Research on Stress Field of the Steam Turbine Rotor Based on SVM and the Finite Element Analysis

Abstract:

A model for on-line calculation of equivalent stresses in steam turbine rotors has been built up based on Support Vector Machine (SVM) neural network and the finite element method. Regarding 125MW steam turbine rotor as an object, SVM method is employed as a tool to train large numbers of date about the equivalent stress of the rotor, which obtained from the finite element method. A model can be gotten after finishing training the data. Equivalent stresses of rotor obtained with finite element and SVM model are compared during cold start. Results show that similar calculation results of equivalent stress may be obtained with either finite element or SVM model. However, with the latter one, the calculation becomes easier and fast, which is applicable for on-line calculation of equivalent stresses in turbine rotors, and may serve as a reference for on-line life management of turbine rotors.

• Periodical: Advanced Materials Research (Volumes 354-355)
• Pages: 446-453
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.354-355.446
• Online since: October 2011
• Authors: Jun Yu Wang, Dong Mei Ji, Xiu Ping Yao, Jin Yuan Shi, Yu Yang
• Keywords: Finite Element, Online Calculation, Rotors, Steam Turbine, Stress Field, Support Vector Machine (SVM)

References

[1] Jingbo Gao, Song Xia. The discussion of the application of the neural network on the online calculation of the thermal stress for turbine rotors[J]. Turbine Technology,1998, 40(5):263-264. In Chinese

[2] Xiaoyang Lou, Deren Sheng, Jianhong Chen, et al. Calculation of Finite Element of Thermal Stress and Analysis of Low-cyclic Fatigue Life for Non-central Hole Rotor of 135 MW Turbine[J]. Zhejiang Electric Power ,2007,10(5):10-14. In Chinese

[3] Zhiqiang Jiang, Jianhong Chen, Deren Sheng et al. Influence of Simplifying Shaft-Seal Grooves upon Thermal Stress Calculation Result of Steam Turbine's Rotor[J].Thermal Power Generation, 2006, 11(5):11-15. In Chinese

[4] Ying Li, Zheng Yun. Life Assessment on HP-IP Rotot of 125MW Turbine[J].East China Electric Power,1999,25(4)：7-11. In Chinese

[5] Yanjun Shen, Yonghua Yang. The Finite Elements Analysis Approach to the 300MW Turbine Rotor Stress Field[J]. Journal of Zhejiang Ocean University, 1998, 17(3):200-207. In Chinese

[6] Jun Liu, Xiaojun Chang, Jian Liu. Pinciple of Neural Network and its applications in Control[J]. Journal of QinDao Institute of chemical technology,1994,(2):167-171. In Chinese

[7] SIMON Haykin. Neural Network[M].Wei Shi, JAN Value translation.Machinery Industry Press, 2004.

[8] Yuanbing Hou, Jingyi Du, Mei Wang. Neural Network[M]. Xi'an University of Electronic Science and Technology Press,2007. In Chinese

[9] Minghua Shen, Li Xiao, Feixing Wang. Application of Support Vector Machine(SVM) in Pattern Recognition[J].Telecommunication Engineering,2006(4):9-12. In Chinese

[10] Ailing Ding, Xiaojun Xie, Yi Wen. The Comparison between SVM with Gaussian Kernel and Radial Basis Function Classifier [J]. Computer and Communications,2003(3):44-48. In Chinese

[11] Fengling Tao, Zhaonian Li, Jihua Li et al. Application of least squares Support Vector Machine to load forecasting in power system[J]. Water resources nd power,2010(12):146-148. In Chinese

[12] Jinyuan Shi, Yu Yang, Zhicheng Deng, et al. On-line calculation method based on artificial neutral network for equivalent stresses in steam turbine rotors[J]. Journal of Power Engineering, 2009, 29(4):316-319. In Chinese

DOI: 10.1007/978-3-540-76694-0_66

[13] Feng Pan, Haozhong Cheng, Jingfei Yang et al. Power system short-term load forecasting based on Support Vector Machines[J].Power system technology,2004,29(4):39-42. In Chinese

[14] Ning Fang, Dongmei Ji, Xiuping Yao, et al. Model of the stress correction coefficient of steam turbine rotor based on SVR[J]. Journal of Power Engineering, 2010, 30(3):166-169. In Chinese