台灣的半導體產業以代工為主,並負責客戶端的原料代購服務。半導體封裝產業 中,當單一產品代工案結束時,剩餘的代購原料常因其特用性無法轉用於其他產品, 而發生代工廠必須請客戶購回原料之情況,然而代工廠在此種情況下大多居於弱勢, 使得餘料成為無法處理的呆料。因此,若能有效預測客戶需求以為代購數量之參考, 為可行方法之一。然由於多數消費性電子產品之生命週期極短,並無法有效收集長期 數據做為預測模式建模所用。在過往的文獻中,雖然灰預測模式(Grey Model, GM)已 被證實能使用短期時間序列資料而產生準確之預測值,但仍具其準確度改善空間。故 本研究基於模糊(Fuzzy)理論,提出一個模糊灰預測模式 FGM(1,1)。該方法流程如下: (1) 針對短期時間序列資料進行模糊化以產生三組模糊序列資料;(2) 使用 GM(1,1) 建構三個預測模式並產生最新期預測值;(3) 透過三個 GM(1,1)之各期預測誤差進行 權重的計算,再以此權重與三個最新期預測值進行解模糊化,而產生最終的預測值。 本研究從個案公司取得九種產品對於封裝基板之需求量,進行效果驗證,實驗結果顯 示,FGM(1,1)比 GM(1,1)確有更佳的整體預測結果。

Because the lifecycles of consumable electronic products are very short nowadays, it has become very difficult for original equipment manufacturers to precisely prepare materials for production. In this paper, a real case of a worldwide leading company in the integrated circuit (IC) assembly industry is revealed. To avoid specific materials from being idle stock, forecasting customer’s demand has become an important strategy for the firm under consideration. However, it is almost impossible to collect enough data to build robust forecasting models because of the short product lifecycles. Over the past two decades, the grey model (GM) has been shown to be effective tools to deal with short-term time series data. To further enforce the effectiveness of data uncertainty treatment for dynamic IC industries, a novel GM model is developed based on a fuzzy-set concept, called fuzzy-based GM (FGM). In FGM, short term series data is fuzzified to form a fuzzy time series for building GM models, where the final prediction is aggregated by the predictions of the GM models with proposed weights. The experimental results for the real case and a public dataset indicate that FGM outperforms GM and thus has practical value in tackling the real case.

王永泰. (2016). 以整體趨勢擴散技術為核心之灰預測模型求解面板產業退返品還貨 備料問題. (碩士), 國立成功大學, 台南市
林萬吉. (1996). 基於灰色系統的物件輪廓影像之斷線復原法. (碩士), 國立臺灣科技 大學, 台北市
曹銳勤. (2006). Forecasting Analysis by Fuzzy Grey Model GM(1,1). [模糊灰色 gm(1,1) 預測模式]. 工業工程學刊, 23(5), 415-422.
陳盈融. (2017). 運用德爾菲法探討巨量資料分析成功之影響因素-以全民健保資料 庫為例. (碩士), 國立中正大學, 嘉義縣
陳秋恭. (2004). 應用模糊類神經網路於穿刺結構之動態訊號分析. (碩士), 國立成功 大學, 台南市
楊志平. (2003). 灰預測、指數平滑法與預測組合之應用─以台灣地區鮮食鳳梨產地價 格為例. (碩士), 國立屏東科技大學, 屏東縣
廖景帆. (2012). 演化式模糊關係之模糊時間序列預測模式. (碩士), 國立成功大學, 台 南市
鄭亦君. (2008). 決定性模糊時間序列預測模式之研究. (博士), 國立成功大學, 台南 市
謝俊嘉. (2009). 灰色系統分析應用於多頻譜影像之分類. (碩士), 國立勤益科技大學, 台中市
Chen, S.-M. (1996). Forecasting Enrollments Based on Fuzzy Time Series. Fuzzy Sets and Systems, 81(3), 311-319.
Chen, S.-M. (2002). Forecasting Enrollments Based on High-order Fuzzy Time Series. Cybernetics and Systems, 33(1), 1-16.
