【摘要】 为解决火电机组中凝结水节流模型难以兼顾准确性、快速性和泛化性的问题，提出一种结合机理建模和数据驱动建模的混合建模方法，深入分析了凝结水节流对除氧器内部压力的动态影响，并引入参数辨识技术。首先，根据凝结水节流系统的动态特性和静态特性，建立准确性高的复杂机理模型；其次，在保证模型精准度的前提下，借助数据驱动方法找到复杂模块中某些复杂变量之间的关系，降低模型的复杂度并提高模型的快速性；最终，采用粒子群优化（PSO）算法，根据所提出的关于负荷、除氧器容积和压力偏差的适应度函数，对不同工况下模型中未知参数进行辨识，提高模型的泛化性。仿真结果表明，在260 MW和450 MW工况下，所提模型的均方根误差（RMSE）、Pearson相关系数等评价指标均有较好表现。证明该模型具有较高的准确性、快速性和泛化性。更多还原

【Abstract】 In order to solve the problem that it is difficult to combine accuracy, rapidity and generalization of condensate throttling models in thermal power units, a hybrid modeling method that combines mechanism modeling and data-driven modeling is proposed. The dynamic effect of condensate throttling on the internal pressure of the deaerator is deeply analyzed, and the parameter identification technology is introduced. A complex mechanism model with high accuracy is established based on the dynamic and static characteristics of the condensate throttling system. Under the premise of ensuring the accuracy of the model, with the help of data-driven methods, the relationship between a certain complex variables in the complex module is found, which reduces the complexity of the model and improves the rapidity of the model. The particle swarm optimization(PSO) algorithm is used to identify the unknown parameters in the model under different operating conditions and improve the generalization of the model according to the proposed fitness function about load, deaerator volume and pressure deviation. The simulation results show that the evaluation indexes such as root mean square error(RMSE) and Pearson correlation coefficient of the present model can perform well under 260 MW and 450 MW operating conditions. It proves that the present model has high accuracy, rapidity and generalization.更多还原