DSpace community: 工業管理研究所碩士在職專班

自然環境因子對甘草採購策略的影響-以A公司為例;自然環境因子對甘草採購策略的影響-以A公司為例

Tue, 20 Oct 2026 06:40:53 GMT

title: 自然環境因子對甘草採購策略的影響-以A公司為例;自然環境因子對甘草採購策略的影響-以A公司為例 abstract: 甘草作為中藥方劑中「調和諸藥」的核心藥材，亦是製藥產業極為關鍵的原料藥材。本研究以「脹果甘草」作為研究對象，整合海拔、年平均氣溫及年降水量等八項關鍵環境因子作為自變數，並以甘草酸（Glycyrrhizic acid）含量作為依變數。研究首先透過K-Means分群分析確認樣本分群，隨後採用多元線性回歸（MLR）之最小平方法（OLS）建構品質預測模型，並搭配「80/20驗證法則」以確保模型的泛化能力。此外，本研究進一步導入環境因子間的「交互作用分析」（如：氣溫與降水量的交互影響），以捕捉自然環境對甘草次級代謝產物累積所產生的複雜非線性影響。研究結果證實，透過監控產地環境變因，能有效建立高品質甘草之預測模型。將此模型轉化為實務管理工具並應用於採購前置篩選，將能預先過濾並淘汰高風險樣本，顯著提升採購合格率。本研究不僅深化了環境因子對甘草品質影響的學術理解，更為製藥產業在精實物控管理與降低缺料風險上，提供了具備實證基礎的科學化與數據化的決策機制。;Licorice (Glycyrrhiza)， serving as the core medicinal material for "harmonizing various drugs" in traditional Chinese medicine prescriptions， is also a crucial raw material in the pharmaceutical industry. This study focused on Glycyrrhiza inflata as the research subject. Eight key environmental factors， including altitude， annual mean temperature， and annual precipitation， were integrated as independent variables， with the glycyrrhizic acid content set as the dependent variable. Initially， K-Means clustering analysis was employed to identify and confirm sample clusters.Subsequently， a quality prediction model was constructed using Ordinary Least Squares (OLS) based Multiple Linear Regression (MLR)， paired with the "80/20 validation rule" to ensure the model′s generalization capability.Furthermore， this study introduced "interaction analysis" among environmental factors (e.g.， the interactive effect between temperature and precipitation) to capture the complex， non-linear impacts of the natural environment on the accumulation of secondary metabolites in licorice. The results demonstrated that by monitoring the environmental variables of the origin， a highly effective prediction model for high-quality licorice can be established. Transforming this model into a practical management tool and applying it to pre-procurement screening can proactively filter and eliminate high-risk samples， significantly improving the procurement qualification rate. This study not only deepens the academic understanding of how environmental factors influence licorice quality but also provides an evidence-based， scientific， and data-driven decision-making mechanism for the pharmaceutical industry to streamline material control management and mitigate the risk of material shortages.

新冠疫情對平板電腦市場之季節性結構演變與供應鏈緩衝策略的影響 The Impact of the COVID-19 Pandemic on the Evolution of Seasonal Structures and Supply Chain Buffering Strategies in the Tablet Computing Market;新冠疫情對平板電腦市場之季節性結構演變與供應鏈緩衝策略的影響 The Impact of the COVID-19 Pandemic on the Evolution of Seasonal Structures and Supply Chain Buffering Strategies in the Tablet Computing Market

