Probabilistic method for time-varying reliability analysis of structure via variational bayesian neural network

In order to improve the accuracy and calculation efficiency of aeroengine rotor vibration reliability analysis, a time-varying rotor vibration reliability analysis method under the aeroengine operating state is proposed. Aiming at the highly nonlinear and strong coupling of factors affecting the reliability of aeroengine rotor vibration, an intelligent neural network modeling framework (short form-INNMF) is proposed. The proposed method is based on DEA, with QAR information as the analysis data, and four factors including engine working state, fuel/oil working state, aircraft flight state, and external conditions are considered to analyse the rotor vibration reliability. INNMF is based on the artificial neural network (ANN) algorithm through improved particle swarm optimization (PSO) algorithm and Bayesian Regularization (BR) optimization. Through the analysis of the rotor vibration reliability of the B737-800 aircraft during a flight mission from Beijing to Urumqi, the time-varying rotor vibration reliability was obtained, which verified the effectiveness and feasibility of the method. The comparison of INNMF, random forest (RF), and ANN shows that INNMF improves analysis accuracy and calculation efficiency. The proposed method and framework can provide useful references for aeroengine rotor vibration analysis, special treatment, maintenance, and design.

Download Full-text

Risk Simulation Based on Variational Bayesian Neural Network in Integrated Management Systems

10.1109/itqmis53292.2021.9642831 ◽

2021 ◽

Author(s):

Elena V. Dyakonova ◽

Sergei A. Odinokov

Keyword(s):

Neural Network ◽

Integrated Management ◽

Management Systems ◽

Bayesian Neural Network ◽

Variational Bayesian ◽

Simulation Based ◽

Risk Simulation ◽

Integrated Management Systems

Download Full-text

Variational Bayesian Neural Network for Ensemble Flood Forecasting

Water ◽

10.3390/w12102740 ◽

2020 ◽

Vol 12 (10) ◽

pp. 2740

Author(s):

Xiaoyan Zhan ◽

Hui Qin ◽

Yongqi Liu ◽

Liqiang Yao ◽

Wei Xie ◽

...

Keyword(s):

Neural Network ◽

Gaussian Process Regression ◽

Flood Forecasting ◽

Economic Losses ◽

Model Parameters ◽

Probabilistic Forecasting ◽

Bayesian Neural Network ◽

Forecast Uncertainty ◽

Variational Bayesian ◽

Forecasting Models

Disastrous floods are destructive and likely to cause widespread economic losses. An understanding of flood forecasting and its potential forecast uncertainty is essential for water resource managers. Reliable forecasting may provide future streamflow information to assist in an assessment of the benefits of reservoirs and the risk of flood disasters. However, deterministic forecasting models are not able to provide forecast uncertainty information. To quantify the forecast uncertainty, a variational Bayesian neural network (VBNN) model for ensemble flood forecasting is proposed in this study. In VBNN, the posterior distribution is approximated by the variational distribution, which can avoid the heavy computational costs in the traditional Bayesian neural network. To transform the model parameters’ uncertainty into the model output uncertainty, a Monte Carlo sample is applied to give ensemble forecast results. The proposed method is verified by a flood forecasting case study on the upper Yangtze River. A point forecasting model neural network and two probabilistic forecasting models, including hidden Markov Model and Gaussian process regression, are also applied to compare with the proposed model. The experimental results show that the VBNN performs better than other comparable models in terms of both accuracy and reliability. Finally, the result of uncertainty estimation shows that the VBNN can effectively handle heteroscedastic flood streamflow data.

Download Full-text

Creep-Based Reliability Evaluation of Turbine Blade-Tip Clearance with Novel Neural Network Regression

Materials ◽

10.3390/ma12213552 ◽

2019 ◽

Vol 12 (21) ◽

pp. 3552 ◽

Cited By ~ 1

Author(s):

Chun-Yi Zhang ◽

Jing-Shan Wei ◽

Ze Wang ◽

Zhe-Shan Yuan ◽

Cheng-Wei Fei ◽

...

Keyword(s):

Neural Network ◽

High Pressure ◽

Reliability Analysis ◽

Response Surface ◽

Response Surface Method ◽

Tip Clearance ◽

Strong Nonlinearity ◽

Surface Method ◽

Blade Tip ◽

Blade Tip Clearance

To reveal the effect of high-temperature creep on the blade-tip radial running clearance of aeroengine high-pressure turbines, a distributed collaborative generalized regression extremum neural network is proposed by absorbing the heuristic thoughts of distributed collaborative response surface method and the generalized extremum neural network, in order to improve the reliability analysis of blade-tip clearance with creep behavior in terms of modeling precision and simulation efficiency. In this method, the generalized extremum neural network was used to handle the transients by simplifying the response process as one extremum and to address the strong nonlinearity by means of its nonlinear mapping ability. The distributed collaborative response surface method was applied to handle multi-object multi-discipline analysis, by decomposing one “big” model with hyperparameters and high nonlinearity into a series of “small” sub-models with few parameters and low nonlinearity. Based on the developed method, the blade-tip clearance reliability analysis of an aeroengine high-pressure turbine was performed subject to the creep behaviors of structural materials, by considering the randomness of influencing parameters such as gas temperature, rotational speed, material parameters, convective heat transfer coefficient, and so forth. It was found that the reliability degree of the clearance is 0.9909 when the allowable value is 2.2 mm, and the creep deformation of the clearance presents a normal distribution with a mean of 1.9829 mm and a standard deviation of 0.07539 mm. Based on a comparison of the methods, it is demonstrated that the proposed method requires a computing time of 1.201 s and has a computational accuracy of 99.929% over 104 simulations, which are improvements of 70.5% and 1.23%, respectively, relative to the distributed collaborative response surface method. Meanwhile, the high efficiency and high precision of the presented approach become more obvious with the increasing simulations. The efforts of this study provide a promising approach to improve the dynamic reliability analysis of complex structures.

Download Full-text