摘要：As a typical single-pump multi-actuator system, the hydraulic manipulator faces the flow saturation problem when moving at a high speed to track a desired trajectory. To overcome this problem, this paper proposes a real-time anti-saturation flow optimization algorithm based on the gradient projection method. By projecting the gradient of the demand flow in the null space of the task Jacobians, this algorithm can reduce the flow demand while enforcing a global volumetric flow limit in real time. The model of a 7-degree-of-freedom (DOF) hydraulic redundant manipulator was established to carry out theoretical derivation and algorithm design. Then, the experimental verification was completed on the real manipulator platform. Experimental results show that this algorithm reduces average demand flow by 9.85% and average power consumption by 310.3 W under no saturation condition. When flow saturation occurs, the algorithm can increase the average endpoint velocity by 7.52% and reduce the maximum directional error by 71.73% with an average calculation time step of 3 ms. The average trajectory position error can also be reduced by 42.59% compared with the anti-saturation algorithm. Therefore, the proposed algorithm can achieve real-time optimization to reduce flow consumption and achieve anti-saturation in practical applications of redundant hydraulic manipulator.