Chen, S.-M., & Chen, C.-D. (2011). Handling Forecasting Problems Based on High-order Fuzzy Logical Relationships. Expert Systems with Applications, 38(4), 3857-3864.
Deng, J.-L. (1982). Control Problems of Grey Systems. Systems & Control Letters, 1(5), 288-294.
Deng, J.-L. (1989). Introduction to Grey System Theory. The Journal of Grey System, 1(1), 1-24.
Dong, D., Yan, Y., & Wang, Z., 12-14 (2011). Application of Gray Correlative
Model for Surface Quality Evaluation of Strip Steel Based on the Variation Coefficient Method. Paper presented at the Proceedings of 2011 International Conference on Electronic & Mechanical Engineering and Information Technology.
Ene, S., & Öztürk, N. (2017). Grey Modelling Based Forecasting System for Return Flow of End-of-life Vehicles. Technological Forecasting and Social Change, 115, 155-166.
Hamzacebi, C., & Es, H. A. (2014). Forecasting the Annual Electricity Consumption of Turkey Using an Optimized Grey Model. Energy, 70, 165-171.
Hsu, Y.-L., Lee, C.-H., & Kreng, V. B. (2010). The Application of Fuzzy Delphi Method and Fuzzy AHP in Lubricant Regenerative Technology Selection. Expert Systems with Applications, 37(1), 419-425.
Javed, S. A., Liu, S., Mahmoudi, A., & Nawaz, M. (2018). Patients' Satisfaction and Public and Private Sectors' Health Care Service Quality in Pakistan: Application of Grey
Decision Analysis Approaches. The International Journal of Health Planning and
Management.
Lewis, C. D. (1982). Industrial and Business Forecasting Methods: London: Butterworths. Li, B., Yang, W., & Li, X. (2017). Application of Combined Model with DGM(1,1) and
Linear Regression in Grain Yield Prediction. Grey Systems: Theory and Application,
8(1), 25-34.
Li, D.-C., Lin, W.-K., Chen, C.-C., Chen, H.-Y., & Lin, L.-S. (2018). Rebuilding Sample
Distributions for Small Dataset Learning. Decision Support Systems, 105, 66-76. Li, S.-J., Ma, X.-P., & Yang, C.-Y. (2018). Prediction of Spontaneous Combustion in the
Coal Stockpile Based on an Improved Metabolic Grey Model. Process Safety and
Environmental Protection, 116, 564-577.
Liu, S., & Forrest, J. (2006). Grey Information:Theory and Practical Applications
Springer-Verlag, Londun Ltd (2006).
Lu, S.-L. (2018). Integrating Heuristic Time Series with Modified Grey Forecasting for
Renewable Energy in Taiwan. Renewable Energy.
Mentzer, J. T., & Cox, J. E. (1984). Familiarity, Application, and Performance of Sales
Forecasting Techniques. Journal of Forecasting, 3(1), 27-36.
Pan, L., Sun, B., & Wang, W. (2011). City Air Quality Forecasting and Impact Factors
Analysis Based on Grey Model. Procedia Engineering, 12, 74-79.
Song, Q., & Chissom, B. S. (1993). Fuzzy Time Series and Its Models. Fuzzy Sets and
Systems, 54(3), 269-277.
Wang, Y., Tang, J., & Cao, W.,15-18 (2011). Grey Prediction Model-based
Food Security Early Warning Prediction. Paper presented at the Proceedings of 2011 IEEE International Conference on Grey Systems and Intelligent Services.
Wang, Z.-X., & Li, Q. (2019). Modelling the Nonlinear Relationship between CO2 Emissions and Economic Growth Using a PSO Algorithm-based Grey Verhulst Model. Journal of Cleaner Production, 207, 214-224.
Yang, S.-H., & Chen, Y.-P. (2011). Intelligent Forecasting System Using Grey Model Combined with Neural Network. International Journal of Fuzzy Systems, 13(1), 8-15.
Zadeh, L. A. (1965). Fuzzy Sets. Information and Control, 8(3), 338-353.
Zhao, H., & Guo, S. (2016). An Optimized Grey Model for Annual Power Load
Forecasting. Energy, 107, 272-286.