隨著消費者對高品質商品的需求不斷提升，製造商愈加重視產品在全生命週期中的可靠度表現。為了降低潛在失效風險並縮短檢測時間，製造商常透過預燒試驗來觀測產品在早期階段的行為，以便進行壽命與可靠度的評估。在此過程中，產品的性能往往可透過一組或多組品質特徵加以量化，例如電性參數、材料強度或功能輸出等，而這些品質特徵隨時間的衰變資料能夠反映產品的衰退過程，並提供建立可靠的衰變模型之依據。然而，品質特徵的衰退通常受到隨機波動影響，不同個體間也可能存在顯著差異，若僅依靠傳統壽命試驗結果，往往難以於早期準確區分高可靠與低可靠產品。過去的研究多假設衰退過程具有同質變異數，然而實際上品質特徵往往呈現異質變異，使不同個體的衰退速率與變異程度存在顯著差異。忽略此一特性可能導致壽命推估偏誤，降低可靠度判別的精確度。本研究採用Wiener過程作為隨機模型，以刻畫產品衰退路徑的趨勢與隨機變異特性，並結合判別分析方法建立基於衰退資訊的分類準則，用以區分不同品質水準之產品。為提升分類準確性，分類邊界透過最小化期望判別錯誤成本的方法進行推導。該方法旨在於產品早期階段進行分類決策，提供具統計基礎的判別依據。研究結果可作為後續產品良率篩選與製程改善的參考，對提升可靠度判別精確性具有潛在實務應用價值。

This study develops a burn-in classification framework for distinguishing products with different reliability levels under heterogeneous degradation behaviors. In practical manufacturing environments, degradation processes often exhibit both trend and variability differences across products, which makes early-stage reliability classification challenging. To address this issue, the Wiener process is adopted to model degradation dynamics. Two key degradation features, including degradation path values and incremental variance, are extracted to characterize product behavior. A discriminant analysis approach is then developed to classify products into normal and weak categories. The optimal classification boundary is derived by minimizing the expected cost of misclassification (ECM), incorporating both prior probabilities and misclassification costs. Numerical results show that the proposed method improves classification performance compared with Huang (2025), which employs an ECM-based decision rule with jointly optimized thresholds for both degradation features. The proposed framework provides a systematic and practical approach for early reliability assessment and can be applied to burn-in testing, yield screening, and manufacturing quality improvement.

蕭裕翰（2024）。應用判別分析探討高可靠度產品之預燒試驗分類決策。﹝碩士論文。國立成功大學﹞臺灣博碩士論文知識加值系統。https://hdl.handle.net/11296/92rd63。
黃彥凱（2025）。考量Wiener衰退過程路徑值與增量變異差異之預燒試驗。﹝碩士論文。國立成功大學﹞臺灣博碩士論文知識加值系統。https://hdl.handle.net/11296/8ym35h。
Chen, Y., Yuan, T., Bae, S. J., & Kuo, Y. (2021). Two-level differential burn-in policy for spatially heterogeneous defect units in semiconductor manufacturing. Computers & Industrial Engineering, 162, 107768.
Finkelstein, M., Cha, J. H., & Langston, A. (2023). Improving classical optimal age-replacement policies for degrading items. Reliability Engineering & System Safety, 236, 109303.
Hove, H., & Mlambo, F. (2022). On Wiener Process Degradation Model for Product Reliability Assessment: A Simulation Study. Modelling and Simulation in Engineering, 2022(1), 7079532.
Huang, J., Golubović, D. S., Koh, S., Yang, D., Li, X., Fan, X., & Zhang, G. Q. (2015). Degradation modeling of mid-power white-light LEDs by using Wiener process. Optics Express, 23(15), A966–A978.
Jensen, F., & Petersen, N. E. (1982). Burn-In: An Engineering Approach to the Design and Analysis of Burn-In Procedures. Wiley.
Johnson, R. A., & Wichern, D. W. (2007). Applied Multivariate Statistical Analysis. Pearson Prentice Hall.
Leemis, L. M., & Beneke, M. (1990). Burn-In Models and Methods: A Review. IIE Transactions, 22(2), 172–180.
Meeker, W. Q., & Escobar, L. A. (1998). Statistical Methods for Reliability Data. Wiley.
Pan, Z., & Balakrishnan, N. (2011). Reliability modeling of degradation of products with multiple performance characteristics based on gamma processes. Reliability Engineering & System Safety, 96(8), 949–957.
Suhir, E. (2022). Predictive modeling sheds useful light on burn-in testing (BIT): Brief review and recent extension. Microelectronics Reliability, 128, 114371.
Tsai, C. C., Tseng, S. T., & Balakrishnan, N. (2011). Optimal Burn-In Policy for Highly Reliable Products Using Gamma Degradation Process. IEEE Transactions on Reliability, 60(1), 234–245.
Tseng, S.-T., Tang, J., & Ku, I.-H. (2003). Determination of burn-in parameters and residual life for highly reliable products. Naval Research Logistics (NRL), 50(1), 1–14.
Wang, H., Zhao, Y., & Ma, X. (2018). Mechanism Equivalence in Designing Optimum Step-Stress Accelerated Degradation Test Plan Under Wiener Process. IEEE Access, 6, 4440–4451.
Wang, Z., Zhai, Q., & Chen, P. (2021). Degradation modeling considering unit-to-unit heterogeneity-A general model and comparative study. Reliability Engineering & System Safety, 216, 107897.
Xiao, M., Zhang, Y., Li, Y., & Wang, W. (2020). Degradation Modeling Based on Wiener Process Considering Multi-Source Heterogeneity. IEEE Access, 8, 160982–160994.
Ye, Z.-S., & Chen, N. (2014). The Inverse Gaussian Process as a Degradation Model. Technometrics, 56(3), 302–311.
Ye, Z.-S., Chen, N., & Shen, Y. (2015). A new class of Wiener process models for degradation analysis. Reliability Engineering & System Safety, 139, 58–67.
Ye, Z.-S., & Xie, M. (2015). Stochastic modelling and analysis of degradation for highly reliable products. Applied Stochastic Models in Business and Industry, 31(1), 16–32.
Zhai, Q., Chen, P., Hong, L., & Shen, L. (2018). A random-effects Wiener degradation model based on accelerated failure time. Reliability Engineering & System Safety, 180, 94–103.
Zhai, Q., Li, Y., & Chen, P. (2025). Modeling product degradation with heterogeneity: A general random-effects Wiener process approach. IISE Transactions, 57(12), 1422–1435.
Zhang, M., & Revie, M. (2016). Model Selection with Application to Gamma Process and Inverse Gaussian Process. In: L. Walls, M. Revie, & T. Bedford (eds.) 26th Conference on European Safety and Reliability (ESREL). Glasgow, SCOTLAND.
Zhang, Z., Si, X., Hu, C., & Lei, Y. (2018). Degradation data analysis and remaining useful life estimation: A review on Wiener-process-based methods. European Journal of Operational Research, 271(3), 775–796.
Zhou, S., & Xu, A. (2019). Exponential Dispersion Process for Degradation Analysis. IEEE Transactions on Reliability, 68(2), 398–409.