OPMLabguidebook副本.doc

Operations Management Experimentation Guidebook By Wang Xiao-Guang School of Mechanical and Electrical Engineering The Wuhan University of Technology 1.18.2004 Contents Experimentation 1: Quantitative Demanding Forecasting (3 hours) 2 Experimentation 2: Linear Programming: LP (1.5 hours) 4 Experimentation 3: Resource Requirement Planning: MRP (1.5 hours) 7 Experimentation 1: Quantitative Demanding Forecasting (3 hours) 1 Experiment Purpose Master the principle of selecting a forecasting model. Make a demand forecasting with computer software. Evaluate the result of forecasting. 2 Case: Sundance Chemical Company Tyler Jones has just been hired as the new production manager at the Sundance Chemical Company (SCC). He believes his first action should be to develop his own sales forecasts for the company’s primary chemical product. Mr. Jones asked his assistant to collect quarterly sales data for the past 10 years, as shown below: Quarterly Sales (thousands of gallons) Year Q1 Q2 Q3 Q4 1 594 570 560 565 2 540 531 515 498 3 485 479 463 456 4 319 324 336 340 5 348 355 354 367 6 375 379 385 396 7 404 416 422 430 8 436 439 450 459 9 470 475 485 489 10 505 513 516 518 The president of the SCC has been disappointed in recent years by the previous production manager’s poor forecasting accuracy. To make a good impression with top management, Tyler Jones intends to perform a thorough forecasting analysis to forecast sales for the next four quarters. 3 Experiment Design Following are suggested experiment design steps: 3.1 Graph the data. To see what help you can get. 从图表看出近十年产量先下降后上升，后6年呈线性增长趋势 3.2 Decide how much of the past data should be used to develop a forecasting model. Provide an explanation that justifies your decision. 3.3 Which forecasting models would be most appropriate to evaluate the case? Includes: Linear regres