Han WuFollow

Date on Master's Thesis/Doctoral Dissertation


Document Type

Doctoral Dissertation

Degree Name

Ph. D.


Industrial Engineering

Degree Program

Industrial Engineering, PhD

Committee Chair

Evans, Gerald

Committee Co-Chair (if applicable)

Bae, Kihwan

Committee Member

Alexander, Suraj

Committee Member

Bai, Lihui

Committee Member

Chang, Dar-jen

Author's Keywords

Production System; inventory control; ADP; ANN


Production systems focus not only on providing enough product to supply the market, but also on delivering the right product at the right price, while lowering the cost during the production process. The dynamics and uncertainties of modern production systems and the requirements of fast response often make its design and operation very complex. Thus, analytical models, such as those involving the use of dynamic programming, may fail to generate an optimal control policy for modern production systems. Modern production systems are often in possession of the features that allow them to produce various types of product through multiple working stations interacting with each other. The production process is usually divided into several stages, thus a number of intermediate components (WIP) are made to stock and wait to be handled by the next production stage. In particular, development of an efficient production and inventory control policy for such production systems is difficult, since the uncertain demand, system dynamics and large changeover times at the work stations cause significant problems. Also, due to the large state and action space, the controlling problems of modern production systems often suffer from the "curse of dimensionality".