论文部分内容阅读
通过对功率平衡关系进行分析,提出了利用功率反馈设计智能神经网络PID控制器的方法。基于BP(Back Propagation)神经网络,将功率信号作为神经网络的输入层信号,并改进了网络权值的学习规则。通过在线整定PID参数,控制器能够根据功率误差信号的变化实时调整控制参数,从而使系统自主寻找到功率平衡点,具有良好的稳态和动态响应特性。仿真结果表明:该方法可以使涡轴发动机在全包线范围内具有理想的控制性能。
By analyzing the power balance, a method of designing intelligent neural network PID controller by power feedback is proposed. Based on BP (Back Propagation) neural network, the power signal is regarded as the input layer signal of neural network and the learning rule of network weight is improved. By tuning PID parameters online, the controller can adjust the control parameters in real time according to the change of the power error signal, so that the system can find the power balance point autonomously and has good steady-state and dynamic response characteristics. The simulation results show that this method can make the turbine engine have ideal control performance in the whole envelope.