Fatigue reliability analysis of aeroengine blade-disc systems using physics-informed ensemble learning.

For the fatigue reliability analysis of aeroengine blade-disc systems, the traditional direct integral modelling methods or separate independent modelling methods will lead to low computational efficiency or accuracy. In this work, a physics-informed ensemble learning (PIEL) method is proposed, i.e. firstly, based on the physical characteristics of blade-disc systems, the complex multi-component reliability analysis is split into a series of single-component reliability analyses; moreover, the PIEL model is established by introducing the mapping of multiple constitutive responses and the multi-material physical characteristics into the ensemble learning; finally, the PIEL-based system reliability framework is established by quantifying the failure correlation with the Copula function. The reliability analysis of a typical aeroengine high-pressure turbine blade-disc system is regarded as an example to verify the effectiveness of the proposed method. Compared with the direct Monte Carlo, support vector regression, neural network, ensemble learning and physics-informed neural network, the proposed method exhibits the highest computing accuracy and efficiency, and is validated to be an efficient method for the reliability analysis of blade-disc systems. The current work can provide a novel insight for physics-informed modelling and fatigue reliability analyses. This article is part of the theme issue 'Physics-informed machine learning and its structural integrity applications (Part 1)'.

Decomposed Collaborative Modeling Approach for Probabilistic Fatigue Life Evaluation of Turbine Rotor.

To improve simulation accuracy and efficiency of probabilistic fatigue life evaluation for turbine rotor, a decomposed collaborative modeling approach is presented. In this approach, the intelligent Kriging modeling (IKM) is firstly proposed by combining the Kriging model (KM) and an intelligent algorithm (named as dynamic multi-island genetic algorithm), to tackle the multi-modality issues for obtaining optimal Kriging parameters. Then, the decomposed collaborative IKM (DCIKM) comes up by fusing the IKM into decomposed collaborative (DC) strategy, to address the high-nonlinearity problems for accelerating simulation efficiency. Moreover, the DCIKM-based probabilistic fatigue life evaluation theory is introduced. The probabilistic fatigue life evaluation of turbine rotor is regarded as case study to verify the presented approach; the evaluation results reveal that the probabilistic fatigue life of turbine rotor is 3296 cycles. The plastic strain range ∆εp and fatigue strength coefficient σf' are the main affecting factors to fatigue life, whose effect probability are 28% and 22%, respectively. By comparing with direct Monte Carlo method, KM method, IKM method and DC response surface method, the presented DCIKM is validated to hold high efficiency and accuracy in probabilistic fatigue life evaluation.