A Framework for Blockchain-Based Data-Driven Fault Tolerant Control in Industrial Internet of Things Enabled Smart Factories

Abstract

This thesis presents two novel frameworks, the Blockchain-Based Data-Driven Fault-Tolerant Control (BB-DD-FTC) and Blockchain-Driven Deep Reinforcement Learning (BlockDRL), designed to enhance cybersecurity and optimize resource management within Industry 4.0-enabled smart factories. The BB-DD-FTC framework leverages a blockchain-integrated DD-FTC to detect and mitigate cyber threats effectively, enhancing the robustness of IIoT systems. Simultaneously, the BlockDRL framework, utilizing DRL, innovatively addresses the challenges of computational and data storage efficiency, facilitating autonomous, optimal decision-making without reliance on third-party verification. These frameworks are rigorously validated through simulation experiments, demonstrating their efficacy in enhancing operational resilience and efficiency in smart manufacturing environments under various cyber-physical threat scenarios.