长短时记忆网络在热力站建模中的应用-计算机工程与应用.pdfVIP

Computer Engineering and Applications 计算机工程与应用 2018 ，54（24 ） 227 长短时记忆网络在热力站建模中的应用 用 李 琦，于明伟 应 LI Qi, YU Mingwei 与 内蒙古科技大学 信息工程学院，内蒙古 包头 014000 程 College of Information Engineering, University of Science and Technology of Inner Mongolia, Baotou, Inner Mongolia g 014000, China 工 r o . j LI Qi, YU Mingwei. Application of long short-term memory network in heating station modeling. Computer Engi- 机 a neering and Applications, 2018, 54 （24 ）：227-233. e 算 c . Abstract ：Aiming at the problem about the heating station control system belongs to multivariable, nonlinear, strong cou- 计 w pling and large time delay complex process control system, it is difficult to establish an accurate model. The long short- term memory based on recurrent neural network is proposed to model the heating station control system. The algorithm w not only considers the influence factors in time factor, but also solves the problem of long sequence information loss. Using w a large real-time data in Baotou heating station, the neural network model is build by the tensorflow framework. The simu- lation result shows that the long short-term memory network modeling can effectively reduce the modeling error, and improve the accuracy of neural network modeling system in heating station. Key words ：time series; recurrent neural network; long short-term memory; tensorflow; modeling of heating station 摘 要：针对热力站为多变量、非线性、强耦合、大时滞的复杂时序控制系统，难以建立精确模型的问题，提出基于循 环神经网络的长短时记忆算法对热力站控制系统建模，该算法既考虑到时间上的影响因素，又解决了长序列信息丢 失的问题。以包头某热力站大量实时工况数据通过tensorflow 框架搭