超临界机组协调控制系统的预测优化控制

Predictive optimal control for coordinated system of a supercritical power unit

为适应电网负荷需求,超临界机组常处于大幅度变工况运行状态,从而使得传统协调控制策略不能很好地适应机网协调运行的要求,影响机组的负荷响应速度,造成主蒸汽压力等参数大幅波动。对此,提出了一种基于神经网络和粒子群(PSO)算法的协调预测优化控制方法,并以某超临界600MW机组为对象,基于Matlab软件建立模型预测优化控制(MPOC)算法,借助火电机组仿真机对该控制方法进行验证。结果表明,该方法可大大提高机组的负荷响应速度,且满足主蒸汽压力等参数的控制要求。

In order to meet the requirements of power grid,a supercritical power generating unit often operates under wide-range load-changing conditions.The conventional coordinated control strategy can not well adapt to the load deep regulation situations,and often leads to slow load response and large main steam pressure fluctuations.Therefore,a model predictive optimal control（MPOC）method for coordinated control of the supercritical units was proposed,on the basis of neural network model and particle swarm optimization（PSO）algorithm.The proposed MPOC scheme was programmed with MATLAB software and tested by extensive control simulation experiments in the full-scope simulator of a 600 MW supercritical power generating unit.The simulation results show that the proposed MPOC method can improve the load dynamic response speed greatly and keep main steam pressure within safety limits.