Application Research of Adaptive Control Techniques in the Hydraulic Torque Converter's Buffer Locking Process


Article Preview

When hydraulic torque converter is applied in hydraulic transmission-vehicle, control precision in buffer locking process of hydraulic torque converter was easily disturbed by friction plate's abrasion, changed buffer slope and other factors, which accordingly caused Impact to transmission system of vehicle. In this paper, adaptive control techniques was applied in buffer locking process as a solution to improve control precision, on basis of Back Propagation (BP) Neural Networks and Genetic Algorithm (GA). In the research, the BP Neural Networks and PID control algorithm was designed to control buffer locking process and Genetic Algorithm was applied to optimize the neural network parameters. Based on AMEsim and Matlab/simulink, joint simulation was carried out. The simulation result shows that Adaptive Control Techniques based on GA-BP can control the locking process fast and accurately.



Advanced Materials Research (Volumes 588-589)

Edited by:

Lawrence Lim




Y. Jin et al., "Application Research of Adaptive Control Techniques in the Hydraulic Torque Converter's Buffer Locking Process", Advanced Materials Research, Vols. 588-589, pp. 1495-1498, 2012

Online since:

November 2012




[1] Li Yong-tang: Hydraulic System Model and Simulation (Metallurgical Industry Press, PRC 2003).

[2] Zeng Xiang-rong: Hydraulic Transmission (Defense Publications, PRC 1980).

[3] Ma chao, study on locking type hydraulic converter controller, Beijing: Beijing Institute of Technology, (2004).

[4] Sun Xuguang: On Braking Function and Controlling System of Hydraulic Torque Converter of Traction-and-Brake Type, Beijing: Doctoral Dissertation, Beijing Institute of Technology, (2006).

[5] Takao K and Yamamoto T, A design of model driven cascade PID controllers using a neural network, Conference on neural Networks, 2003, pp.167-169.


[6] SUN Wei-na, Research and application of PID control based on genetic neural network, Journal of Shenyang Aerospace University, vol. 28, no. 3, pp.52-57, June (2011).