Advertisement

Assessment of Reliability in Accelerated Degradation Testing with Initial Status Incorporated

  • Chengjie Wang
  • Qingpei HuEmail author
  • Dan Yu
Chapter
Part of the Communications in Computer and Information Science book series (CCIS, volume 1102)

Abstract

Accelerated Degradation Test (ADT) provides effective information for reliability assessment of performance characteristic of long-life and high-reliability products. Existing typical models and analysis usually assume that the products under test are of high consistency level during the manufacturing process, which implies that the individual differences of the initial performance of the products can be ignored. However, this may not be the case, and the initial performance of the test units may have great impact on the subsequent degradation rate. Both positively related and negatively related are possible. This phenomenon can be observed in many different examples, such as the performance of inkjet printer heads. It means that reliability-related information can be obtained before accelerated degradation test. The study considers the impact of initial performance on the reliability assessment. Based on the existing typical accelerated degradation test model and analysis process, this paper introduces the initial information of the products to carry out reliability assessment and test plan. The asymptotic variance of a lifetime quantile at normal use conditions is considered to obtain the optimum test plan. Results show that the initial performance of the test units can be made use of to improve the accuracy of estimators. The impact of fisher information has been taken into account.

Keywords

Accelerated degradation test Reliability assessment Random initial degradation Fisher information Asymptotic variance Test plan 

Notes

Acknowledgements

The authors are honored to get invitation for contributing a book chapter to celebrate the 80th birthday of Professor Jinhua Cao. The authors are also thankful for the reviewers’ comments and suggestions.

References

  1. 1.
    Chow, S.C.: Advanced Linear Models: Theory and Applications. Routledge, New York (2018)Google Scholar
  2. 2.
    Kiefer, J.: Optimum experimental designs. J. Roy. Stat. Soc.: Ser. B (Methodol.) 21(2), 272–304 (1959)MathSciNetzbMATHGoogle Scholar
  3. 3.
    Klein, A., Mélard, G., Zahaf, T.: Construction of the exact fisher information matrix of gaussian time series models by means of matrix differential rules. Linear Algebra Appl. 321(1), 209–232 (2000)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Li, L.: Design of accelerated degradation test. The university of Chinese Academy of Sciences (2013)Google Scholar
  5. 5.
    Lu, J.: Degradation processes and related reliability models. McGill University Montreal, Canada (1995)Google Scholar
  6. 6.
    Lu, J.C., Park, J., Yang, Q.: Statistical inference of a time-to-failure distribution derived from linear degradation data. Technometrics 39(4), 391–400 (1997)CrossRefGoogle Scholar
  7. 7.
    Marseguerra, M., Zio, E., Cipollone, M.: Designing optimal degradation tests via multi-objective genetic algorithms. Reliab. Eng. Syst. Saf. 79(1), 87–94 (2003)CrossRefGoogle Scholar
  8. 8.
    Meeker, W.Q., Escobar, L.A.: Statistical Methods for Reliability Data. Wiley, New York (2014)Google Scholar
  9. 9.
    Sheng-Tsaing, T., Hong-Fwu, Y.: A termination rule for degradation experiments. IEEE Trans. Reliab. 46(1), 130–133 (1997)CrossRefGoogle Scholar
  10. 10.
    Wang, X., Xu, D.: An inverse gaussian process model for degradation data. Technometrics 52(2), 188–197 (2010)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Weaver, B.P., Meeker, W.Q., Escobar, L.A., Wendelberger, J.: Methods for planning repeated measures degradation studies. Technometrics 55(2), 122–134 (2013)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Whitmore, G.A.: Estimation of wiener diffusion parameters using process measurements subject to error. In: Jewell, N.P., Kimber, A.C., Lee, M.L.T., Whitmore, G.A. (eds.) Lifetime Data: Models in Reliability and Survival Analysis, pp. 363–369. Springer, Heidelberg (1996).  https://doi.org/10.1007/978-1-4757-5654-8_47CrossRefGoogle Scholar
  13. 13.
    Wu, S.J., Shao, J.: Reliability analysis using the least squares method in nonlinear mixed-effect degradation models. Stat. Sin. 9(3), 855–877 (1999)MathSciNetzbMATHGoogle Scholar
  14. 14.
    Ye, Z.S., Hu, Q., Yu, D.: Strategic allocation of test units in an accelerated degradation test plan. J. Qual. Technol. 51(1), 64–80 (2019)CrossRefGoogle Scholar
  15. 15.
    Yu, H.F., Tseng, S.T.: Designing a degradation experiment. Naval Res. Logistics (NRL) 46(6), 689–706 (1999)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Academy of Mathematics and Systems ScienceChinese Academy of SciencesBeijingChina

Personalised recommendations