On the Stress Prediction of Key Components in Steam Turbine Rotors Based on the NARX Neural Network

ZHANG Chaodong; ZHAO Xiang; RU Dongheng; WANG Peng; WU Hao; GAN Lei

doi:10.21656/1000-0887.410372

Volume 42 Issue 8

Aug. 2021

Turn off MathJax

Article Contents

Article Navigation > Applied Mathematics and Mechanics > 2021 > 42(8): 771-784

ZHANG Chaodong, ZHAO Xiang, RU Dongheng, WANG Peng, WU Hao, GAN Lei. On the Stress Prediction of Key Components in Steam Turbine Rotors Based on the NARX Neural Network[J]. Applied Mathematics and Mechanics, 2021, 42(8): 771-784. doi: 10.21656/1000-0887.410372

Citation:

PDF( 6144 KB)

On the Stress Prediction of Key Components in Steam Turbine Rotors Based on the NARX Neural Network

doi: 10.21656/1000-0887.410372

1. School of Aerospace Engineering and Applied Mechanics, Tongji University, Shanghai 200092, P.R.China;
2. Turbine Plant, Shanghai Electric Power Generation Equipment Co. Ltd.,Shanghai 200240, P.R.China;
3. School of Science, Harbin Institute of Technology(Shenzhen), Shenzhen, Guangdong 518055, P.R.China

Funds:

The National Natural Science Foundation of China(11932005

11972255

11772106)

Received Date: 2020-12-07
Rev Recd Date: 2021-04-14

Available Online: 2021-08-14

Abstract

Abstract

Stress prediction of steam turbine rotors during startup processes is of great significance. To predict the stresses of key components in a 350 MW supercritical steam turbine rotor, a NARX neural network-based method was proposed with a 2D axisymmetric finite element model established according to the actual dimensions of the rotor. Appropriate boundary conditions were applied to the model and the temperature and stress distributions under cold startup conditions were calculated. The simulated results were experimentally verified and the danger points of the rotor were then determined after 288 finite element calculations according to typical startup conditions. The stresses calculated near the danger points as well as several user-selected operating parameters were used to establish the neural network sample dataset. An effective NARX neural network was employed to estimate the stresses at the danger points. The results show that, the proposed method can accurately predict the stresses with their tendency. The stresses predicted by the NARX neural network are in good agreement with the finite element simulated results, and can meet the requirements for rotor stress monitoring.
- turbine rotor,
- NARX neural network,
- finite element method,
- stress prediction

FullText(HTML)

References(30)

References

[2]甘磊, 吴昊, 仲政. 基于能量法的多轴疲劳寿命预测方法[J]. 固体力学学报, 2019,40(3): 260-268.(GAN Lei, WU Hao, ZHONG Zheng. Fatigue life prediction under multiaxial loading using energy-based models[J]. Chinese Journal of Solid Mechanics, 2019,40(3): 260-268.(in Chinese))

吕方明, 王坤, 黄树红, 等. 国产超临界汽轮机转子钢低周疲劳特性的试验研究[J].动力工程学报, 2013,33(8): 653-658.

(Lü Fangming, WANG Kun, HUANG Shuhong, et al. Experimental study on low-cycle fatigue properties of domestic supercritical turbine rotor steels[J]. Journal of Chinese Society of Power Engineering,2013,33(8): 653-658.(in Chinese))

[3]黄仙, 倪维斗. 汽轮机转子热应力的“复频法”建模研究[J]. 动力工程, 1995,15(6): 6-11.(HUANG Xian, NI Weidou. Thermal stress of steam turbine rotor based on complex frequency method[J]. Journal of Power Engineering,1995,15(6): 6-11.(in Chinese))

[4]黄仙, 倪维斗. 大型汽轮机转子动态热应力的数学模型[J]. 清华大学学报(自然科学版), 1996,36(10): 25-29.(HUANG Xian, NI Weidou. Study on dynamic thermal stresses in large-scale steam turbine rotors[J]. Journal of Tsinghua University (Science and Technology),1996,36(10): 25-29.(in Chinese))

[5]张恒良, 谢诞梅, 熊扬恒, 等. 600 MW汽轮机转子高精度热应力在线监测模型研制[J]. 中国电机工程学报, 2006,26(1): 21-25.(ZHANG Hengliang, XIE Danmei, XIONG Yangheng, et al. The research and development of high-quality thermal-stress online monitoring model for 600 MW turbine rotors[J]. Proceedings of the CSEE,2006,26(1): 21-25.(in Chinese))

[6]黄柳燕, 荆建平, 孟光. 采用平均温度计算汽轮机转子热应力的二维差分法[J]. 汽轮机技术, 2014,56(5): 332-334.(HUANG Liuyan, JING Jianping, MENG Guang. Two-dimensional difference method for thermal stress calculation of steam turbine rotor by using average temperature[J]. Turbine Technology,2014,56(5): 332-334.(in Chinese))

[7]BIAN S, LI W Y. Calculation of thermal stress and fatigue life of 1 000 MW steam turbine rotor[J]. Energy and Power Engineering,2013,5(4): 1484-1489.

[8]赵乃龙, 吴穹, 王炜哲, 等. 超超临界汽轮机高压转子低周疲劳及损伤分析[J]. 上海交通大学学报, 2015,49(5): 590-594.(ZHAO Nailong, WU Qiong, WANG Weizhe, et al. Numerical analysis of low-cycle fatigue and damage of a ultra-supercritical steam turbine high-pressure rotor[J]. Journal of Shanghai Jiao Tong University,2015,49(5): 590-594.(in Chinese))

[9]张炜, 胡玉峰. 基于有限元分析的汽轮机转子低周疲劳损耗研究[J]. 热能动力工程, 2018,33(9): 31-38.(ZHANG Wei, HU Yufeng. Study on low cycle fatigue loss of turbine rotor based on finite element analysis[J]. Journal of Engineering for Thermal Energy and Power,2018,33(9): 31-38.(in Chinese))

[10]SIMON H. Neural Networks: a Comprehensive Foundation[M]. New York: MacMillan College Publishing Company, 1994.

