Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Supply Chain Risk Assessment through Data-Driven Bayesian Networks

Lois, Robert (2022) Supply Chain Risk Assessment through Data-Driven Bayesian Networks. Master's Thesis, University of Pittsburgh. (Unpublished)

[img]
Preview
PDF (MS Thesis)
Primary Text

Download (10MB) | Preview

Abstract

The supply chain is an integrated process of suppliers, plants, warehouses, and manufacturers all working together in an effort to procure raw materials, process the raw materials into final products, and deliver the final products to customers. However, the supply chain today has grown into a complex network, leading to vulnerabilities and an increase of uncertainty for decision makers. These vulnerabilities are defined as events with an associated likelihood to cause disruptions. With a limited amount of information on events occurring, the uncertainty decision makers encounter ultimately impedes the goals of the supply chain. These consequences are prevalent in low-volume, high-value supply chains such as the nuclear power generating industry.

The goal of this research is to reduce the uncertainty decision makers face in the nuclear power generating supply chain by developing a Bayesian network to monitor, plan, and control supply chain disruptions. The aim is to integrate models of event disruptions, resource availability, and mitigation options. Events that disrupt the flow of goods and information are identified through an ontological approach and are quantified with a likelihood of occurring through a general elicitation method. Resource availability of the nuclear power generating supply chain is modeled using control theory to simulate inventory data. The inventory data of upstream suppliers is estimated using Kalman filters and particle filters. The likelihood of events and the resource availability data are - integrated into a Bayesian network depicting the nuclear power plant supply network. Mitigation options are added to the Bayesian network to reduce the likelihood of events at a financial cost to deploy the option. Several scenarios are used to illustrate the application of the Bayesian network in terms of the supplier selection problem to demonstrate how uncertainty in decision making is
reduced.


Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: University of Pittsburgh ETD
Status: Unpublished
Creators/Authors:
CreatorsEmailPitt UsernameORCID
Lois, Robertrobert.lois@pitt.edurol450000-0002-9356-8468
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Committee ChairCole, Danieldgcole@pitt.edudgcole0000-0001-9541-3198
Committee MemberBan, Hengheng.ban@pitt.eduhengban0000-0003-3554-8730
Committee MemberMichael, Sherwinmdsherwin@pitt.edumdsherwin0000-0001-7580-6621
Date: 10 June 2022
Date Type: Publication
Defense Date: 1 April 2022
Approval Date: 10 June 2022
Submission Date: 12 April 2022
Access Restriction: No restriction; Release the ETD for access worldwide immediately.
Number of Pages: 173
Institution: University of Pittsburgh
Schools and Programs: Swanson School of Engineering > Mechanical Engineering
Degree: MS - Master of Science
Thesis Type: Master's Thesis
Refereed: Yes
Uncontrolled Keywords: machine learning, data-driven modeling, supply chain, decision making, probabilistic reasoning, risk assessment
Date Deposited: 10 Jun 2022 19:43
Last Modified: 10 Jun 2022 19:43
URI: http://d-scholarship.pitt.edu/id/eprint/42595

Metrics

Monthly Views for the past 3 years

Plum Analytics


Actions (login required)

View Item View Item