臺灣博碩士論文加值系統

一個新設計的複雜系統為達成研究發展品質目標(或稱為可靠度目標)，必經過數個發展測試階段，而在一個階段測試(Test)裡，都會經由設計檢討(Analysis)及改進(Fix)的作為(簡稱TAAF)，來提昇該產品研究發展階段之壽命可靠度值，這種反覆的TAAF程序就叫「可靠度成長」。透過適當的數學模式配合研發測試數據；我們可以估計出研發原型之現在可靠度水準，同時可作評估研發進度的指標，必要時調整各種可用資源，以期研發目標能如期達成。
本研究針對可靠度成長過程符合Power Law之合理假設，結合可隨時間變動的貝氏預測方法─Kalman Filter，建構一個新的可靠度成長模式，不僅有效的解決了產品持續研改(TAAF)過程中可靠度水準的估計與預測的困難，並可適用於有失效合併修改(Delay Fix)之研發過程。本研究利用模擬的數據與現行最為業界採用的AMSAA模式進行比較，包括敏感度分析說明本模式之穩健性(robustness)及以較少的測試件數即可達到減少預測誤差的優點。

A complex, newly designed system generally undergoes several stages of development testing before it is put into operation. After each stage of testing changes are made to the design with the hope that the new design would lead to a longer period of performance. This procedure is referred to as reliability growth. It is the result of iterative Test Analyze and Fix (TAAF) processes.
For the requirement to manage these TAAF processes effectively, a planned growth curve and a way to determine the continually changing reliability status is necessary. Thus, reliability growth models of the TAAF process have been developed to assist management.
We plan to study a delayed fix case in this research. It is of particular importance in the case of integrated reliability growth. In addition, it may be more economical to make several corrections at once. There may be a long lead-time required to implement design changes. Management may choose not to fix failure modes (causes) identified on prototype system until a production contract is awarded.
Furthermore, for a RDGT (Reliability Growth Development Tests) of a complex system it is usually difficult and expensive to obtain larger testing data. This motivated us to study the reliability growth-testing problem from a Bayesian point of view.
In this research we propose a new methodology for describing reliability growth and projecting future expected reliability of a complex system in a RGDT based on a delayed fixes failure process. The algorithm of our Kalmam Filter model and the simulation for model comparisons provided.

第一章 緒論
第一節 研究動機與背景
第二節 相關文獻回顧
第三節 研究目的及範圍
第二章 可靠度成長理論與失效合併改正模式
第一節 可靠度成長管理
第二節 失效分析
第三節 可靠度成長模式
壹、Duane模式
貳、AMSAA模式
第四節 失效合併改正關係式
第三章 卡門濾波之建立
第一節 卡門濾波方法
第二節 卡門濾波模式建立
第三節 演算程序
第四節 模式驗證
第四章 模式比較
第一節 數據模擬之設計
第二節 比較結果
第三節 敏感度分析
第五章 結論與建議

一、中文部份
1.王宗華，可靠度試驗與評估，1989，中華民國品質管制學會.
2.朱子雄，"可靠度成長技術應用於ISO9001品質系統之研究"，1998義守 學報，pp259-267.
3.朱子雄、魏達延，"從ISO9001之設計管制談產品可靠度成長技術之應用"，KPI邁向21世紀的品質與管理技術應用研討會，1997，pp 200-209.
4.林溪東，"產品研發與使用階段之可靠度成長比較"，品質管制月刊，1995年10月，pp46-50.
5.侯文祥、廖中明，"應用卡門濾波預警養殖池溶氧通量"，台灣漁業學刊，1996，pp17-29.
6.馮正民、游明敏、曾平毅，"台北市房價與卡門濾波理論之應用"，台灣銀行季刊，Vol. 43，No.4，pp218-231.
7.蘇朝墩、唐麗英、柳進明，"結合時間序列與類神經網路構建可靠度成長之預測模式研究"，中國工業工程學刊，Vol. 14，No. 4，1997年，pp419-430.
二、英文部份
1.Bhattacharya, G. K. and Fries, A. and Johnson, R., "Properties of continuous analog estimators for a discrete reliability growth model", IEEE Trans. Reliability, vol. R-38, Aug. 1989, pp373-378.
2.Chu, Tuzz-Shong, A Practical Bayesian Solution to the Problem of Reliability Demonstration (1988 Proceedings of the 2nd Sino Korea Quality Control Symposium)
3.Chu, Tuzz-Shong, Bayes Reliability Growth Model with Delayed Fixes for the Development Testing Program of a Complex System (Ph.D. Dissertation, 1994)
4.Chu, Tuzz-Shong, The Planning of A Reliability Testing Program for An One Shot Device, RE 75 Illumination, and Demonstration (1988 Proceedings Institute of Environmental Sciences)
5.Chu, Tuzz-Shong, Wang, Shi-Gong "Bayes Inferences for a Reliability Growth Models with Delayed Fixes", Proc. Of the 1st R.O.C. Symp. On R&M, 1995, pp357-366.
6.Crow, L. H., "Reliability Analysis for Complex Repairable System", WS Army Materiel System Analysis Activity, Technical Report 138, Dec. 1975, AD-A020296.
7.Duane, J. T., "Learning Cure Approach to Reliability Monitoring", IEEE Trans. Aerospace, vol. 2, 1964, pp563-566.
8.E. Ellis, "Robustness of Reliability-Growth Analysis Techniques", Proceedings Annual Reliability and Maintainability Symposium, 1992, pp303-315.
9.Gate, R., Gibson, G. and McLain, K., "Reliability Growth Prediction", Rome Air Development Center Study, TR86-148, Sep. 1986.
10.Guida, M., Calabria, R. and Pulcini, G., "Bayes Inference for A Non-homogeneous Poisson Process with Power Intensity Law", IEEE Tran. Reliability, vol. R-38, Dec. 1989, pp603-609.
11.M. XIE and M. ZHAO, "Reliability Growth Plot-An Underutilized Tool in Reliability Analysis", Microelectronics and Reliability, Jun 1996, pp797-805.
12.Meinhold and Singpuwalla, "A Kalman Filter Approach to Accelerated Life Test", proceedings of the International school of Physics Theory of Reliability, 1986
13.Meinhold and Singpuwalla, "Understanding the Kalman Filter", The American Statistician, Vol. 37, No. 2, May 1983, pp123-127
14.MIL－HDBK－189, "Reliability Growth Management", US Do, 1981.
15.Morris, S. F. and MacDiarmid, P. R., "Reliability Growth Testing Effectiveness", Proc. of Institute of Environment Sciences, 1988, pp271-282.
16.NAVWEPS 00-65-502, "US Navy Reliability Engineering Handbook", Jun. 1964, pp -4.
17.Robinson, D. and Dietrich, D., "A Nonparametric-Bayes Reliability-Growth Model", IEEE Trans. Reliability, vol. R-5, Dec. 1989, pp591-598.
18.Schafer, R., "Reliability Growth Study", RADC Study Hughes Aircraft Co., RADC TR75-253, Oct. 1975.
19.Smith, A. F. M., "A Bayesian note on reliability growth during a development testing program", IEEE Trans. Reliability, vol. R-26, Dec. 1977, pp346-347.