Tue, 20 Oct 2026 06:40:16 GMT

title: 新冠疫情對平板電腦市場之季節性結構演變與供應鏈緩衝策略的影響 The Impact of the COVID-19 Pandemic on the Evolution of Seasonal Structures and Supply Chain Buffering Strategies in the Tablet Computing Market;新冠疫情對平板電腦市場之季節性結構演變與供應鏈緩衝策略的影響 The Impact of the COVID-19 Pandemic on the Evolution of Seasonal Structures and Supply Chain Buffering Strategies in the Tablet Computing Market abstract: 全球平板電腦市場於2018年進入成熟平台期，年出貨量約為1.44至1.46億台，季節性需求波動成為供應鏈管理的核心挑戰。新冠疫情同時驅動居家辦公與緊急遠距教學需求，將年出貨量推至2021年高峰1.683億台，隨後的牛鞭效應導致2023年出貨量暴跌20.5%至1.285億台。本研究設定四項研究目的：記錄八年市場軌跡（O1）、量化疫情期季節性擾動（O2）、測量疫後季節重建幅度（O3），以及將重建後的指數轉化為可部署2026年供應鏈緩衝策略（O4）。本研究以IDC全球季度平板追蹤報告32季數據（2018–2025年）為基礎，提出「疫情期－疫後期分析框架」：疫情期（During，2020–2022）與疫後期（After，2023–2025）分別進行乘法型居中移動平均季節分解。研究發現：疫情期季節振幅為34.93百分點（〖SI〗_D：Q1=0.8313、Q4=1.1806）；疫後期縮小至16.51百分點（〖SI〗_A：Q1=0.9272、Q4=1.0923），降幅52.7%。商用區段變異係數由疫情期0.1755大幅下降至疫後期0.0772（∈56%），跨越Fisher（1997）之變異係數閾值0.10；消費者區段變異係數則由0.1577溫和下降至0.1324。根據疫後季節指數建構2026年「水準生產緩衝策略」：水準生產率為每季3，508萬台、H1緩衝庫存520萬台（Q1:+255萬、Q2:+265萬）、年底庫存餘額為零，預估年度淨節省USD 1.24–2.57億。本研究提出五項管理建議（包括年度規劃制度化、區段差異庫存策略、電商通路預置指定期限、ODM合約重議與年度參數更新機制），以及三項理論貢獻：疫情期－疫後期季節量測方法論、疫後商用需求穩定化發現，以及適用於平板電腦品牌製造商的零年底庫存餘額供應鏈緩衝規劃框架。;The global tablet computer market entered 2018 as a mature， replacement-cycle plateau with annual shipments of approximately 144 to 146 million units. A consistent seasonal pattern had emerged as the dominant supply chain cost driver， with Q4 demand exceeding Q1 by approximately 40 percent and second-half shipments exceeding first-half by 23 to 30 percent. The COVID-19 pandemic pandemic shattered this stability: simultaneous Work-From-Home mandates and Emergency Remote Teaching drove global shipments to a pandemic peak of 168.34 million units in 2021， before a Bullwhip-driven inventory correction collapsed demand to 128.49 million units in 2023 (−20.5 percent)， the deepest contraction in modern tablet history. Brand manufacturers including Apple， Samsung， Lenovo， Amazon， and Acer face a critical planning problem: pandemic-era seasonal data is too distorted to serve as a reliable baseline for post-pandemic supply chain decisions， yet no methodology existed to formally separate and compare the pandemic seasonal structure from the reconstructed post-pandemic equilibrium. This research pursues four research objectives: (O1) document the eight-year market trajectory; (O2) quantify COVID-19’s seasonal distortion during 2020–2022; (O3) measure the post-pandemic seasonal reconstruction in 2023–2025; and (O4) translate the reconstructed indices into a deployable 2026 supply chain buffer strategy. A During–After Multiplicative Centered Moving Average decomposition is applied to 32 quarters of IDC Worldwide Quarterly Tablet Tracker data (Q1 2018 – Q4 2025): the During Regime (2020–2022) captures pandemic distortion and the After Regime (2023–2025) captures post-pandemic reconstruction. Four models are applied sequentially: Seasonal Index computation (Equation 3-1)， Coefficient of Variation analysis (Equation 3-2)， Channel Amplification Factor (Equation 3-4)， and the Level Production buffer model (Equations 3-5 and 3-6). Four principal findings emerge. The seasonal amplitude reached 34.93 percentage points during the pandemic (During: SI Q1 = 0.8313， Q4 = 1.1806) and narrowed to 16.51 percentage points post-pandemic (After: SI Q1 = 0.9272， Q4 = 1.0923)， a 52.7 percent reduction. Commercial segment demand volatility stabilized dramatically (CV: 0.1755 → 0.0772， −56 percent)， crossing the Fisher (1997) CV threshold， while Consumer volatility moderated more gradually (0.1577 → 0.1324). Applying the After indices as 2026 planning parameters， the Level Production buffer framework yields a Level Production Rate of 35.08 million units per quarter， a first-half buffer of 5.20 million units， and zero year-end inventory residual， with an estimated net annual saving of USD 124–257 million versus the Chase strategy. Five managerial recommendations are derived: institutionalize the annual Level Production buffer planning cycle; adopt differentiated inventory policies for Consumer and Commercial segments; pre-position 1.33 million eTailer units before end-September; renegotiate ODM seasonal surcharges using the quantified During vs After amplitude reduction as evidence; and build an annual SI parameter update process. Three theoretical contributions are made: (C1) the During–After During/After Seasonal Index framework as a formal post-pandemic measurement methodology; (C2) the discovery of Commercial segment CV stabilization as a novel post-pandemic equilibrium finding; and (C3) an integrated supply chain buffer plan with zero year-end inventory balance， connecting all four analytical models into a single deployable framework.

