Due to the highly nonlinear,time-varying,and uncertain working environment of robotic arms,their dynamic behavior is complex.Traditional control methods often encounter problems such as large joint position angle errors and poor stability during the control process.Therefore,a control method based on the improved Deep Deterministic Policy Gradient(DDPG)is proposed.Firstly,a kinematic model of intelligent loading and unloading machinery equipment is established;secondly,a loading and unloading action control model based on the DDPG algorithm is established;thirdly,u the Actor network(strategy network)and Critic network(value network)are used to improve the loading and unloading action control process in DDPG;finally,the reward function is optimized to train the Actor network and Critic network.and achieve loading and unloading machinery equipment control.The experimental results show that the actual motion trajectory of intelligent loading and unloading machinery equipment is very close to the ex-pected trajectory,and the joint position error is always less than 5.0 cm,and the attitude angle error is al-ways less than 1.00°.This can effectively control the joint position and attitude angle.The proposed im-proved DDPG algorithm has a good control effect.
To solve the position control problem of the induction motor with parameter perturbations, load disturbances, and modeling errors, a predefined-time position tracking optimization control method with prescribed performance is proposed. In practice, the rotor flux linkage of the induction motor can't be measured, and a predefined-time sliding mode observer (PTSMO) is applied to accurately estimate it. Additionally, predefined-time disturbance observers (PTDOs) are employed to identify the uncertainties in the motor system. The position and flux linkage controllers are then designed by integrating the predefined-time control approach with the prescribed performance function method, realizing accurate tracking control of the induction motor within a predefined time. Next, the adaptive genetic algorithm (AGA) and the improved particle swarm optimization (IPSO) technique are combined to optimize the designed controllers, enhancing the convergence rate and steady-state accuracy of the induction motor. Finally, comparative analyses through simulations and dSPACE simulated experiments validate the efficacy of the proposed control method, highlighting its applicability in practical motor systems.
In this paper, the requirements of field debugging of intelligent gateway of power distribution are studied, and the on-site simulation cloud testing technology and signal injection method of different types of terminals are proposed. According to the results we got, the automatic closed-loop debugging of "End, Edge and Cloud" is realized through the field debugging. For the field debugging of primary and secondary fusion DTU/FTU, an independent electromagnetic/ electronic signal output channel and high-precision output technology are designed, and the automatic closed-loop debugging is conducted in cooperation with the analog power distribution master station. The software architecture of debugging tool and the automatic test flow of intelligent terminal are also described in this paper in detail. The debugging tool based on this technology has been tested on site and proofed it is with high-performance.
在多因素耦合作用下桥梁结构会产生振动,以毫米波雷达技术为测量手段,提出桥梁索杆振动检测及自动控制方法.分析在恒载作用下桥梁索杆静止状态与振动状态的应变能,结合动能、势能和恒载做功等建立索杆平面内与平面外的振动特征描述方程.通过发送多周期连续毫米波雷达探测信号,取得同周期回波信号.根据回波信号与对应瞬时相位得到单频差拍信号及瞬时相位,检测出索杆振动幅值.利用半正定矩阵和正定矩阵等函数,建立令振动幅值达到最小值的桥梁索杆振动自动控制模型.实验结果表明,所提方法检测精准度较高,自动控制效果较好,并有效抑制了振动幅度,具备良好的应用性能.
机器人的惯性参数辨识是基于动力学模型控制器设计的基础,除了需要辨识机器人自身的惯性参数外,还需要快速准确地辨识负载的惯性参数.针对需要更换负载的工作场景,提出了 一种快速辨识负载的激励轨迹,该轨迹不需要经过优化,即可在短时间内覆盖更多的机器人运动状态,从而获得更为全面的采样参数集,提高了辨识效率的同时增强了辨识模型的泛化能力.实验表明,辨识的结果与负载模型的CAD参数符合,机器人关节理论力矩能较好地拟合实际驱动力矩,验证了负载参数的正确性.
