| Author | Das, Atash Kumar |
| Call Number | AIT Thesis no. IE-88-07 |
| Subject(s) | Production planning
|
| Note | A Thesis Submitted in Partial Fulfilment of the Requirements for t he Award of the Degree of Master of Engineering, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Series Statement | Thesis ; no. IE-88-07 |
| Abstract | This study was concerned with the production planning problem of a
multi- product multi- stage system (an edible oil refinery). A two phase planning
scheme has been considered for the problem. In the first phase of this study
similar products have been aggregated into some major product categories and
the demands for each of these categories were forecasted for an entire seasonal
cycle (a year). Three exponentially weighted time series smoothing models were
employed for the purpose and the smoothing constants were optimized. The best
forecasts corresponding to the least sum of square error were chosen and used
subsequently. In the second phase a modified LP model was employed to
determine the optimal production plan for each product of each facility and in
each period that would meet all the demands and satisfy the capacity and
storage restrictions throughout the entire planning horizon . To permit a detailed
consideration of all products (which is essential for the system), a hierarchical
approach has been adopted. In the aggregate analysis the planning horizon has
been partitioned into four equal periods and for each period the cost- optimal
production and inventory decisions subject to the aggregate restrictions for
capacity and storage were determined. In the succeeding step these decisions for
the first period were disaggregated to obtain biweekly production plans for each
facility. Since the forecasts are likely to vary from the actual realizations of
demand (because of the random component in the time series), safety measures
have been incorporated in the models to ensure that all demands can be met.
This measure assumes that in no periods the actual demand of a product will
exceed the corresponding forecast by an amount more than its next month's
demand and in each period thus carries an inventory equal to the product's
next month's forecasted demand. Finally a rolling horizon model- implementation
scheme has been suggested that would allow periodic application of the
aggregate and the disaggregate models. |
| Year | 1988 |
| Corresponding Series Added Entry | Asian Institute of Technology. Thesis ; no. IE-88-07 |
| Type | Thesis |
| School | School of Engineering and Technology |
| Department | Other Field of Studies (No Department) |
| Academic Program/FoS | Industrial Engineering (IE) |
| Chairperson(s) | Fujiwara, Okitsugu
; |
| Examination Committee(s) | Tabucanon, Mario T. ;Awate, Prakash G. ; |
| Scholarship Donor(s) | DAAD, West Germany; |
| Degree | Thesis (M.Eng.) - Asian Institute of Technology, 1988 |