基于复合控制策略的电动负载模拟器研究

针对某雷达随动系统电动负载模拟器自身复杂的非线性以及多余力矩对系统加载性能的影响，提出了一种基于改进的小波神经网络和灰预测的控制策略。该策略主要由变结构的小波神经网络控制器（VSWNNC）和灰预测补偿器（GPC）构成，前者利用自学习算法动态改变隐含神经元数目，加快了系统的收敛速度，降低了系统的计算复杂度，提高了系统的动静态响应性能；后者利用灰理论来预测输入力矩偏差，进一步提高了系统的稳定性和准确性。半实物台架仿真试验结果表明：该复合控制策略具有较强的鲁棒性和较高的控制精度，保证了系统动态加载时的稳定性和抗干扰能力。

Research on electric-driven load simulator based on compound control strategy

Aiming at the influence of the complex nonlinearity and extra torque of electric-driven load simulator of a radar servo system on the system loading performance,a control strategy based on the modified wavelet neural network and grey pre-diction is put forward in this paper,Which is mainly composed of a variable structural wavelet neural network controller （VSWNNC）with particle swarm optimization and grey prediction compensator（GPC）. The former changes the number of hiden neurons dynamically by the self-learning algorithm to speed up the system convergence,reduce the calculation complexity,and improve the dynamic and static performance of the system. The latter predicts the input torque deviation by the grey theory to fur-ther improve the stability and accuracy of the system. The results of semi-physical simulation show that the compound control strategy has strong robustness and high control precision,and ensures the stability and anti-interference ability of the system dy-namic loading.