为创建精确、稳定的试件二维加速度过载环境, 提高对转盘跟踪试验系统的控制精度, 对系统矢量转盘进行建模, 采用自适应混沌蚁群优化的RBF神经网络PID控制器, 解决RBF神经网络权值优化较慢的问题, 有效缩短神经网络学习时间, 提高PID控制器的在线自适应能力, 使转盘跟踪试验系统快速跟踪目标。仿真结果表明: 自适应混沌蚁群优化的RBF神经网络PID控制器优于传统的RBF神经网络PID控制器, 具有很好的准确性和快速性, 对于转盘跟踪试验系统设计具有较大的工程意义。

In order to create an accurate and stable two-dimensional acceleration overload environment for the test pieces and improve the control precision of the turntable tracking test system, the vector turntable is modeled.The PID controller based on the RBF neural network optimized by the adaptive chaotic ant colony algorithm is used, to solve the problem that the optimization of the weight of the RBF neural network is very slow, to effectively shorten the learning process of the neural network, and to improve the online adaptive ability of the PID controller, thus to enable the turntable tracking test system to rapidly track the target.The simulation results show that the PID controller based on the RBF neural network optimized by the adaptive chaotic ant colony algorithm is superior to that based on the traditional RBF neural network, and has satisfying accuracy and rapidity.It has great engineering significance for the design of the turntable tracking test system.