本文考慮在加速破壞性衰退試驗下，假設產品衰退特徵服從對數常態分配，並與應力和
時間的乘積具對數線性關係，藉以進行統計之可靠度推論。所謂衰退特徵值乃產品判定
失效的主要指標及數據，而破壞性試驗是指衰退特徵之測量數據為一次性測量，即破壞
性測量。在推估上，我們利用貝氏理論與馬可夫鏈蒙地卡羅方法來獲得參數之貝氏估計，進而探討在正常應力條件下產品之平均失效時間與其對應之百分位點、失效時間點及可靠度函數之貝氏統計推論，我們也利用預測分配進行產品失效時間之預測。模擬結果顯示，在資訊準確的先驗分配時，即使樣本數不是很大，產品失效時間之貝氏可靠度推論十分準確。

In this thesis, we consider the accelerated destructive degradation test (ADDT) in which the degradation characteristic is the major indicator of the product failure. We discuss the products whose degradation characteristic is of lognormal distribution with mean being log-linear in the product of the stress level and square root of the observation time. In ADDT, after we measure the degradation characteristics, the products damage. It is called the destructive measure. We use the Bayesian approach with the aid of Markov chain Monte Carlo method to estimate the parameters. Furthermore, we are interested in reliability inferences at the normal stress level, including the mean time to failure, failure time distribution quantiles, failure time piont, and reliability function. We also use the predictive distribution to predict the failure time. From simulation results, when the prior distribution is very informative, the Bayesian approach on ADDT provides accurate reliability inference.

[1] Escobar, L.A., Meeker, W.Q., Kugler, D.L. and Kramer, L.L. (2003). Accelerated destructive degradation tests: data, models, and analysis. Chapter 21 in Mathematical and Statistical Methods in Reliability, B. H. Lindqvist and K. A. Doksum, Editors, River Edge, NJ: World Scientific Publishing Company .

[2] Fan, T.H., Balakrishnan, N. and Chang, C.C. (2009). “The Bayesian approach for highly reliable electro-explosive devices using oneshot device testing.” Journal of Statistical Computation and Simulation, 79, 1143-1154.

[3] Geman, S. and Geman, D. (1984). “Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images.” IEEE Trans. on Pattern Analysis and Machine Intelligence, 6, 721-741.

[4] Gertbsbakh, I.B. and Kordonskiy, K.B. (1969). Models of failure. Springer-Verlag, New York.

[5] Lu, C.J. and Meeker, W.Q. (1993). “Using degradation measures to estimate a time-to-failure distribution.” Technometrics, 35, 161-174.

[6] Lu, C.J., Meeker, W.Q. and Escobar, L.A. (1996). “A comparison of degradation and failure-time analysis methods for estimating a time-to-failure distribution.” Statistica Sinica, 6, 531-546.

[7] Lu, J.C., Park, J. and Yang, Q. (1997). “Statistical inference of a time-to-failure distribution derived from linear degradation data.” Technometrics, 39, 391-400.

[8] Meeker, W.Q. and Escobar, L.A. (1998). Statistical methods for reliability data. John Wiley & Sons, New York.

[9] Nelson, W. (1981). “Analysis of performance degradation data from accelerated
tests.” IEEE Transactions on Reliability, R-30, 149-155.

[10] Oliveira, V.R.B. and Colosimo, E.A. (2004). “Comparison of methods to estimate the time-to-failure distribution in degradation tests.” Quality and Reliability Engineering International, 20, 363-373.

[11] Robinson, M.E. and Crowder, M.J. (2000). “Bayesian methods for a growth-curve degradation model with repeated measures.” Lifetime Data Analysis, 6, 357-374.

[12] Ross, S.M. (2012). Simulation. 5th ed. Academic Press, San Diego.

[13] Shi, Y. and Meeker, W.Q. (2012). “Bayesian methods for accelerated destructive degradation test planning.” IEEE Transactions on Reliability, 61, 245-253.

[14] Tsai, C.C., Tseng, S.T. and Balakrishnan, N. (2011). “Mis-specification analyses of gamma and Wiener degradation processes.” Journal of Statistical Planning and Inference, 141, 3725-3735.

[15] Tseng, S.T. and Peng, C.Y. (2004). “Optimal burn-in policy by using an integrated Wiener process.” IIE Transactions, 36, 1161-1170.

[16] Wang, X. and Xu, D. (2010). “An inverse Gaussian process model for degradation data.” Technometrics, 52, 188-197.

[17] 黃蓓盈(2009). ”加速破壞性衰變測試中分配誤判之穩健實驗規劃.” 國立成功大學統計學研究所碩士論文.

[18] 蘇瓔漪(2012). ”串聯系統元件壽命服從韋伯分配下之定應力破壞性加速壽命試驗分析.” 國立中央大學統計研究所碩士論文.