Trend Renewal Process模型之最適試驗配置

Optimal Design for Trend Renewal Process Model

饒瑞哲(Rui-Zhe Rao) ； 王義富(Yi-Fu Wang)

《中國統計學報》 57卷3期 (2019/09) Pp. 178-210

摘要

由於現今產品的壽命越來越長，致使高可靠度產品在傳統的壽命試驗下不容易失效，此時我們可透過觀測產品品質特徵值來進行衰變分析。然而在衰變試驗中，如何決定產品之最適樣本數以及最適試驗次數，使得產品壽命估計最爲精準亦爲重要的研究課題。本文首先介紹Lindqvist et al.（2003）所提出的TRP（trend renewal process）模型，在產品觀測間隔時間爲等距測量時，本文採用TRP模型來處理衰變分析，並進一步探討其最適試驗配置議題。最後，我們將以雷射衰變資料及金屬裂縫衰變資料來進行實例分析，探討其衰變試驗之最適樣本數及最適觀測個數。

關鍵字

衰變分析 ； TRP模型 ； 最適試驗配置

並列摘要

For highly reliable products, it is difficult to obtain the product's failure information. Thus, degradation model is usually used to predict the product's lifetime based on the quality characteristic of product. In this article, the trend renewal process (TRP) model is utilized to describe the degradation path. The purpose of this article is to address the optimal design problem to the TRP model. That is, under the constraint of total experimental cost, the decision variables can be obtained by minimizing the asymptotic variance of the estimated 100p-th quantile of lifetime. Finally, two real degradation examples well be carried out to investigate the optimal decision variables.

並列關鍵字

Degradation analysis ； Trend renewal process model ； Optimal design

參考文獻

Bagdonavicius, V. and Nilulin, M. (2001). Estimation in degradation models with explanatory variables. Lifetime Data Analysis, 7: 85-103.

Kummer, E. E. (1837). De integralibus quibusdam definitis et seriebus infinitis. Journal für die reine und angewandte Mathematik (in Latin), 17: 228-242.

Lawless, J. and Crowder, M. (2004). Covariates and random effects in a gamma process model with application to degradation and failure. Lifetime Data Analysis, 10: 213-227.

Lindqvist, B. H., Elvebakk, G. and Heggland, K. (2003). The trend-renewal process for statistical analysis of repairable systems. Technometrics, 45: 31-44.

Liao, C. M. and Tseng, S. T. (2006). Optimal design for step-stress accelerated degradation tests. IEEE Transactions on Reliability, 55: 59-66,