles’ passive and active suspensions. International Journal of Control, Automation and Systems5(4): 371–378.
2.
Alkhoori F, Bin Safwan S, Zweiri Y, et al. (2017) PID–LQR controllers for quad-rotor hovering mode. In: 2017 4rd International Conference on Systems and Informatics (ICSAI), Hangzhou, China, 11–13 November 2017. Piscataway, NJ: Institute of Electrical and Electronics Engineers, pp.51–55.
3.
AlyAASalemFA (2013) Vehicle suspension systems control: A review. International Journal of Control, Automation and Systems2(2): 46–54.
4.
Bin Safwan S, Alkhoori F, Zweiri Y, et al. (2018) Implementation of a novel optimal PID methods in UAV applications. In: ICARM 2018–IEEE International Conference on Advanced Robotics and Mechatronics, National University of Singapore, Singapore, 18–20 July 2018. USA: IEEE, pp.256–261.
5.
Chen HY and Huang SJ (2005) Functional approximation-based adaptive sliding control with fuzzy compensation for an active suspension system. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering 219(11): 1271–1280.
6.
Dessort R and Chucholowski C (2017) Explicit model predictive control of semi-active suspension systems using artificial neural networks (ANN). In: Pfeffer P (ed.) Proceedings of the 8th International Munich Chassis Symposium. Wiesbaden, Springer: pp.207–228.
7.
FischerDIsermannR (2004) Mechatronic semi-active and active vehicle suspensions. Control Engineering Practice12(11): 1353–1367.
8.
Gupta S, Ginoya D, Shendge PD, et al. (2016) An inertial delay observer-based sliding mode control for active suspension systems. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering 230(3): 352–370.
9.
Heidari M and Homaei H (2013) Design a PID controller for suspension system by back propagation neural network. Journal of Engineering 2013: 1–9. Article ID 421543. Available at: https://www.hindawi.com/journals/je/2013/421543/ (accessed 1 March 2018).
10.
Huang SJ and Lin WC (2007) A neural network based sliding mode controller for active vehicle suspension. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering 221(11): 1381–1397.
11.
Kim C and Ro PI (1998) A sliding mode controller for vehicle active suspension systems with nonlinearities. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering 212(2): 79–92.
12.
Metered H, Bonello P and Oyadiji SO (2010) An investigation into the use of neural networks for the semi-active control of a magnetorheologically damped vehicle suspension. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering 224(7): 829–848.
13.
QinYXiangCWangZ, et al.(2018) Road excitation classification for semi-active suspension system based on system response. Journal of Vibration and Control24(13): 2732–2748.
14.
Ramsbottom M, Crolla DA and Plummer AR (1999) Robust adaptive control of an active vehicle suspension system. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering 1999 213(1): 1–17.
15.
RashidUJamilMGilaniS, et al.(2016) LQR based training of adaptive neuro-fuzzy controller. Journal of Intelligent & Fuzzy Systems54: 311–322.
16.
Shin D, Lee G, Yi K, et al. (2016) Motorized vehicle active suspension damper control with dynamic friction and actuator delay compensation for a better ride quality. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering 230(8): 1074–1089.
17.
Tsao YJ and Chen R (2001) The design of an active suspension force controller using genetic algorithms with maximum stroke constraints. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering 215(3): 317–327.
18.
Watton J, Holford KM and Surawattanawan P (2004) The application of a programmable servo controller to state control of an electrohydraulic active suspension. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering 218(12): 1367–1377.
19.
ZhaoFDongMQinY, et al.(2015) Adaptive neural networks control for camera stabilization with active suspension system. Advances in Mechanical Engineering7(8): 1–11.
20.
ZhaoFGeSSTuF, et al.(2016) Adaptive neural network control for active suspension system with actuator saturation. IET Control Theory Applications10(14): 1696–1705.
