DOI QR코드

DOI QR Code

Degradation Quantification Method and Degradation and Creep Life Prediction Method for Nickel-Based Superalloys Based on Bayesian Inference

베이지안 추론 기반 니켈기 초합금의 열화도 정량화 방법과 열화도 및 크리프 수명 예측의 방법

  • Junsang, Yu (Data Analytics Team, Doosan Enerbility) ;
  • Hayoung, Oh (College of Computing and Informatics, Sungkyunkwan University)
  • Received : 2022.11.20
  • Accepted : 2022.12.02
  • Published : 2023.01.31

Abstract

The purpose of this study is to determine the artificial intelligence-based degradation index from the image of the cross-section of the microstructure taken with a scanning electron microscope of the specimen obtained by the creep test of DA-5161 SX, a nickel-based superalloy used as a material for high-temperature parts. It proposes a new method of quantification and proposes a model that predicts degradation based on Bayesian inference without destroying components of high-temperature parts of operating equipment and a creep life prediction model that predicts Larson-Miller Parameter (LMP). It is proposed that the new degradation indexing method that infers a consistent representative value from a small amount of images based on the geometrical characteristics of the gamma prime phase, a nickel-base superalloy microstructure, and the prediction method of degradation index and LMP with information on the environmental conditions of the material without destroying high-temperature parts.

본 연구의 목적은 고온부품의 소재로 사용하는 니켈기 초합금인 DA-5161 SX에 대한 크리프시험으로 얻은 시편 의 주사전자현미경으로 촬영한 미세조직 단면의 이미지로부터 인공지능 기반 열화인덱스(Degradation Index)로 정 량화 하는 새로운 방법을 제시하고 운전 중인 기기의 고온부품의 구성품을 파괴하지 않고 베이지안 추론 기반 열화 도를 예측하는 모델과, Larson-Miller Parameter(LMP)를 예측하여 크리프 수명 예측 모델을 제안하는 것이다. 니켈 기 초합금 미세조직인 감마프라임 상(γ')의 기하학적 특징 및 베이지안 추론 기반으로 소량의 이미지로 일관성 있는 대푯값을 추론하는 새로운 열화인덱스 방법과 고온부품을 파괴하지 않고 소재의 환경조건 정보만으로 열화인덱스 와 LMP를 예측할 수 있는 방법을 제안한다.

Keywords

Acknowledgement

This work was supported by the Doosan Enerbility and the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT) (No. NRF-2022R1F1A1074696).

References

  1. A. O'Hagan, "Bayesian statistics: principles and benefits," Frontis, pp. 44, May. 2004.
  2. B. Rezaeianjouybari and Y. Shang, "Deep learning for prognostics and health management: State of the art, challenges, and opportunities," Measurement, vol. 163, pp. 107929, Oct. 2020. DOI: 10.1016/j.measurement.2020.107929.
  3. G. Marahleh, A. R. I. Kheder, and H. F. Hamad, "Creep-life prediction of service-exposed turbine blades," Materials Science and Engineering, vol. 42, no. 4, pp. 476-481, Jul. 2006. DOI: 10.1007/s11003-006-0103-8.
  4. F. R. Larson and J. Miller, "Closure to "Discussions of 'A Time-Temperature Relationship for Rupture and Creep Stresses," Transactions of the American Society of Mechanical Engineers, vol. 74, no. 5, pp. 774-775, Jul. 1952. DOI: 10.1115/1.4015915.
  5. American Society for Testing and Materials std. E139-11, Standard test methods for conducting creep, creep-rupture, and stress-rupture tests of metallic materials, ASTM International, 2006.
  6. R. L. Graham and F. F. Yao, "Finding the convex hull of a simple polygon," Journal of Algorithms, vol. 4, no. 4, pp. 324-331, Dec. 1983. DOI: 10.1016/0196-6774(83)90013-5.
  7. University of Guelph CIS 6320 (2001). Shape analysis and measurement [Internet]. Available: http://www.cyto.purdue.edu/cdroms/micro2/content/education/wirth10.pdf.
  8. Dept. of Brain and Cognitive Sciences, Univ. of Rochester, Rochester, NY(2012). Bayesian Inference: Metropolis-Hastings Sampling [Internet]. Available: https://www2.bcs.rochester.edu/sites/jacobslab/cheat_sheet/MetropolisHastingsSampling.pdf.
  9. E. Schulz, M. Speekenbrink, and A. Krause, "A tutorial on Gaussian process regression: Modelling, exploring, and exploiting functions," Journal of Mathematical Psychology, vol. 85, pp. 1-16, Aug. 2018. DOI: 10.1016/j.jmp.2018.03.001.
  10. M. Ebden. (2015, August), Gaussian processes: A quick introduction. arXiv preprint arXiv:1505.02965, [Online]. Available: https://arxiv.org/pdf/1505.02965.pdf.