论文部分内容阅读
为完成对微型直升机航向的控制,利用机载测控系统获得人工操纵数据,采用神经网络和参数拟合的方法提取人工控制指令u和对应的航向变化ψ,从而得出人工控制策略,并建立相应的控制策略模型。在比较两种不同的控制策略模型时发现,神经网络模型适用于控制指令实时输出的参考,而参数化模型更易于在微型直升机的控制系统中使用。以参数化控制策略模型和PID控制律为基础,可规划控制指令轨迹并设计航向控制器。实验结果表明,该控制器能够稳定而准确地改变和保持微型直升机航向。
In order to complete the control of the helicopter’s heading, artificial control data is obtained by using the on-board measurement and control system and the artificial control instruction u and the corresponding heading change ψ are extracted by neural network and parameter fitting method to obtain the artificial control strategy and establish the corresponding Control strategy model. When comparing two different control strategy models, it is found that the neural network model is suitable for reference of real-time control command output, while the parametric model is easier to be used in the control system of micro helicopter. Based on the parametric control strategy model and PID control law, the trajectory of control commands can be planned and the course controller can be designed. The experimental results show that the controller can change and maintain the helicopter course steadily and accurately.