论文部分内容阅读
随着电动加载系统的不断发展,对控制精度、动态特性和稳定性提出了更高的要求,常规的小脑模型(CMAC)和PD控制相结合的复合控制策略难以满足加载指标要求。针对无人机舵机电动加载系统的控制需求,提出了一种基于平衡学习、最优权值和自适应学习率的新型小脑模型(BOWA-CMAC)复合控制策略,它在保留小脑模型算法正常学习过程的同时,避免了算法的过学习现象,保证了系统的稳定,同时提高了跟踪精度和动态特性。仿真和实验结果表明,BOWA-CMAC复合控制策略具有很强的鲁棒性,抑制了加载系统的多余力矩,保证了系统的稳定性,有效提高了系统的跟踪精度和动态特性,非常适合于实时控制。
With the continuous development of electric loading system, the control precision, dynamic characteristics and stability are put forward higher requirements. The combined control strategy of CMAC and PD control can not meet the requirements of loading index. Aiming at the control requirements of the UAV servo loading system, a novel BOWA-CMAC compound control strategy based on equilibrium learning, optimal weight and adaptive learning rate is proposed. Learning process at the same time, to avoid over-learning algorithm to ensure the stability of the system, while improving the tracking accuracy and dynamic characteristics. The simulation and experimental results show that the BOWA-CMAC composite control strategy has strong robustness, restrains the extra torque of loading system, ensures the stability of the system and effectively improves the tracking accuracy and dynamic characteristics of the system. It is very suitable for real-time control.