[11]BISHOP C M. Neural Networks for Pattern Recognition[M]. Oxford: Oxford University Press, 1995.

[12]HECHT-NIELSEN R. Theory of the backpropagation neural network[C]//IEEE International 1989 Joint Conference on Neural Networks. Washington DC, USA, 1989.

[13]DOMINICZAK K, RZADKOWSKI R, RADULAKI W, et al. Online prediction of temperature and stress in steam turbine components using neural networks[J]. Journal of Engineering for Gas Turbines & Power,2015,138(5): 052606.

[14]DOMINICZAK K, RZADKOWSKI R, RADULAKI W. Steam turbine stress control using NARX neural network[J]. Open Engineering,2015,5(1): 421-428.

[15]RZADKOWSKI R, DOMINICZAK K, RADULAKI W. Thermoelastic steam turbine rotor control based on neural network[J]. Journal of Physics Conference,2015,662: 012021.

[16]王鹏, 李潇潇, 李文福, 等. 汽轮机高温热部件寿命监测系统介绍[J]. 热力透平, 2019,48(4): 248-253.(WANG Peng, LI Xiaoxiao, LI Wenfu, et al. Life monitoring system for high temperature components in steam turbines[J]. Thermal Turbine,2019,48(4): 248-253.(in Chinese))

[17]黄来, 韩彦广, 焦庆丰. 600 MW超临界汽轮机启停过程热力耦合分析[J]. 汽轮机技术, 2011,53(1): 66-70.(HUANG Lai, HAN Yanguang, JIAO Qingfeng. The start and stop process coupled thermo-mechanical analysis of 600 MW supercritical steam turbine[J]. Turbine Technology,2011,53(1): 66-70.(in Chinese))

[18]BRILLIANT H M, TOLPADI A K. Analytical approach to steam turbine heat transfer in a combined cycle power plant[C]//ASME Turbo Expo: Power for Land, Sea & Air. Vienna, Austria, 2004,3: 401-409.

[19]ZHAO N L, WANG W Z, ZHANG J H, et al. Numerical investigation on life improvement of low-cycle fatigue for an ultra-supercritical steam turbine rotor[J]. Journal of Mechanical Science and Technology,2016,30: 1747-1754.

[20]KUBOTA M, KATAOKA S, KONDO Y. Effect of stress relief groove on fretting fatigue strength and index for the selection of optimal groove shape[J]. International Journal of Fatigue,2009,33(3): 439-446.

[21]施徐明. 转子三段圆弧结构应力释放槽的研究[J]. 热力透平, 2020,49(1): 58-62.(SHI Xuming. Study of stress relief groove with three arcs in rotor[J]. Thermal Turbine,2020,49(1): 58-62.(in Chinese))

[22]张雅美, 郝涛, 尹四倍, 等. 具有时延和随机扰动的未知C-G神经网络的有限时间函数投影同步及其在保密通信中的应用[J]. 应用数学和力学, 2020,41(12): 1405-1416.(ZHANG Yamei, HAO Tao, YIN Sibei, et al. Finite-time function projective synchronization of unknown Cohen-Grossberg neural networks with time delays and stochastic disturbances and its application in secure communication[J]. Applied Mathematics and Mechanics,2020,41(12): 1405-1416.(in Chinese))

[23]刘松, 彭勇, 邵毅明, 等. 基于门控递归单元神经网络的高速公路行程时间预测[J]. 应用数学和力学, 2019,40(11): 1289-1298.(LIU Song, PENG Yong, SHAO Yiming, et al. Expressway travel time prediction based on gated recurrent unit neural networks[J]. Applied Mathematics and Mechanics,2019,40(11): 1289-1298.(in Chinese))

[24]SIEGELMANN H T, HORNE B G, GILES C L. Computational capabilities of recurrent NARX neural networks[J]. IEEE Transactions on Systems, Man, and Cybernetics (Part B): Cybernetics,1997,27(2): 208-215.

[25]MENEZES JR J M P, BARRETO G A. Long-term time series prediction with the NARX network: an empirical evaluation[J]. Neurocomputing,2008,71(16/18): 3335-3343.

[26]NOWAK G, RUSIN A. Using the artificial neural network to control the steam turbine heating process[J]. Applied Thermal Engineering,2016,108: 204-210.

[27]LIN T, HORNE B G, TINO P, et al. Learning long-term dependencies in NARX recurrent neural networks[J]. IEEE Transactions on Neural Networks,1996,7(6): 1329-1338.

[28]方开泰. 均匀设计: 数论方法在试验设计的应用[J]. 应用数学学报, 1980,3(4): 363-372.(FANG Kaitai. The uniform design: application of number-theoretic methods in experimental design[J]. Acta Mathematica Sinica,1980,3(4): 363-372.(in Chinese))

[29]方开泰. 正交与均匀试验设计[M]. 北京: 科学出版社, 2001.(FANG Kaitai. Orthogonal and Uniform Test Design[M]. Beijing: Science Press, 2001.(in Chinese))

[30]HAGAN M T, MENHAJ M B. Training feedforward networks with the Marquardt algorithm[J]. IEEE Transactions on Neural Networks,1994,5(6): 989-993.

Relative Articles

Supplements(0)

Cited By

Proportional views