摘要
针对水轮发电机组的数学机理建模存在的建模过程复杂、非线性和多参数耦合表达效果差的问题和大型水轮发电机组面临的风光能源接入和电网互联复杂的问题,比较分析机理建模和数据驱动优缺点,研究深度信念网算法关于水轮发电机组建模的可行性,建立了基于深度信念网数据驱动方法的大型水轮发电机组模型,通过某机组共计129600组实际数据进行模型训练和校验,并在机组空载频率扰动下进行仿真试验验证所建模型的有效性和稳定性。
Aiming at the problems of complex modeling process, nonlinear and poor multi parameter coupling expression effect existing in the mathematical mechanism modeling of hydraulic turbine generator units, and the complex problems of wind and solar energy access and grid interconnection faced by large hydraulic turbine generators, the advantages and disadvantages of mechanism modeling and data driving are compared and analyzed, and the feasibility of deep belief network algorithm on the modeling of hydraulic turbine generator units is studied. A large hydro generator unit model based on the data driven method of deep belief network is established. The model is trained and verified by a total of 129600 groups of actual data of a unit, and the effectiveness and stability of the model are verified by simulation tests under the no-load frequency disturbance of the unit.
作者
赵金平
ZHAO Jinping(Yalong River Hydropower Development Company Ltd.,Chengdu 610051,China)
出处
《大电机技术》
2023年第2期73-78,90,共7页
Large Electric Machine and Hydraulic Turbine
