The Calculation of Turbine Exhaust Enthalpy Based on the Hybrid Model of the Principal Component Analysis and the BP Neural Network

doi:10.11930/j.issn.1004-9649.201702049

Abstract

Abstract: Taking a 300 MW turbine as an example, in this paperthe calculation of turbine exhaust enthalpy based on the hybrid model of the principal component analysis and the BP neural network is established. The principal component analysis and the BP neural network are introduced at first. Then,the historical data are collected as the main parameters that affect the steam turbine exhaust enthalpy.The data pre-processing is applied to exclude the bad points. The four major components, with the cumulative contribution value greater than 99.95%, are identified. The calculation model of turbine exhaust enthalpy is established with the four identified components as the BP neural network input parameters and the steam turbine exhaust enthalpy as the output parameter. After being trained and tested, the calculation model of turbine exhaust enthalpy is obtained to facilitate the real-time online monitoring. The results show that the principal component analysis can help to determine the reasonable BP neural network input parameters and improve the accuracy and the speed of the training. The precision of the hybrid model meets the requirements of the project. The fluctuation of the exhaust steam enthalpy is not big in all working conditions.

Key words: steam turbine, exhaust enthalpy, principal component analysis, BP neural network

CLC Number:

TM621

YANG Bin, YANG Yongjun, ZHANG Ya, HUANG Meng, LI Kunlun, DENG Xinliang, BAI Huanqing. The Calculation of Turbine Exhaust Enthalpy Based on the Hybrid Model of the Principal Component Analysis and the BP Neural Network[J]. Electric Power, 2018, 51(1): 126-132.

Add to citation manager EndNote|Ris|BibTeX

URL: https://www.electricpower.com.cn/EN/10.11930/j.issn.1004-9649.201702049

https://www.electricpower.com.cn/EN/Y2018/V51/I1/126

References

[1] 韩中合,杨昆. 汽轮机中蒸汽湿度测量方法的研究现状[J]. 华北电力大学学报,2002,29(4):44-47. HAN Zhonghe, YANG Kun. Reviews on wetness measurement methods of wet steam in turbine[J]. Journal of North Electric Power University, 2002, 29(4):44-47.
[2] 曹祖庆. 汽轮机变工况特性[M]. 北京:水利电力出版社,1989.
[3] 朱明善. 工程热力学[M]. 北京:清华大学出版社,1995.
[4] 沈士一,庄贺庆,康松,等. 汽轮机原理[M]. 北京:水利电力出版社,1992.
[5] 任浩仁,盛德仁. 汽轮机在线性能计算中排汽焓的确定[J]. 动力工程,1998,18(6):1-4. REN Haoren, SHENG Deren. The enthalpy determining in the steam turbine online performance calculation[J]. Power Engineering, 1998, 18(6):1-4.
[6] 韩中合,杨昆. 凝汽式汽轮机排汽焓的简便算法与误差分析[J]. 汽轮机技术,2006,48(3):167-170. HAN Zhonghe, YANG Kun. A simple method of online calculation steam turbine exhaust enthalpy and error analysis[J]. Turbine Technology, 2006, 48(3):167-170.
[7] 郭江龙,张树芳,陈海平. 火电机组排汽焓在线计算方法的研究[J]. 发电设备,2001(6):11-14. GUO Jianglong, ZHANG Shufang, CHEN Haiping. On-line calculation of exhaust steam enthalpy in thermal power sets[J], Generating Equipment, 2001(6):11-14.
[8] 李慧君,孙定,张斌. 机组母管制给水系统分配方案的研究[J]. 华北电力大学学报,2003,30(3):57-61. LI Huijun, SUN Ding, ZHANG Bin. Research on feed-water distribution scheme in fossil-fired power station[J]. Journal of North Electric Power University, 2003, 30(3):57-61.
[9] 郭江龙,张树芳,陈海平. 基于BP神经网络的汽轮机排汽焓在线计算方法[J]. 热能动力工程,2004,19(2):179-181. GUO Jianglong, ZHANG Shufang, CHEN Haiping. The online calculation method of the steam turbine exhaust steam enthalpy based on the BP neural network[J]. Journal of Engineering for Thermal Energy and Power, 2004, 19(2):179-181.
[10] 吴俊杰,侯宏娟,杨勇平. 神经网络算法在汽轮机排汽焓估算中的应用[J]. 热力发电,2014(8):125-130. WU Junjie, HOU Hongjuan, YANG Yongping. Application of neural network algorithm in steam turbine's exhaust enthalpy estimation[J]. Thermal Power Generation, 2014(8):125-130.
[11] 高惠璇. 应用多元统计分析[M]. 北京:北京大学出版社,2005.
[12] 高隽. 人工神经网络原理及仿真实例[M]. 北京:机械工业出版社,2003.
[13] 黄德双. 神经网络模式识别系统理论[M]. 北京:电子工业出版社,1996.
[14] 张雨浓,杨逸文,肖秀春,等. 样条神经网络的权值直接确定法[J]. 系统工程与电子技术,2009,31(11):2685-2688. ZHANG Yunong, YANG Yiwen, XIAO Xiuchun, et al. Weights direct determination of a spline neural network[J]. System's Engineering and Electronics, 2009, 31(11):2685-2688.
[15] 黄青贵. 人工神经网络导论[M]. 北京:中国水利水电出版社,2004.
[16] 董学育,胡华进,徐治皋. 电站性能分析采样数据的可靠性检验方法[J]. 动力工程,1998,18(2):16-19. DONG Xueyu, HU Huajing, XU Zhigao. The reliability testing method of the sampling data for the power plant performance analysis[J]. Power Engineering, 1998, 18(2):16-19.