運用數位孿生優化水冷機櫃生產空間布局;Leveraging Digital Twin to Optimize Factory Layout in Cooling Rack Production

Tue, 20 Oct 2026 06:39:25 GMT

title: 運用數位孿生優化水冷機櫃生產空間布局;Leveraging Digital Twin to Optimize Factory Layout in Cooling Rack Production abstract: 近年來，隨著人工智慧與高效能運算需求快速成長，GPU 功耗持續攀升，所產生之熱負載亦大幅增加，進而帶動市場對散熱解決方案之需求。由於傳統氣冷散熱技術已逐漸接近物理極限，液冷散熱系統遂成為新世代資料中心的重要基礎設施。然而，水冷散熱機櫃具備高重量、大體積與測試時間長等產品特性，在台灣廠房空間普遍受限之情況下，產線配置常需採取 S 型或 U 型動線規劃，容易造成搬運次數增加、物流距離延長等問題，進而影響整體生產效率。因此，如何透過有效之廠區配置規劃降低物流浪費並提升生產效能，已成為製造管理之課題。此外，傳統廠區規劃多仰賴工程經驗與靜態分析，難以完整評估不同配置方案於實際生產情境下之動態變化與資源利用情形，增加企業於產線建置或搬遷時之決策風險。因此，本次結合靜態布局理論與動態模擬技術，以提升規劃效率及降低試錯成本。本研究以國內某電源管理與散熱解決方案的企業為個案研究對象，聚焦於水冷散熱機櫃生產流程，雙階段整合架構探討布局優化的可能性。首先運用系統化佈置規劃（SLP）針對主要作業區域進行產品－產量分析、流程程序圖及活動關係矩陣分析，以釐清各作業區之物流強度與空間需求。其次，結合數位孿生概念與離散事件模擬（DES）工具 FlexSim，建構產線虛擬模型，確認不同配置方案之運作績效。研究結果可作為大型機櫃產線配置規劃的參考依據，協助企業運用數位模擬與分析，作為投資決策的依據。;In recent years， the rapid growth of artificial intelligence (AI) and high-performance computing (HPC) has significantly increased GPU power consumption and thermal loads， driving the demand for advanced cooling technologies. As conventional air-cooling approaches are reaching their physical limits， liquid cooling has become a key solution for next-generation data centers. However， liquid-cooled racks are characterized by their heavy weight， large size， and long testing time. Coupled with the limited factory space in Taiwan， these characteristics often lead to inefficient production layouts， increased material handling， and longer transportation distances. Therefore， optimizing facility layouts to improve production efficiency has become an important issue in manufacturing. This study adopts a case study of a Taiwanese company specializing in power management and thermal management solutions， focusing on the production process of liquid-cooled racks. A two-stage integrated approach is proposed for facility layout optimization. First， Systematic Layout Planning (SLP) is applied to conduct Product-Quantity (P-Q) analysis， process flow analysis， and activity relationship analysis to identify logistics requirements and space utilization. Second， the Digital Twin concept is integrated with the discrete event simulation (DES) software FlexSim to establish a virtual production model for evaluating the operational performance of different layout alternatives. The simulation results enable comparisons of multiple layout scenarios before physical implementation， reducing planning risks and trial-and-error costs. The proposed approach provides a systematic framework for facility layout planning of large-scale liquid-cooled racks production lines and serves as a practical reference for enterprises in production planning， facility investment， and smart manufacturing implementation.

