BP 神經(jīng)網(wǎng)絡(luò)已被廣泛應(yīng)用于PID 控制器的優(yōu)化調(diào)參,但這種調(diào)參方法具有收斂速度慢、
學(xué)習(xí)時間長、連接權(quán)重初值為隨機值、易于陷入局部極小等缺點。本文提出了一種不同于用BP 網(wǎng)絡(luò)調(diào)整PID 參數(shù)的新的融合方法：PID 神經(jīng)網(wǎng)絡(luò)控制器（PIDNN）；該控制器不僅能克服以上缺點,而且具有很好的魯棒性。本文對PIDNN 在某無人機姿態(tài)控制系統(tǒng)的應(yīng)用進(jìn)行了仿真研究,仿真結(jié)果表明該控制器能夠大大地改善姿態(tài)控制系統(tǒng)性能。
關(guān)鍵詞：飛行控制 姿態(tài)控制 PID 神經(jīng)網(wǎng)絡(luò)控制器

Abstract: The neural network with BP algorithm has these disadvantages, such as slow
convergence rate, long learn time, local optimization and random value for the initial weight of the net, although it has been widely applied to regulate the parameters of PID controller. A new type of controller called PIDNN, which coalesces traditional PID and neural network together, is introduced in this paper. It overcomes these shortcomings mentioned and has better robustness. Then it is used in the flight control system of UAV, the simulation results show that it improves the performance of the system effectively.
Keywords: Flight Control, Attitude Control, PIDNN