dc.description.abstract | Material Requirements Planning (MRP) plays a vital role in managing
manufacturing facilities. The problem is determining the production loading
plan consisting of the quantity of production and inventory level - fulfilling
future demand. This paper investigates two-stage stochastic optimization
methods for Material Requirements Planning (MRP) systems under demand
uncertainty in the automotive industry. First, this study addresses the demand
forecast by applying the decomposition model and compared with other
forecasting methods. Although forecast models could be used to improve
forecast accuracy, error and uncertainty still exist. To deal with this
uncertainty, a two-stage stochastic scenario-based production planning model
is developed to maximize the net profit received at the end of the planning
horizon. A parametric analysis is used to derive managerial insights related to
three factors: total cost, unexpected loss, and revenue. Specifically, the first
stage determines the production quantity needed to assemble cars while
demand is unknown at period 0. When a possible realization of demand is
revealed, the second stage variables represent the over-time production
quantity, inventory level, backorder level, defective rate, and planned order
receipts. In addition, the model also considers Order-up-to level method to
tighten inventory control and re-balance stock on hand. The model is solvediv
with data from a local manufacturing facility, and the results are compared
with deterministic production models to show the effectiveness of the
developed stochastic model. As a result, implementing the two-stage
stochastic optimization model should be considered in MRP systems since
this method would allow manufacturers to determine a plan that yields an
optimal trade-off between the profit and production costs in this complex
environment | en_US |