A Novel Reliability Analysis Approach With Collaborative Active Learning Strategy-Based Augmented RBF Metamodel

Abstract

Metamodels in lieu of time-demanding performance functions can accelerate the reliability analysis effectively. In this paper, we propose an efficient collaborative active learning strategy-based augmented radial basis function metamodel (CAL-ARBF), for reliability analysis with implicit and nonlinear performance functions. For generating the suitable samples, a CAL function is first designed to constrain the new samples being generated in sensitivity region, near limit state surface and keep certain distances mutually. Then by adjusting the adjustment coefficient of CAL function, the CAL-ARBF is mathematically modeled and the corresponding reliability analysis theory is developed. The effectiveness of the proposed approach is validated by four numerical samples, including global nonlinear problem, local nonlinear problem, nonlinear oscillator and truss structure. Through comparison of several state-of-the-art methods, the proposed CAL-ARBF is demonstrated to possess the computational advantages in efficiency and accuracy for reliability analysis.

Recent advances in reliability analysis of aeroengine rotor system: a review

“…Improved Kriging function (i.e. effective expected feasibility function (EFF) (Bichon et al, 2012), learning function U (Zheng et al, 2017) and learning function H (Lv et al, 2015)), the best-expected sample points are precisely selected and sequentially added into the sample set in iterative process, the active learning function-based surrogate model can reduce the required sample number and improve the computational efficiency, whose basic thought is drawn in Figure 7 ( Wei et al, 2020). Combining the human-like inference ability of fuzzy logic system with the flexible structure of ANN model, a high-precision fuzzy neural network model method is proposed (Song et al, 2018) to address the complex multiple fluid-structure interaction calculation issues, as shown in Figure 8; By combining wavelet basis function with ANN structure, a wavelet neural network surrogate model method is proposed (Song et al, 2019b) to accomplish the fatigue reliability estimation, as shown in Figure 9; For the reliability analysis problem of complex time-varying environmental load, large time-varying characteristics and high instability of output response in time domain, an extreme response surface model method is proposed (Song et al, 2017) to transform the time-varying Reliability analysis of aeroengine rotor system process to output variables, as shown in Figure 10.…”

Adaptive Local Maximum-Entropy Surrogate Model and Its Application to Turbine Disk Reliability Analysis

“…If and only if a Voronoi diagram meets the following conditions (15), it is called the gravity center Voronoi diagram.…”

“…When the performance functions are implicit, the performance must be obtained through experiments or numerical simulations. Obviously, the MC method is impractical for numerous costly experiments, or time-consuming numerical simulations, such as 3-D Finite Element (FE) simulations [14,15], which are abundant in the design and manufacturing of aero-engines. Therefore, a surrogate model is proposed to replace these expensive experiments or simulations, which utilizes approximate methods to establish an approximate function that can represent the real function.…”

DNN-Based Surrogate Modeling-Based Feasible Performance Reliability Design Methodology for Aircraft Engine

“…Probabilistic design method is proved to be an effective method to solve the uncertainty-based design problem. Lots of relevant research is devoted to probabilistic design methods in the robustness and reliability of aerospace engineering and civil engineering [6][7][8][9]. These research works wisely utilized the probabilistic design method to settle the quantitative analysis of uncertainty.…”