论文部分内容阅读
针对温室温度控制系统存在非线性、时变、大滞后与大惯性等问题,传统的PID控制方法并不能满足温室温度控制系统强自适应力、强鲁棒性的要求,提出了一种自适应能力强的径向基神经网络(RBF)PID的控制策略。建立了3层的神经网络模型,在RBF神经网络PID控制过程中,由神经网络RBF在线辨识得到了梯度信息,然后由得到的梯度信息对PID中的三个参数进行在线调整。仿真结果表明,基于RBF-PID控制系统动态响应快、自适应性强、超调量小、稳态精度高,能够实现温室温度的自适应控制。
In order to solve the problems of non-linear, time-varying, large-delay and large inertia of greenhouse temperature control system, the traditional PID control method can not meet the requirements of strong self-adaptability and strong robustness of greenhouse temperature control system. Powerful Radial Basis Function Neural Network (RBF) PID Control Strategy. A three-layer neural network model is established. In the process of PID control of RBF neural network, the gradient information is obtained by RBF neural network identification online. Then the three parameters of PID are adjusted online by the obtained gradient information. The simulation results show that the RBF-PID control system has the advantages of fast dynamic response, strong adaptability, small overshoot and high steady-state accuracy, and can realize adaptive control of greenhouse temperature.