Probabilistic LCF life assessment for turbine discs with DC strategy-based wavelet neural network regression
Source abstract
Abstract
Abstract Low cycle fatigue (LCF) seriously affects the performance and reliability of turbomachinery like aeroengine. Probabilistic LCF assessment can effectively quantify risk and improve components reliability. To improve the accuracy and efficiency of probabilistic LCF life assessment, a distributed collaborative (DC)-wavelet neural network regression (WNNR) (called as DC-WNNR) surrogate model is developed by proposing Bayesian regularization-Quasi Newton (BR-QN) error control technique. The mathematical model of DC-WNNR is structured and the corresponding probabilistic framework of LCF life assessment is introduced. The probabilistic LCF life assessment for turbine discs is regarded as one case to evaluate the proposed method with respect to various uncertainties such as material property, load fluctuation and model variability. The analysis results reveal that the reliability-based LCF life of a turbine disc under reliability 99.87% is 6 058 cycles; fatigue strength coefficient σf′ and strain range Δɛt play a leading role on the fatigue life failure since their effect probabilities of 45% and 36%, respectively. The comparison of methods (Monte Carlo method, WNNR, DC response surface method and DC-WNNR) shows that the DC-WNNR holds high efficiency and accuracy for the probabilistic LCF assessment. The present efforts offer an effective way for predicting and evaluating structural LCF failure from a probabilistic perspective.
Source: openaire · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Probabilistic and Robust Engineering Design · Fatigue and fracture mechanics · High Temperature Alloys and Creep
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (52)
Show source-provided references
1. Structural integrity assessment of turbine discs in presence of potential defects: probabilistic analysis and implementation10.1111/ffe.12325 ↗
2. A study on thermo mechanical fatigue life prediction of Ni-base superalloy10.1016/j.ijfatigue.2013.10.011 ↗
3. Local maximum-entropy based surrogate model and its application to structural reliability analysis10.1007/s00158-017-1760-y ↗
4. Probabilistic low cycle fatigue life prediction using an energy-based damage parameter and accounting for model uncertainty10.1177/1056789511429836 ↗
5. High temperature low cycle fatigue deformation behaviour of forged IN 718 superalloy turbine disc10.1016/j.msea.2012.12.069 ↗
6. Numerical modelling of the fatigue crack shape evolution in a shot-peened steam turbine material10.1016/j.ijfatigue.2017.07.017 ↗
7. Zone-based reliability analysis on fatigue life of GH720Li turbine disk concerning uncertainty quantification10.1016/j.ast.2017.08.011 ↗
8. A Bayesian analysis of fatigue data10.1016/j.strusafe.2009.08.001 ↗
9. The framework for a strain-based fatigue reliability analysis10.1016/j.ijfatigue.2007.04.006 ↗
10. A fatigue reliability analysis method including super long life regime10.1016/j.ijfatigue.2010.11.011 ↗
11. Deterministic and probabilistic creep-fatigue-oxidation crack growth modeling10.1016/j.probengmech.2013.03.004 ↗
12. A probabilistic-based airframe integrity management model10.1016/j.ress.2008.10.010 ↗
13. Uncertainty quantification and model validation of fatigue crack growth prediction10.1016/j.engfracmech.2011.02.017 ↗
14. Stochastic updating of probabilistic life models for rotorcraft dynamic components10.4050/JAHS.54.012009 ↗
15. Creep-fatigue behavior of turbine disc of superalloy GH720Li at 650 °C and probabilistic creep-fatigue modeling10.1016/j.msea.2016.05.117 ↗
16. Probabilistic framework for multiaxial LCF assessment under material variability10.1016/j.ijfatigue.2017.06.019 ↗
17. Probabilistic physics of failure-based framework for fatigue life prediction of aircraft gas turbine discs under uncertainty10.1016/j.ress.2015.10.002 ↗
18. A new tool for design and certification of aircraft turbine rotors10.1115/1.1622409 ↗
19. Probabilistic methods for design assessment of reliability with inspection10.2514/2.1730 ↗
20. Application of probabilistic fracture mechanics to prognosis of aircraft engine components10.2514/1.13142 ↗
