2k Factorial Experiments in Reliability Analysis for Weibull and log-normal Distributions

Year 2021, Volume: 3 Issue: 2, 115 - 120, 01.05.2021

Berna Yazıcı , Beldine Omondi

https://doi.org/10.47933/ijeir.826795

Abstract

The life times of the components of a product are often analysed in quality control processes. Design of Experiment is mainly used to achieve quality but its’ application to life times are less common. Life times always associate with Reliability. This study integrates experimental design specifically a two-level factorial experimental design and simulation models to determine the important the stress factors subjected to different conditions which significantly effects the life times of a product. The main purpose is to optimize the response by extending the lifetimes of a product. The Factors considered are Temperature and voltage and their magnitude of the power are set at two levels. Simulation design of Weibull and log-normal distributions are used to generate failure times and maximum likelihood (ML) applied in the estimation of parameters.

Keywords

Reliability, Simulation, Weibull Distribution, Log-normal Distribution, Factorial Design

2k Factorial Experiments in Reliability Analysis for Weibull and log-normal Distributions

Abstract

Bir ürünün bileşenlerinin yaşam süreleri genellikle kalite kontrol süreçlerinde analiz edilir. Deney tasarımı, esas olarak kaliteyi elde etmek için kullanılır, ancak yaşam sürelerine uygulanması daha az yaygındır. Yaşam süreleri her zaman Güvenilirlik ile ilişkilendirilir. Bu çalışma, bir ürünün yaşam sürelerini önemli ölçüde etkileyen farklı koşullara maruz kalan önemli stres faktörlerini belirlemek için deneysel tasarımı özellikle iki seviyeli bir faktöryel deneysel tasarım ve simülasyon modellerini birleştirir. Ana amaç, bir ürünün kullanım ömrünü uzatarak tepkiyi optimize etmektir. Dikkate alınan Faktörler Sıcaklık ve gerilimdir ve bunların güç büyüklükleri iki seviyede ayarlanmıştır. Weibull simülasyon tasarımı ve log-normal dağılımları, hata süreleri ve parametrelerin tahmininde uygulanan maksimum olasılık (ML) oluşturmak için kullanılır.

Keywords

Güvenilirlik, Simulasyon, Weibull Dağılımı, Log-normal Dağılımı, Faktöriyel Tasarım

References

• [1] Zhang, C. W., Zhang, T., Xu, D., and Xie, M. (2013). Analyzing highly censored reliability data without exact failure times: an efficient tool for practitioners. Quality Engineering, 25(4), 392–400. http://doi.org/10.1080/08982112.2013.783598.
• [2] Kesler, J. L. K., Freeman, L. J., and Vining, G. G. (2014). A Practitioner’s guide to analyzing reliability experiments with random and subsampling. Quality Engineering, 26(3), 359–369. http://doi.org/10.1080/08982112.2014.887101.
• [3] Beaudry, M. (1978). Performance-reliability measures for computing systems. IEEE Transactions on Computing, Vol. 27.
• [4] Yu, Z., Ren, Z., Tao, J., and Chen, X. (2014). Accelerated testing with multiple failure modes under several temperature conditions, Mathematical Problems in Engineering, Vol.1 http://doi.org/10.1155/2014/839042.
• [5] Huairou, A. M. (2008). Reliability assessment using a likelihood ratio test. International Journal of Performance Engineering, 4, 196-198. http://doi.org/10.23940/ijpe.08.p196.mag.
• [6] Hu, Z. and Du, Xiaoping D. (2013). Lifetime cost optimization with time-dependent reliability, Journal of Engineering Optimization, Vol. 46, Issue 10, p.1389-1410. http://doi.org/10.1080/0305215X.2013.841905.
• [7] Rigdon, S. E., Englert, B. R., Lawson, I. A., Borror, C. M., Montgomery, D. C. and Pan, R. (2012). Experiments for reliability achievement. Quality Engineering, 25(1), 54-72. http://doi.org/10.1080/08982112.2013.733611.
• [8] Khan, M. A. and Islam, H. M. (2012). Bayesian analysis of system availability with half-normal life time. Quality Technology and Quantitative Management, 9(2), 203-209. http://doi.org/10.1080/16843703.2012.11673286.
• [9] Lwo, B. J., Frank, Lin, M. S., Huang, K. H. (2014). TSV reliability model under various stress tests. IEEE 64th Electronic Components and Technology Conference (ECTC), http://doi.org/10.1109/ECTE.2014.6897350.
• [10] Crowder, M. a. (2002). Statistical concepts in reliability. (Vol. 50). Springer.
• [11] Tobias, P. A. and Trindade, D. (2012). Applied reliability. New York: CRC Press.
• [12] Woo, S., and Neal, D. L. O. (2018). Improving the reliability of a domestic refrigerator compressor subjected to repetitive loading, International Compressor Engineering Conference.
• [13] Wu, C. F. J. and Hamada, M. S. (2009). Experiments: Planning, Analysis, and Optimization, 2nd Edition, John Wiley and Sons.
• [14] Wang, G. a. (2017). Bootstrap analysis of designed experiments for reliability improvement with a non-constant scale parameter. Reliability Engineering & System Safety, 160, p.114-121, http://dx.doi.org/10.1016/j.ress.2016.12.006.
• [15] Silvapulle, M. J. (1986). Existence of maximum likelihood estimates in regression models for grouped and ungrouped data. Journal of the Royal Statistical Society, Vol. 48. No.1, p. 100-106.