Brief Description:
With time, it has been widely believed that a wide variety of natural and human-made incidents threaten to disrupt the supply chain and logistics networks, especially in today’s world in which the globalisation concept has raised and made these networks more complex. Uncertainties and disruptions mainly exert adverse effects on these networks’ operations and imperil effective and efficient performance. Damage caused by disruptions can appear in various forms, including cost hikes, profit losses, companies’ reputation loss, or even a combination of these. These necessitate developing novel methodologies to make the optimal decision to tolerate, respond, and recover against disruptions efficiently.
This project intends to apply optimisation and artificial intelligence (AI) techniques to develop an integrated decision support system (DSS) for resilient supply chain networks (SCNs). The outcome of this project will assist supply chain managers within this ever-changing environment and can be divided into several phases. The first phase focuses on analysing the supply chain network to evaluate the resilience performance and determine the system’s shortcomings. The influence of network characteristics on resilience performance is studied in the second phase to determine the most critical influential factors. The third phase devotes the application of artificial intelligence and machine learning techniques to ameliorate the resilience behaviour of the supply chain. Finally, the fourth phase will develop mathematical models aiming to design the resilience supply chains.
The efficient decision-making frameworks proposed by this research will increase the competitive ability of the organisations and empower them for their survival even under uncertain and disrupting conditions. This research will provide decision-makers with different primary tools to evaluate, improve, and design resilient SCNs. Using the resilience evaluation tool, decision-makers can assess the performance of their system to observe how it behaves when potential disruptions occur. Using the analysing tool, the practitioners are able to observe the effects of network characteristics on the system resilience and estimate the effects of possible disruptions on SCN. AI techniques empower supply chain managers to improve the resilience of their supply chain system. The designing tool provides the managers with an integrated decision-making framework to develop a new SCN that can efficiently respond, tolerate, and recover against disruptions.
Project start date: 13 September, 2021.
Expected finish date: March 2025.
Student: Farhad Habibi. Email: f.habibi@adfa.edu.au
Supervisors: Alireza Abbais and Ripon K Chakrabortty
