论文部分内容阅读
隧道窑温度具有非线性、不确定、大时滞等特点,PID控制精度不高,工况变化时难再次达到稳态,为了提高控制精度采用了神经网络预测控制,充分利用神经网络的非线性、自组织、自学习的性能和预测控制的滚动优化、反馈调节的有效性。为了提高神经网络预测控制的性能文中结合了改进粒子群优化算法。结合了改进粒子群算法的神经网络预测控制的进行了隧道窑烧成带的仿真实验。仿真结果表明该方法的有效性和控制的效果的优越性和良好应用前景。
The temperature of tunnel kiln is nonlinear, uncertain and time-lag. The PID control precision is not high and it is hard to reach the steady state again when the working conditions change. In order to improve the control accuracy, the neural network predictive control is adopted, which makes full use of the nonlinearity of the neural network , Self-organizing, self-learning performance and predictive control of rolling optimization, feedback regulation effectiveness. In order to improve the performance of neural network predictive control, this paper combines improved particle swarm optimization algorithm. Combined with the improved particle swarm optimization algorithm neural network predictive control of tunnel kiln firing zone simulation. The simulation results show the superiority and good application prospect of the effectiveness of the method and the control effect.