Prediction method of non-stationary random vibration fatigue reliability of turbine runner blade based on transfer learning

Lui, Fuxiu; Li, Zhaojun; Liang, Minglang; Zhao, Binjian; Ding, Jiang

doi:10.1016/j.ress.2023.109215

Cited by 17 publications

(2 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The inlet measurement rake is affected by the engine vibration environment and unsteady airflow excitation, and the vibration characteristics are quite complex. The broadband random vibration excitation transmitted from the engine casing is the main reason for the vibration of the rake [11][12][13].…”

Section: Introductionmentioning

confidence: 99%

Random Vibration Characteristics and Vibration Suppression of an Aero-engine Inlet Rake Fabricated by Laser Powder Bed Fusion

Niu

2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The inlet rake is generally installed in aero-engine during rig and flight test for flow field pressure and temperature measuring. There are usually complex flow channels and pipelines inside the rake to extract air flow to the sensor. The laser powder bed fusion(L-PBF) technique was applied in rake fabrication recently due to its progressive layer stacking molding procedure. However, the difference of thermoforming method between L-PBF and the traditional casting process leads to the mechanical property disparities of the material. In this work, the determinants of random vibration response of the inlet rake manufactured by L-PBF with GH4169 powder were studied individually. The stiffness and yield property of the material were investigated by the specimen tensile test, which indicates higher elasticity modulus and yield stress comparing to the ones by castling or forging process. The damping ratio of the inlet rake was obtained through stress attenuation characteristics experiment and analysis under stepwise excitation. The stress distribution and resonance margin of the inlet rake under the aero-engine random vibration spectrum were simulated by finite element modal and random vibration analysis. The results showed that the damping ratio of the L-PBF inlet rake is much smaller than engineering recommendations, and the resonance margin is insufficient. Thus, the stress level of the inlet rake was very high, especially in the blade root section, quite close to the yield limit of the material. To solve this problem, the vibration suppression methods of the inlet rake were studied from the perspective of structural design optimization and damping ratio increasing. Through the rational design of the resonance margin and addition of vibration damping structure, the vibration stress of inlet rake was significantly suppressed. As the result, the rake was installed in the inlet during the aero-engine rig test for flow field pressure and temperature measurement successfully.

show abstract

Section: Introductionmentioning

confidence: 99%

Random Vibration Characteristics and Vibration Suppression of an Aero-engine Inlet Rake Fabricated by Laser Powder Bed Fusion

Niu

2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…There are two main methods for RUL prediction: physical model-based methods and data-driven methods [3]. Physical model-based methods mainly constructs a parameterized mathematical model describing the degradation process of systems based on the failure mechanism, and updates the mechanism model parameters based on state monitoring data to achieve the RUL [4], [5]. However, due to the complex and diverse fault mechanism of complex systems, it is difficult to establish an accurate physical model [6].…”

Section: Introductionmentioning

confidence: 99%

A Novel Remaining Useful Life Prediction Approach Combined eXtreme Gradient Boosting and Multi-Quantile Recurrent Neural Network

Yin,

Zhao,

Zhang

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Remaining useful life (RUL) prediction is a key technology to ensure the reliability and safety of high-end equipment. Deep learning is widely used for RUL prediction due to the excellent feature extraction ability and nonlinear fitting ability. Traditional recurrent neural networks adopt recursive strategy, which easily lead to the problems of error accumulation and low stability. On the other hand, most deep learning methods are used for point prediction and cannot quantify uncertainty in the prediction results. Although some probability prediction methods based on deep learning can provide probability prediction results, it require the assumption that the prediction results follow a specific distribution in advance. However, the distribution of most prediction results does not match a suitable distribution function. To solve above problems, a novel RUL prediction approach based on eXtreme gradient boosting (XGBoost) and multiquantile recursive neural network (MQ-RNN) is proposed in this article. Specifically, XGBoost is used to select features closely related to RUL, and the selected features are fed into MQ-RNN to train the RUL prediction model. The advantage of MQ-RNN is that it has non-parametric framework, prediction results can be obtained by multi-quantile regression, which does not require prior assumptions about the distribution of predicted results. Furthermore, the proposed framework is verified by C-MAPSS dataset. Finally, comparative experiments are conducted. The experimental results show that the proposed method maintains good predictive performance in both point estimation and interval estimation.INDEX TERMS Remaining useful life, eXtreme gradient boosting, Multi-quantile recursive neural network, Quantile regression, Forking sequences training scheme.

show abstract

Decision-Making in Structural Health Monitoring and Predictive Maintenance of Wind Turbines

Borissova

2024

International Series in Operations Research &Amp; Management Science

View full text Add to dashboard Cite

Prediction method of non-stationary random vibration fatigue reliability of turbine runner blade based on transfer learning

Cited by 17 publications

References 43 publications

Random Vibration Characteristics and Vibration Suppression of an Aero-engine Inlet Rake Fabricated by Laser Powder Bed Fusion

Random Vibration Characteristics and Vibration Suppression of an Aero-engine Inlet Rake Fabricated by Laser Powder Bed Fusion

A Novel Remaining Useful Life Prediction Approach Combined eXtreme Gradient Boosting and Multi-Quantile Recurrent Neural Network

Decision-Making in Structural Health Monitoring and Predictive Maintenance of Wind Turbines

Contact Info

Product

Resources

About