運用實驗設計提升CPO光纖陣列之良率;A Study on Improving the Process Yield of Co-Packaged Optics Fiber Array Unit using Design of Experiments

Tue, 20 Oct 2026 06:37:10 GMT

title: 運用實驗設計提升CPO光纖陣列之良率;A Study on Improving the Process Yield of Co-Packaged Optics Fiber Array Unit using Design of Experiments abstract: 隨著高效能運算對資料傳輸速率的要求日益嚴苛，共同封裝光學（Co-Packaged Optics， CPO）技術已成為半導體先進封裝的發展核心。然而CPO光纖陣列單元（FAU）的點膠與固化製程涉及高精密與異質材料整合，極易受環境與製程參數波動影響導致量產初期良率低迷。本研究旨在解析製程變異來源、建構多因子統計模型，並推導最佳化參數以建立標準作業程序（SOP）與品質管制計畫。研究首先運用品質管制工具，界定出「內部氣泡」與「表面分層」為兩大關鍵缺陷。隨後導入田口實驗設計法（DOE），採用L9(3^4)直交表針對環境溫度、相對濕度、UV曝光能量強度與UV曝光時間等四項關鍵因子進行多水準實驗。研究中結合光學顯微鏡之數位影像量化與望小特性訊號雜音比（S/N比），並透過變異數分析（ANOVA）精準拆解系統變異。相對濕度為誘發氣泡的絕對因子，而UV曝光能量強度則是導致介面分層的關鍵。經由主效應與等高線操作視窗分析推導出最佳製程參數組合。經產線大樣本確認實驗實證此最佳化參數不僅具備跨批次（Lot-to-lot）之穩健性，更成功將製程綜合良率大幅提升。本研究有效排除了傳統試誤法的盲點，為前瞻矽光子封裝奠定了科學化的量產管制基準。;Background and Objectives: Co-Packaged Optics (CPO) is critical for high-speed computing but faces severe yield bottlenecks during Fiber Array Unit (FAU) packaging due to high sensitivity to process variations. This study aims to identify variance sources， optimize parameters， and establish Standard Operating Procedures (SOPs) for robust mass production. Methods: "Internal voids" and "interfacial delamination" were identified as primary defects. A Taguchi L9(3^4) orthogonal array was utilized to evaluate four control factors: temperature， relative humidity (RH)， UV exposure intensity， and UV exposure time. Data were analyzed using digital image quantification， signal-to-noise (S/N) ratios， and Analysis of Variance (ANOVA). Results: ANOVA revealed that RH is the dominant factor for void formation， while UV intensity primarily drives delamination. The optimal parameter combination was determined and Confirmation experiments verified cross-batch robustness， successfully improving the overall yield from 5% to over 40%. Conclusions: This study replaces traditional trial-and-error approaches with a scientifically validated framework， establishing a highly stable mass production baseline for advanced silicon photonics packaging.