The continuous rotating valve plate piston pump (CRVPPP) can efficiently drive actuators such as hydraulic cylinders or hydraulic motors to generate excitation motion. This CRVPPP-driven excitation system can avoid the throttling losses associated with servo-valve-controlled excitation systems. However, this excitation system exhibits an asymmetric excitation phenomenon during actual operation. Through theoretical analysis and experimental research on the mechanical characteristics of the valve plate pair in the CRVPPP, it was found that the asymmetric excitation originates from the annular grooves of the fixed valve plate alternating between oil suction and discharge states. This alternation subjects the rotating valve plate to an overturning moment, which in turn causes a periodic variation in the end-face clearance of the valve plate. Targeting the asymmetric and nonlinear leakage characteristics of the CRVPPP, an adaptive neural network module was established based on the Amesim-Matlab/Simulink co-simulation framework. This module incorporates the mapping from the rotational speeds of the rotating valve plate and cylinder block to the equivalent leakage opening of the distribution grooves. By training with experimental data, the CRVPPP- driven excitation system model was formulated. Experimental results show that the established model achieves a correlation coefficient of 0.99786 on the training set, indicating its excellent fitting accuracy. Furthermore, the mean squared error on the test set is within 0.04 mm2, demonstrating the model’s good generalization ability. It can reproduce the dynamic characteristics of the CRVPPP-driven excitation system with high precision, thereby laying a solid modeling foundation for the characteristic analysis, structural optimization, and high-precision control of such excitation systems.
Ge et al. (Mon,) studied this question.