130 likes | 320 Views
Demand Management. Contents for demand management. Demand Mgt and MPC Environment. Communication with other MPC Modules. Forecasting Models. Conclusion. MPC Concept.
E N D
Contents for demand management Demand Mgt and MPC Environment Communication with other MPC Modules Forecasting Models Conclusion
MPC Concept • 중심에는Business Plan, Sales and Operation Plan, Master Production Schedule, Material Requirement Plan이 존재한다. 즉 4단계의 Plan을 통해 생산계획이 이루어진다.MPC(Mfg Planning and Control) 의 기본적 개념이다. • 1. Front End는 MPS까지, 2. Engine은 MRP까지, 3. Back End는 두 개의 PO(Production Order와 Purchase Order)가 존재. • 1. Frond End의 좌우에는 Demand(Management)와 Resource(Plan)이 존재 • 2. MRP엔진의 좌우에 PS(Planningand Scheduling-RCCP,DCCP,APS)와 MD(Master Data-BOM,IR,R)가 존재. • 그림?
MPC Concept • Flow Shop, Repetitive Shop, Job Shop, Project Shop • Lean Manufacturing(JIT: Just In Time)의 적용 범주? • MRP의 적용범주?
Demand Mgt and MPC Environment • Customer Order Decoupling Point • Independent Demand vs. Dependent Demand • MTS(Make To Stock), ATO(Assemble To Order), MTO(Make To Order) and ETO(Engineer To Order)의MPC환경이 존재 • 예: 양복점또는 피자가게의 MTS, ATO, MTO, ETO
Demand Mgt and MPC Environment: MTS • Final Goods Inventory, How much and when to order • Physical Distribution Considerations: • -Plant Warehouse, Distribution Centers, Local Warehouse • -VMI(Vendor Managed Inventory) • Balancing the Level of Inventory vs. Level of Service • Better Forecast, Rapid Transportation, Speedy and More Flexible Manufacturing
Demand Mgt and MPC Environment: ATO, MTO, ETO • ATO: Personal Computer, Car, Some Industrial Products • Configuration Management, Modules, Options Components • Inventory Advantage over MTS(예: Computer) • 4 processor options, 3 hard disk options, • 4 CD-DVD options, 2 speakers, 4 monitors • 374 final products vs. 17 components • ETO: 설계 능력 및 설계 용량
Communication with Other Modules: Pyramid Forecasting Aggregation에 따른 Variance의 변화는?
Forecasting Models • Simple Models vs. Complicated Models • Moving Average, Exponential Smoothing, Holt Winters, HW Seasonal, … • 예측 주체: 비전문가, 마케팅 전문가, 예측전문가 자료 소스: KAIST 전덕빈 교수
Forecasting Models • 수요예측 정보의 소스: • Data(주로 시계열), 2.상식,3.지식(소비자에 대한, 그리고 이론지식), 4.경험(영업 담당자), 5. 환경(신상품, 기술혁신, 경쟁, 규제완화, 고객 행태 및 구매력 변화) • 모델: 시계열 모델 (Time Series, BJ) • vs. 인과관계 모델(Regression, Econometric, Causal Rel.) 자료 소스: KAIST 전덕빈 교수
Forecasting Models • Time Series Model • Regression Model • The general representation of an autoregressive model, well-known as AR(p), is where the term εt is the source of randomness and is called white noise. It is assumed to have the following characteristics: With these assumptions, the process is specified up to second-order moments and, subject to conditions on the coefficients, may be second-order stationary. If the noise also has a normal distribution, it is called normal or Gaussian white noise. In this case, the AR process may be strictly stationary, again subject to conditions on the coefficients. In the more general multiple regression model, there are p independent variables: where xij is the ith observation on the jth independent variable, and where the first independent variable takes the value 1 for all i (so is the regression intercept). The least squares parameter estimates are obtained from p normal equations. The residual can be written as The normal equations are In matrix notation, the normal equations are written as where the ij element of X is xij, the i element of the column vector Y is yi, and the j element of is . Thus X is n×p, Y is n×1, and is p×1. The solution is For a derivation, see linear least squares, and for a numerical example, see linear regression (example).
Conclusion • Supply Chain의 가장 중요한 부분 • 모델과 실제 경험 부분은 수업 중 강의 내용과 위키피디아 자료 및 별도의 비공개 핸드아웃 참조할 것.