研究预测控制和PID控制在再热汽温系统控制中的应用。通过将神经网络作为预测模型,并用蚁群算法在线优化PID控制器参数。计算机仿真结果表明,基于蚁群算法的预测PID控制能够适应控制对象模型参数的时变,具有较好的鲁棒性,相对传统PID控制策略还表现出了良好的动态性能。 Application of Prediction Control and PID Control in Reheat Steam Temperature System. The neural network is used as a predictive model, and the parameters of PID controller are optimized online with ant colony algorithm. Computer simulation results show that the predictive PID control based on the ant colony algorithm can adapt to the time-varying of the control object model parameters, and has better robustness. Compared with the traditional PID control strategy, it also shows good dynamic performance.