Reliability-based combined high and low cycle fatigue analysis of turbine blade using adaptive least squares support vector machines

다국어 초록 (Multilingual Abstract)

In this work, a novel reliability approach for combined high and low cycle fatigue (CCF) estimation is developed by combining active learning strategy with least squares support vector machines (LS-SVM) (named as ALS-SVM) surrogate model to address the multi-resources uncertainties, including working loads, material properties and model itself. Initially, a new active learner function combining LS-SVM approach with Monte Carlo simulation (MCS) is presented to improve computational efficiency with fewer calls to the performance function. To consider the uncertainty of surrogate model at candidate sample points, the learning function employs k-fold cross validation method and introduces the predicted variance to sequentially select sampling. Following that, low cycle fatigue (LCF) loads and high cycle fatigue (HCF) loads are firstly estimated based on the training samples extracted from finite element (FE) simulations, and their simulated responses together with the sample points of model parameters in Coffin-Manson formula are selected as the MC samples to establish ALS-SVM model. In this analysis, the MC samples are substituted to predict the CCF reliability of turbine blades by using the built ALSSVM model. Through the comparison of the two approaches, it is indicated that the reliability model by linear cumulative damage rule provides a non-conservative result compared with that by the proposed one. In addition, the results demonstrate that ALS-SVM is an effective analysis method holding high computational efficiency with small training samples to gain accurate fatigue reliability.

참고문헌 (Reference)

1 Yue, P., "Threshold damage-based fatigue life prediction of turbine blades under combined high and low cycle fatigue" 150 : 106323-, 2021

2 Zio, E., "The future of risk assessment" 177 (177): 176-190, 2018

3 Dungey, C., "The effect of combined cycle fatigue upon the fatigue performance of Ti-6Al-4V fan blade material" 153 (153): 374-379, 2004

4 Gao, H. F., "Substructure-based distributed collaborative probabilistic analysis method for low-cycle fatigue damage assessment of turbine blade-disk" 79 : 636-646, 2018

5 Yuan, R., "Simulation-based design and optimization and fatigue characteristics for high-speed backplane connector" 11 (11): 1-10, 2019

6 Li, W., "Risk based design optimization under hybrid uncertainties" 1 : 1-13, 2020

7 Socie, D., "Risk and Failure Analysis for Improved Performance and Reliability" Plenum Publication Corp 1980

8 Gao, H. F., "Reliability-based low-cycle fatigue damage analysis for turbine blade with thermo-structural interaction" 49 : 289-300, 2016

9 Zhang, C. Y., "Reliability-based low fatigue life analysis of turbine blisk with generalized regression extreme neural network method" 12 (12): 1545-1560, 2019

10 Gao, H. F., "Reliability analysis on resonance for low-pressure compressor rotor blade based on least squares support vector machine with leave-one-out cross-validation" 7 (7): 1-11, 2015

11 Li, H., "Reliability analysis of the main drive system of a CNC machine tool including early failures" 215 : 107846-, 2021

12 Li, H., "Reliability analysis of floating offshore wind turbine using Bayesian network" 217 : 107827-, 2020

13 Zhang, C. Y., "Reliability analysis of aeroengine blade based on extremum response surface method" 20 (20): 5-10, 2015

14 Niu, X. P., "Probabilistic modeling of uncertainties in fatigue reliability analysis of turbine bladed disks" 142 : 105912-, 2020

15 Zhu, S. P., "Probabilistic framework for multiaxial LCF assessment under material variability" 103 : 371-385, 2017

16 Zhu, S. P., "Probabilistic fatigue life prediction and reliability assessment of a high pressure turbine disc considering load variations" 27 (27): 1569-1588, 2018

17 Song, L. K., "Probabilistic LCF life assessment for turbine discs with DC strategy-based wavelet neural network regression" 119 : 204-219, 2019

18 Li, H., "Physics of failure-based reliability prediction of turbine blades using multi-source information fusion" 72 : 624-635, 2018

19 Wang, B. W., "PSO-LSSVR : A surrogate modeling approach for probabilistic flutter evaluation of compressor blade" 28 : 1634-1645, 2020

20 Zhang, C. Y., "Multiobject reliability analysis of turbine blisk with multidiscipline under multiphysical field interaction" 2015

21 Yuan, R., "Multidisciplinary reliability design optimization using an enhanced saddlepoint approximation in the framework of sequential optimization and reliability analysis" 230 (230): 570-578, 2016

22 Song, L. K., "Multi-objective reliability-based design optimization approach of complex structure with multi-failure modes" 64 : 52-62, 2017

23 Zhang, Y. K., "Modified three-parameter model to predict compressor blade fatigue life under vibration loading" 32 (32): 04019034-, 2019

