Cerry M. Klein
CMMI Division of Civil, Mechanical, and Manufacturing Innovation
ENG Directorate for Engineering
Start Date:
January 1, 2006
Expires:
December 31, 2010 (Estimated)
Awarded Amount to Date:
$633412
Investigator(s):
Michael Ball mball@rhsmith.umd.edu (Principal Investigator)
Michael Fu (Co-Principal Investigator)
Sponsor:
University of Maryland College Park
3112 LEE BLDG
COLLEGE PARK, MD 20742 301/405-6269
NSF Program(s):
ITR-DYNAMIC DATA DRIV APP SYS, MANFG ENTERPRISE SYSTEMS
Field Application(s):
0308000 Industrial Technology
Program Reference Code(s):
MANU, 9147, 7581
Program Element Code(s):
7581, 1786
ABSTRACT
This research project will study the business processes related to receiving, accepting, processing and fulfilling customer orders in global make-to-order supply chains. It will investigate the databases and data flows underlying these processes, the business decision processes and the manner in which these interact. Simulation and optimization models will be developed that monitor real-time streams of input data. Algorithms that monitor these streams must determine when predictions should change and should calculate such changes if appropriate. Research will also be carried out into the development Markov Decision Processes (MDPs) that dynamically adapt to sensor data streams. In addition to building on MDP research, this topic will consider the use of Mixed Integer Programming models for setting MDP parameters.
The results of this research will provide the basis for improved operational control of make-to-order supply chains. It will provide the theory underlying the development of "always on" controllers that continuously monitor supply chain data sources and project the future status of key business processes. This research will support improved decision making under both normal operations and incident response. The normal operations decisions supported could include product positioning decisions, order timing and acceptance decisions and production scheduling decisions. The incident response mode will be used to develop a strategy for reacting to major disruptive events. Such events might include the failure or delay of a major supply shipment, a major breakdown in a factory or acceptance of a large order that preempts existing order commitments. These capabilities should substantially increase the level of customer service and the profitability for supply chains that employ them.
PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH
Chen, CH; He, DH; Fu, M; Lee, LH. "Efficient Simulation Budget Allocation for Selecting an Optimal Subset," INFORMS JOURNAL ON COMPUTING, v.20, 2008, p. 579-595.
Fu, MC. "What You Should Know About Simulation and Derivatives," NAVAL RESEARCH LOGISTICS, v.55, 2008, p. 723-736.
Fu, MC; Lele, S; Vossen, TWM. "Conditional Monte Carlo Gradient Estimation in Economic Design of Control Limits," PRODUCTION AND OPERATIONS MANAGEMENT, v.18, 2009, p. 60-77.
Lan, YJ; Gao, HN; Ball, MO; Karaesmen, I. "Revenue management with limited demand information," MANAGEMENT SCIENCE, v.54, 2008, p. 1594-1609.
Please report errors in award information by writing to: awardsearch@nsf.gov.
