A Dynamic Interval Type 2 Fuzzy Deep Reinforcement Learning Framework for Adaptive Supply Chain Risk Prioritization

Abstract Industry 4.0 digitalization has increased connectivity, efficiency and responsiveness of supply network; however, the digitalized nature of Industry 4.0 also increases exposure to potential cyber threats, system failures, data breaches and other types of disruption. Thus, the importance of supply chain resilience has emerged as a necessity for maintaining continuity and recovery under uncertainty. This research introduces a new dynamic risk prioritization framework using Interval-Type 2 Fuzzy Set (IT2FS) theory, deep reinforcement learning (DRL) and the VIKOR multi-criteria decision-making (MCDM) methodology to enhance Logistics 4.0 resilience. Unlike conventional MCDM methodologies which use fixed weights based upon fixed or rigid expert judgment, the proposed framework uses DRL to learn adaptive criterion weights through sequential interactions with the decision-ranking environment. Additionally, IT2FS captures the uncertainties associated with fuzzy expert assessment; meanwhile VIKOR identifies a compromise solution by generating a risk ranking from competing risks. The proposed framework has been tested using case studies within Pakistan’s logistics industry. The results have shown that the proposed framework provides more stable and consistent risk prioritization than traditional static benchmark frameworks. The top ranked risks are industry 4.0 implementation risk, technology related risk, economics related risk and operation related risk respectively. Also, there were several sub-risks related to cyber security, innovation adoption and integration at a lower rank of importance. Overall, the proposed framework presents an adaptive and explainable decision-support mechanism for Logistics 4.0 risk prioritization in uncertain environments; therefore, it can assist logistics managers in allocating limited resources more efficiently, thereby improving their ability to plan for resilient operations in increasingly dynamic conditions.

Authors

Institutions

Publication Details

Journal
Engineering Research Express
Published
2026-11-16
DOI
https://doi.org/10.1088/2631-8695/aec2a6
Primary Topic
Multi-Criteria Decision Making
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

A Dynamic Interval Type 2 Fuzzy Deep Reinforcement Learning Framework for Adaptive Supply Chain Risk Prioritization

Fahim ul Amin, Awais Yasin, Yassmine Ben Amarat
Engineering Research Express
Multi-Criteria Decision Making
article

A Dynamic Interval Type 2 Fuzzy Deep Reinforcement Learning Framework for Adaptive Supply Chain Risk Prioritization

Fahim ul Amin, Awais Yasin, Yassmine Ben Amarat
article en

Abstract

Abstract Industry 4.0 digitalization has increased connectivity, efficiency and responsiveness of supply network; however, the digitalized nature of Industry 4.0 also increases exposure to potential cyber threats, system failures, data breaches and other types of disruption. Thus, the importance of supply chain resilience has emerged as a necessity for maintaining continuity and recovery under uncertainty. This research introduces a new dynamic risk prioritization framework using Interval-Type 2 Fuzzy Set (IT2FS) theory, deep reinforcement learning (DRL) and the VIKOR multi-criteria decision-making (MCDM) methodology to enhance Logistics 4.0 resilience. Unlike conventional MCDM methodologies which use fixed weights based upon fixed or rigid expert judgment, the proposed framework uses DRL to learn adaptive criterion weights through sequential interactions with the decision-ranking environment. Additionally, IT2FS captures the uncertainties associated with fuzzy expert assessment; meanwhile VIKOR identifies a compromise solution by generating a risk ranking from competing risks. The proposed framework has been tested using case studies within Pakistan’s logistics industry. The results have shown that the proposed framework provides more stable and consistent risk prioritization than traditional static benchmark frameworks. The top ranked risks are industry 4.0 implementation risk, technology related risk, economics related risk and operation related risk respectively. Also, there were several sub-risks related to cyber security, innovation adoption and integration at a lower rank of importance. Overall, the proposed framework presents an adaptive and explainable decision-support mechanism for Logistics 4.0 risk prioritization in uncertain environments; therefore, it can assist logistics managers in allocating limited resources more efficiently, thereby improving their ability to plan for resilient operations in increasingly dynamic conditions.

Engineering Research Express
Hainan University (CN), National University of Technology (PK)
Industry, innovation and infrastructure
Multi-Criteria Decision Making
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon