面向广义预测控制的协调控制系统建模与控制

针对电厂协调控制系统,提出了一种基于支持向量机(SVM)的广义预测控制(GPC)建模方法和控制算法。首先,根据电厂机组的实际运行参数,建立了600 MW亚临界燃煤机组协调控制系统受控对象的数学模型。其次,在建模过程中提出了一种新的混合优化算法——差分进化-灰狼优化混合算法(DE-GWO),以优化SVM,提高模型的准确性。最后,将基于SVM的GPC算法用于电站协调控制系统的设计。仿真结果表明,所提方法具有良好的跟踪能力和较强的鲁棒性。

Modeling and Control of Coordinated Control System Oriented to Generalized Predictive Control

Aiming at the coordinated control system of power plants,a modeling method and control algorithms based on support vector machine (SVM) for generalized predictive control (GPC) is proposed.Firstly,according to the actual operation parameters of a power plant unit,the mathematical model of the controlled object of a 600 MW subcritical coal-fired unit coordinated control system is established.Secondly,a new hybrid optimization algorithm,namely,DE-GWO,is proposed to optimize SVM in order to improve the accuracy of the model.Finally,the coordinated control system is designed by using the generalized predictive control algorithm based on SVM.The simulation results show that the proposed method has good tracking ability and strong robustness.