Date of Award

2-4-2025

Publication Type

Dissertation

Degree Name

Ph.D.

Department

Industrial and Manufacturing Systems Engineering

Keywords

Additive Manufacturing; Genetic Algorithm; Heuristics; Logistics; Machine Learning; Supply Chain Management

Supervisor

Guoqing Zhang

Rights

info:eu-repo/semantics/embargoedAccess

Abstract

In today’s fast-paced and complex global market, supply chain decision-making challenges have grown significantly, driven by the integration of multiple, interdependent optimization problems. Traditional optimization methods struggle to keep pace with the dynamic demands and uncertainties that characterize modern supply chains, where decisions must be made quickly and efficiently to maintain a competitive edge. Machine Learning (ML) offers promising real-time solution paradigms that can address these complexities by rapidly processing vast datasets, identifying patterns, and providing adaptive decision-making sup port. However, designing effective ML-assisted algorithms tailored for integrated supply chain optimization problems remains a key challenge. This research explores the development of ML-enhanced solution methodologies for integrated supply chain models, where multiple interconnected decisions must be made simultaneously to efficiently design sup ply networks. These decisions include facility location, inventory management, production scheduling, and product delivery routing. By bridging the gap between classic optimization methods and learning based tools, this study aims to advance the creation of robust, responsive algorithms that not only optimize individual supply chain components but also enhance the entire network’s performance, providing competitive advantages in an increasingly demanding marketplace.

Available for download on Tuesday, February 03, 2026

Share

COinS