Adaptive vectorial surrogate modeling framework for multi-objective reliability estimation

Lu, Cheng; Teng, Da; Chen, Jun-Yu; Fei, Chengwei; Keshtegar, Behrooz

doi:10.1016/j.ress.2023.109148

Cited by 24 publications

(3 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the work condition, inlet pressure p in , outlet pressure p out , angular speed w, inlet velocity v, and density ρ are considered as the input variables of turbine blisk reliability analysis, while the blisk strain is regarded as output response. The time domain [0, 215 s] is simplified as the flight cycle of all stages for the deterministic and reliability analysis [35,36]. It is assumed that inlet pressure and outlet pressure are 2 × 10 6 Pa and 5.88 × 10 5 Pa, respectively [37].…”

Section: Deterministic Analysis Of Turbine Bliskmentioning

confidence: 99%

Operational Reliability Analysis of Turbine Blisk Using an Enhanced Moving Neural Network Framework

Liang,

Sun,

Sun

et al. 2024

Aerospace

Self Cite

View full text Add to dashboard Cite

As one of the key components of an aeroengine, turbine blisk endures complex coupling loads under a harsh operational environment so that the reliability of turbine blisk directly influences the safe operation of aeroengine. It is urgent to precisely perform the reliability estimation of a complex blisk structure. To address this issue, an enhanced Moving Neural Network Framework (MNNF) is proposed by integrating compact support region theory, improve sooty tern optimization algorithm (ISTOA), and Bayesian regularization strategy into artificial neural network. The compact support region theory is applied to select the efficient samples for modeling from the training samples set, the ISTOA is to determine the optimal compact support region, and Bayesian regularization thought is utilized to improve the generalization ability of neural network model. The operational reliability assessment of aeroengine blisk is performed with the consideration of transient loads to verify the proposed MNNF method. It is shown that the reliability degree of turbine blisk stain is 0.9984 when the allowable value is 5.2862 × 10−3 m. In line with the comparison of methods, the developed MNNF approach has 0.99738 in root means square error, 3.1634 × 10−4 m in goodness of fit, 0.423 s in modeling time, 99.99% in simulation precision, and 0.496 s in simulation time under 10,000 simulations, which are superior to all other methods (i.e., 99.96%, 99.91%, 99.93%, 99.97%, and 99.97% in simulation precision and 16.27%, 4.82%, 30.07%, 39.87%, and 23.59% in simulation efficiency, for the response surface method (RSM), Kriging, support vector machine (SVM), back propagation-artificial neural network (BP-NN), and BP-NN based on particle swarm optimization (BP-PSO) methods, respectively). It is demonstrated that the MNNF method holds excellent modeling and simulation performances. The efforts of this study provide promising tools and insights into the reliability design of complex structures, and enrich and develop reliability theory.

show abstract

Section: Deterministic Analysis Of Turbine Bliskmentioning

confidence: 99%

Operational Reliability Analysis of Turbine Blisk Using an Enhanced Moving Neural Network Framework

Liang,

Sun,

Sun

et al. 2024

Aerospace

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, since the initial weights and thresholds are randomly generated, the gradient descent method tends to converge to a local optimal solution, resulting in insufficient training of the network. This will lead to problems of insufficient fitting accuracy and low computational efficiency of the surrogate model [22][23][24][25][26]. Therefore, this paper introduces Tent map and DBO algorithm on the basis of BP neural network to optimize the weights and thresholds of the initialization population.…”

Section: Basic Theorymentioning

confidence: 99%

Fault logic and data-driven model for operation reliability analysis of the flap deflection angle

Liu,

Feng,

Teng

et al. 2023

Phil. Trans. R. Soc. A.

Self Cite

View full text Add to dashboard Cite

To effectively perform the reliability analysis of the flap deflection angle, the reliability analysis framework is developed by introducing fault logic and a data-driven model. Herein, the fault logic analysis is used to study the fault mechanism and filter out the characteristic fault parameters that can be used to collect input data for data-driven modelling; the data-driven modelling is employed to establish a reliability analysis model with a small amount of input data. Under this proposed framework, the improved dung beetle optimization algorithm for back propagation (IDBO-BP) method is developed to perform the reliability modelling of the flap deflection angle. To validate the effectiveness of the proposed framework, we study the fault logic of flap symmetry and establish a surrogate model of flap deflection based on the fault parameters and the IDBO-BP algorithm. According to the predicted results of the flap deflection angle, the reliability model based on the fault mechanism can reflect the actual flap motion. At the same time, the proposed IDBO-BP algorithm has excellent modelling and simulation property by comparing with other optimization algorithms. Thus, the efforts of this study provide a new solution to the problem of reliable analysis with uncertain fault parameters. This article is part of the theme issue 'Physics-informed machine learning and its structural integrity applications (Part 1)'.

show abstract

“…However, fewer studies have been conducted on the temperature and vibration integrated test profiles, mostly extended traditional methods. with the current increase in the reliability of various types of equipment [26,27], it is no longer able to meet the current demand for reliability enhancement testing of products.…”

Section: Introductionmentioning

confidence: 99%

Study on the Design of Thermal Vibration Integrated Reliability Enhancement test Profile based on Multi-stress Failure Excitation Simulation

Xue,

XU,

Feng

et al. 2023

Preprint

View full text Add to dashboard Cite

The current reliability enhanced test profiles are inefficient and costly, an integrated temperature and vibration reliability enhancement test profile design method based on multi-stress failure excitation simulation (MSS-RET) for typical ballistic devices is presented in this paper. First, the fault logic analysis is conducted by combining the product fault tree and product structural characteristics, and establishment of a integrated test profile design framework, to improve the determination of profile elements of the guidelines. using multi-stress finite element deterministic analysis joint failure physical model of the failure prediction method, obtain a vibration termination stress valuation, starting stress, and other profile elements, achieved the optimization of the test accuracy; Combined with relevant standards, clarify the temperature stabilization time. Through the principle of thermal stress generation, combined with finite element simulation data analysis, specify the vibration excitation loading time, optimize fault excitation intensity, improve the low efficiency and high cost of the reinforcement test. The MSS-RET is validated by taking the design of a comprehensive temperature and vibration test profile of a fuze detection module as an example, the results shows that the obtained test profile can reduce the test error by up to 44% compared with the traditional method.

show abstract

Adaptive vectorial surrogate modeling framework for multi-objective reliability estimation

Cited by 24 publications

References 43 publications

Operational Reliability Analysis of Turbine Blisk Using an Enhanced Moving Neural Network Framework

Operational Reliability Analysis of Turbine Blisk Using an Enhanced Moving Neural Network Framework

Fault logic and data-driven model for operation reliability analysis of the flap deflection angle

Study on the Design of Thermal Vibration Integrated Reliability Enhancement test Profile based on Multi-stress Failure Excitation Simulation

Contact Info

Product

Resources

About