Calculation of hybrid reliability of turbine disk based on self-evolutionary game model with few shot learning

  • PDF / 1,972,896 Bytes
  • 13 Pages / 595.276 x 790.866 pts Page_size
  • 111 Downloads / 162 Views

DOWNLOAD

REPORT


RESEARCH PAPER

Calculation of hybrid reliability of turbine disk based on self-evolutionary game model with few shot learning Gaoxiang Chen 1 & Jiang Fan 1 & Hongbin Xu 1 & Bo Li 2 Received: 14 February 2020 / Revised: 25 June 2020 / Accepted: 3 September 2020 # Springer-Verlag GmbH Germany, part of Springer Nature 2020

Abstract A turbine disk design based on uncertainty quantifies the risks and improves the structural reliability. An optimized design issue related to turbine disk fatigue life reliability with subjective and objective multi-source uncertainties is a three-layer nested analysis process, where each iterative step requires a double-layer nested analysis containing probability and improbability. A self-evolution game model is proposed to solve the efficiency problem of the optimized design issue under a specific accuracy requirement. In the initial state, only a few sample points are needed to start the game. In the process of its evolution, the most valuable points are searched automatically, and performance functions are identified only at the points where the game diverges. The maximum failure probability is obtained after game consistency is achieved. Accuracy and efficiency are verified with typical numerical examples. The method is adopted to analyze the hybrid low cycle fatigue reliability of a real turbine disk. It is found that, owing to the elimination of an unnecessary artificial distribution hypothesis, the reliability is lower under the same safety life, and the results are more in line with engineering practice. Keywords Hybrid reliability analysis . Few shot learning . Self-evolutionary game . Turbine disk . Low cycle fatigue

1 Introduction In practice, a turbine disk, being a key component of the aero engine, needs to bear high temperatures and mechanical loads. Despite many uncertain factors, such as geometry, material, and load, etc., low cycle fatigue (LCF) is one of the common causes of turbine disk failure. The impact of such factors shows a relatively great dispersion. Life prediction, considering such uncertain factors, is of great importance in quantifying their influence. Some factors can be characterized by an accurate probability model; while others, due to lack of information, absence of experience, or sufficient experimental data, may need to be defined with an interval or convex set model called a hybrid reliability model (HRM) (Elishakoff 1995; Responsible Editor: Palaniappan Ramu * Jiang Fan [email protected] 1

School of Energy and Power Engineering, Beihang University, Beijing 100191, China

2

Department of Mechanical and Aerospace Engineering, Case Western Reserve University, Cleveland, OH 44106, USA

Elishakoff 2017; Ben-Haim 1993). Introducing distribution assumptions without an exact basis leads to wrong results. Thus, establishing and solving an HRM is a great necessity. From a geometric point of view, the minimum distance from the origin point to the limit state surface in a standard normal space is regarded as the reliability index βL (Hasofer and Lind 19