24 Schweizer, C., "Mechanisms and modeling of fatigue crack growth under combined low and high cycle fatigue loading" 33 (33): 194-202, 2011

25 Zeng, J. Y., "Generalization of parameter selection of SVM and LS-SVM for regression" 1 : 745-755, 2019

26 Zhu, S. P., "Fatigue reliability assessment of turbine discs under multi-source uncertainties" 41 (41): 1291-1305, 2018

27 Kumari, S., "Failure analysis of gas turbine rotor blades" 45 : 234-244, 2014

28 Zhu, S. P., "Evaluation and comparison of critical plane criteria for multiaxial fatigue analysis of ductile and brittle materials" 112 : 279-288, 2018

29 Gao, H. F., "Dynamic probabilistic-based LCF damage assessment of turbine blades regarding time-varying multi-physical field loads" 108 : 104193-, 2020

30 Yue, P., "Dynamic fatigue reliability analysis of turbine blades under the combined high and low cycle loadings" 30 (30): 828-844, 2021

31 Carter, T. J., "Common failures in gas turbine blades" 12 (12): 237-247, 2005

32 Hu, D. Y., "Combined fatigue experiments on full scale turbine components" 85 (85): 4-9, 2013

33 Academic Committee of the Superalloys, "China Superalloys Handbook" China Zhijian Publishing House & Standards Press of China 2012

34 Manson, S, "Behavior of materials under conditions of thermal stress" Lewis Flight Propulsion Laboratory 1954

35 Bourinet, J. M., "Assessing small failure probabilities by combined subset simulation and Support Vector Machines" 33 (33): 343-353, 2011

36 Hou, N. X., "Application of a combined high and low cycle fatigue life model on life prediction of SC blade" 31 : 616-619, 2009

37 Gao, H., "An integrated reliability approach with improved importance sampling for low-cycle fatigue damage prediction of turbine disks" 199 : 106819-, 2020

38 Yuan, R., "An enhanced genetic algorithm-based multi-objective design optimization strategy" 10 (10): 1-6, 2018

39 Yuan, R., "An enhanced Monte Carlo simulation-based design and optimization method and its application in the speed reducer design" 9 (9): 1-7, 2017

40 Pan, Q., "An efficient reliability method combining adaptive Support Vector Machine and Monte Carlo Simulation" 67 : 85-95, 2017

41 Zhou, Q., "An active learning radial basis function modeling method based on self-organization maps for simulation-based design problems" 131 : 10-27, 2017

42 Song, H., "Adaptive virtual support vector machine for the reliability analysis of high-dimensional problems" 47 (47): 479-491, 2011

43 Comput. Struct, "Adaptive explicit decision functions for probabilistic design and optimization using support vector machines" 86 : 1904-1917, 2008

44 Yu, S., "Active learning Kriging model with adaptive uniform design for time-dependent reliability analysis" 9 : 1-10, 2021

45 Li, H., "A two-stage failure mode and effect analysis of offshore wind turbines" 162 : 1438-1461, 2020

46 Coffin, L. F., "A study of the effects of cyclic thermal stress in a ductile metal" 76 : 931-950, 1954

47 Du, W., "A reliability-based fatigue design for mechanical components under material variability" 36 (36): 1-15, 2019

48 Yuan, R., "A reliability analysis method of accelerated performance degradation based on Bayesian strategy" 7 : 169047-169054, 2019

49 Li, H., "A real-time inspection and opportunistic maintenance strategies for floating offshore wind turbines" 256 : 111433-, 2022

50 Xiao, N. C., "A new adaptive sequential sampling method to construct surrogate models for efficient reliability analysis" 169 : 330-338, 2018

51 Yuan, R., "A multidisciplinary coupling relationship coordination algorithm using the hierarchical control methods of complex systems and its application in multidisciplinary design optimization" 9 (9): 1-11, 2017

52 Beretta, S., "A log-normal format for failure probability under LCF : Concept, validation and definition of design curve" 82 : 2-11, 2016

53 Du, W., "A general framework for fatigue reliability analysis of a high temperature component" 35 (35): 292-303, 2019

54 Yue, P., "A fatigue damage accumulation model for reliability analysis of engine components under combined cycle loadings" 43 (43): 1880-1892, 2020

55 Li, H., "A failure analysis of floating offshore wind turbines using AHP-FMEA methodology" 234 : 109261-, 2021

56 Li, H., "A developed failure mode and effect analysis for floating offshore wind turbine support structures" 164 : 133-145, 2021

57 Hong, L., "A combined radial basis function and adaptive sequential sampling method for structural reliability analysis" 90 : 375-393, 2020