根据超超临界锅炉汽水分离器的结构特点建立了三维有限元模型,以某1 000 MW机组为例模拟了其启动过程的总应力场.将有限元法和神经网络法相结合,以有限元计算结果作为训练样本,以介质压力和筒体壁温序列为辅助变量,建立了基于Elman神经网络的分离器应力动态软测量模型,通过模型的训练,确定了准确的应力预测模型结构.应用电厂实际运行监测数据对所建立的Elman网络软测量模型进行验证,结果表明:模型计算结果可很好地逼近有限元结果,预测精度高,实时性好,可为锅炉寿命的在线监测提供数据支持.
Abstract
Based on structural features of steam-water separator for ultra supercritical boilers, a 3D finite element model was established for thermal analysis purpose, with which the total stress field was simulated during start-up of a 1 000 MW unit. Combining the finite element method with neural network algorithm, a dynamic stress soft-sensing model was set up based on Elman neural network, by taking both the medium pressure and wall temperature series as auxiliary variables, and the finite element calculation results as training samples, of which the structure was subsequently determined after model training. The soft-sensing model was finally verified with actual operating and monitoring data of the power unit. Results show that the model calculation results can well approach that of finite element analysis. Featured by high precision and good real-time performance, the model may serve as a reference for on-line life monitoring of power plant boilers.
关键词
超超临界锅炉 /
汽水分离器 /
神经网络 /
Elman /
软测量模型
{{custom_keyword}} /
Key words
ultra supercritical boiler /
steam-water separator /
neural network /
Elman /
soft-sensing model
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 杨震,史英栓.1 913 t/h 超临界锅炉启动分离器的结构强度与寿命研究[J].动力工程,2006,26(4):462-466.
YANG Zhen,SHI Yingquan. Structural strength and life expectancy of the 1 913 t/h supercritical boiler’s start-up separator[J]. Journal of Power Engineering, 2006,26(4):462-466.
[2] 刘彤,史飞,孙保民,等.超临界锅炉启动汽水分离器应力分析及数值模拟[J].动力工程,2007,27(6):868-871.
LIU Tong,SHI Fei,SUN Baomin, et al. Stress analysis and simulation of a supercritical boiler’s starting water separator[J]. Journal of Power Engineering, 2007,27(6):868-871.
[3] 奚正稳,杜云华.超临界锅炉寿命损耗在线监测系统研究[J].东方电气评论,2008,22(3):27-30.
XI Zhengwen,DU Yunhua. Study on online monitoring system of life expenditure for supercritical pressure boiler[J]. Dong Fang Electric Review,2008,22(3):27-30.
[4] 陈彦桥,郭一,刘建民,等.一种改进烟气含氧量软测量建模方法与仿真[J].动力工程学报,2011,31(1):12-16.
CHEN Yanqiao,GUO Yi,LIU Jianmin, et al. An improved modeling method for soft-sensing of oxygen content in flue gas and the simulation [J]. Journal of Chinese Society of Power Engineering,2011,31(1):12-16.
[5] 闫姝,曾德良,刘吉臻,等.基于简化热平衡方程的再热蒸汽流量实时软测量[J]. 中国电机工程学报, 2011,31(5):114-119.
YAN Shu, ZENG Deliang, LIU Jizhen, et al. A soft-sensor method of reheat steam flow based on simplified heat-balance equation[J]. Proceedings of the CSEE, 2011, 31(5):114-119.
[6] NOOR A K.Bibliography of books and monographs on finite element technology[J].Applied Mechanics Reviews,1991,44(6):307-317.
[7] 唐勇,马卉宇,王益群.改进的协同遗传BP 算法在动态流量软测量技术中的研究与应用[J].机械工程学报, 2009, 45(1):298-302.
TANG Yong, MA Huiyu, WANG Yiqun. Research and application in soft dynamic flow measurement technology through the improved co-evolutionary genetic and BP algorithm[J].Chinese Journal of Mechanical Engineering, 2009,45(1):298-302.
[8] 仝卫国,杨耀权,金秀章.基于RBF神经网络的气体流量软测量模型研究[J].中国电机工程学报, 2006,26(1): 66-69.
TONG Weiguo, YANG Yaoquan,JIN Xiuzhang. Study on soft-sensing model of the gas flowrate measurement based upon RBF neural network[J]. Proceedings of the CSEE, 2006,26(1): 66-69.
[9] ELMAN J L. Finding structure in time [J] . Cognitive Science, 1990, 14(2): 179-211.
[10] 周孑民,朱再兴,刘艳军,等.基于Elman神经网络的动力配煤发热量及着火温度的预测[J].中南大学学报:自然科学版,2011, 42(12): 3871-3875.
ZHOU Jiemin, ZHU Zaixing, LIU Yanjun, et al. Predication of calorific value and ignition temperature of blended coal based on Elman neural network[J]. Journal of Central South University: Science and Technology, 2011, 42(12): 3871-3875.
[11] BECERIKLIA Y,OYSAL Y. Modeling and prediction with a class of time delay dynamic neural networks[J]. Applied Soft Computing, 2007,7(4): 1164-1169.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
中央高校基本科研业务费资助项目(12MS100);国家自然科学基金资助项目(61174111)
{{custom_fund}}