AI SearchImprovement of forecasting and scheduling procedures in the Siam-Fibre Cement Company
Suthad Sinsuesatkul
Improvement of forecasting and scheduling procedures in the Siam-Fibre Cement Company - Bangkok : Asian Institute of Technology, 1994 - 95 leaves - Thesis ; no. IE-94-02 . - Asian Institute of Technology. Thesis ; no. IE-94-02 .
A thesis submitted in partial fulfillment of the requirement for the degree of Master of Engineering, School of Engineering and Technology
Thesis (M.Eng.) - Asian Institute of Technology, 1994
This study concerns with the production planning problem of a multi-product single-stage system of the Siam-Fibre Cement company. At first, the current practices of the company related to the production planning, forecasting, production planning, and scheduling are investigated. Then, practical and appropriate procedures to improve the efficiency are developed. Considering data availability and ease of implementation, two types of time series forecasting models, i.e., Winter's model and ARIMA model, are suggested. Data of company sale are divided into two data sets. The first data set is used for model developing and the second data set is used for model validation. Model evaluation is done by comparing the results of both models with current practice in terms of forecasting error measures. Both models give better results than those of current practice. For production planning, the current practice model uses linear programming to optimize total cost. All relevant costs are included in the model and the assumption of linear costs is also reasonable. Thus, it is not necessary to develop a new model. For the implementation period, the output of model indicates the products to be produced on a specific machine. Now, the final task is how to schedule these products on each machine to minimize setup time. The problem of machine scheduling is analogous to combinatorial problem known as the traveling salesman problem. This problem can be solved by mixed integer programming. However, considering ease of implementation, a heuristic is suggested for ease of solution, and implementation. Both the results of heuristic and traveling salesman algorithm yield the same optimum results.
Scheduling (Management)
Production planning
Improvement of forecasting and scheduling procedures in the Siam-Fibre Cement Company - Bangkok : Asian Institute of Technology, 1994 - 95 leaves - Thesis ; no. IE-94-02 . - Asian Institute of Technology. Thesis ; no. IE-94-02 .
A thesis submitted in partial fulfillment of the requirement for the degree of Master of Engineering, School of Engineering and Technology
Thesis (M.Eng.) - Asian Institute of Technology, 1994
This study concerns with the production planning problem of a multi-product single-stage system of the Siam-Fibre Cement company. At first, the current practices of the company related to the production planning, forecasting, production planning, and scheduling are investigated. Then, practical and appropriate procedures to improve the efficiency are developed. Considering data availability and ease of implementation, two types of time series forecasting models, i.e., Winter's model and ARIMA model, are suggested. Data of company sale are divided into two data sets. The first data set is used for model developing and the second data set is used for model validation. Model evaluation is done by comparing the results of both models with current practice in terms of forecasting error measures. Both models give better results than those of current practice. For production planning, the current practice model uses linear programming to optimize total cost. All relevant costs are included in the model and the assumption of linear costs is also reasonable. Thus, it is not necessary to develop a new model. For the implementation period, the output of model indicates the products to be produced on a specific machine. Now, the final task is how to schedule these products on each machine to minimize setup time. The problem of machine scheduling is analogous to combinatorial problem known as the traveling salesman problem. This problem can be solved by mixed integer programming. However, considering ease of implementation, a heuristic is suggested for ease of solution, and implementation. Both the results of heuristic and traveling salesman algorithm yield the same optimum results.
Scheduling (Management)
Production planning