This thesis deals with a quantitative decision-making system for planning production, inventories and work-force.
The existing method of Parametric Production Planning (PPP) proposed by C.H. Jones is extended to a Multi-item Parametric Decision Rule(MPDR) model.
(1) The PPP postulates the existance of two feed-back rules, one for work-force level and one for aggregate production rate. The MPDR model not only provides feed-back rules for the production rates of individual items, but also explicitly considers the effect of manufacturing progress and other relevant factors such as labor utilization, employee turn-over, difference in work-days, etc. in an effort to make the model more applicable.
(2) Main procedures of this method are as follows;
1. Estimate the important costs related to a production system.
2. Fit the actual cost relations to suitable functions.
3. Build up decision rules for work-force and production rates for individual items.
4. Search the universe of possible parameters to find a set of parameters which minimizes total cost over a specified planning horizon, given estimates of future demands for individual items.
A pattern search method which turns out to be very efficient compared to the grid search is employed for the optimization of objective function. In estimating the inventory cost functions, an analytic approach is proposed in terms of the distribution of monthly sales.
As a case study, a hypothetical decision rule is developed for a particular firm (truck assembly factory) and a computer program for pattern search is attached.