21. Probabilistic fatigue life prediction using AFGROW and accounting for material variability10.1016/j.ijfatigue.2009.12.001 ↗
22. A new approach to the investigation of load interaction effects and its application in residual fatigue life prediction10.1177/1056789515620910 ↗
23. Adaptation of fast Fourier transformations to estimate structural failure probability10.1016/S0168-874X(02)00104-X ↗
24. Inference of equivalent initial flaw size under multiple sources of uncertainty10.1016/j.ijfatigue.2010.06.008 ↗
25. Dynamic neural network method-based improved PSO and BR algorithms for transient probabilistic analysis of flexible mechanism10.1016/j.aei.2017.05.005 ↗
26. Latin hypercube sampling and the propagation of uncertainty in analyses of complex systems10.1016/S0951-8320(03)00058-9 ↗
27. Extremum response surface method for casing radial deformation probabilistic analysis10.2514/1.I010045 ↗
28. Efficient structural reliability analysis method based on advanced Kriging model10.1016/j.apm.2014.07.008 ↗
29. Novel adaptive surrogate model based on LRPIM for probabilistic analysis of turbine disc10.1016/j.ast.2017.07.044 ↗
30. Probabilistic approach to corrosion risk due to carbonation via an adaptive response surface method10.1016/j.probengmech.2005.11.001 ↗
31. Multi-objective reliability-based design optimization approach of complex structure with multi-failure modes10.1016/j.ast.2017.01.018 ↗
32. Distributed collaborative probabilistic design for turbine blade-tip radial running clearance using support vector machine of regression10.1016/j.ymssp.2014.04.013 ↗
33. Dynamic probabilistic design approach of high-pressure turbine blade-tip radial running clearance10.1007/s11071-016-2883-1 ↗
34. Approximate reliability function based on wavelet Latin hypercube sampling and bee recurrent neural network10.1109/TR.2011.2134190 ↗
35. Modeling of throughput in production lines using response surface methodology and artificial neural networks
36. Multi-kernel neural networks for nonlinear unsteady aerodynamic reduced-order modeling10.1016/j.ast.2017.04.017 ↗
37. A novel algorithm for wavelet neural networks with application to enhanced PID controller design10.1016/j.neucom.2015.01.015 ↗
38. A wavelet support vector machine-based neural network metamodel for structural reliability assessment10.1111/mice.12257 ↗
39. Training the random neural network using quasi-Newton methods10.1016/S0377-2217(99)00482-8 ↗
40. On the global convergence of the BFGS method or nonconvex unconstrained optimization problems10.1137/S1052623499354242 ↗
41. Comparing the performance of neural networks developed by using Levenberg-Marquardt and Quasi-Newton with the gradient descent algorithm for modelling a multiple response grinding process10.1016/j.eswa.2011.08.087 ↗
42. Preventing over-fitting during model selection via Bayesian regularization of the hyper-parameters
43. Bayesian reliability analysis for fuzzy lifetime data10.1016/j.fss.2005.11.009 ↗
44. Bayesian regularization neural network based on artificial intelligence optimization10.1080/00207543.2016.1237785 ↗
45. Distributed collaborative response surface method for mechanical dynamic assembly reliability design10.3901/CJME.2013.06.1160 ↗
46. Transient probabilistic analysis for turbine blade-tip radial clearance with multi-component and multi-physics fields based on DCERSM10.1016/j.ast.2015.11.025 ↗
47. Novel method and model for dynamic reliability optimal design of turbine blade deformation10.1016/j.ast.2014.07.003 ↗
48. Reliability-based low-cycle fatigue damage analysis for turbine blade with thermo-structural interaction10.1016/j.ast.2015.12.017 ↗
49. Substructure-based distributed collaborative probabilistic analysis method for low-cycle fatigue damage assessment of turbine blade-disk10.1016/j.ast.2018.06.023 ↗
50. Distributed collaborative probabilistic design of multi-failure structure with fluid-structure interaction using fuzzy neural network of regression10.1016/j.ymssp.2017.09.039 ↗
51. The convergence of conjugate gradient method with nonmonotone line search
52. Academic committee of the superalloys, China Superalloys Handbook. Beijing: China Zhijian Publishing House & Standards Press of China; 2012 (Chinese).