Explainable AI-Based Decision Support Systems for Sustainable Industrial Automation

Abstract

The rapid emergence of Industry 4.0 and the transition toward Industry 5.0 have transformed manufacturing systems into highly interconnected, data-driven, and intelligent ecosystems. Artificial Intelligence (AI) has become a fundamental enabler of industrial automation through predictive maintenance, process optimization, quality assurance, resource allocation, and autonomous decision-making. However, many industrial AI models operate as black-box systems, limiting transparency, interpretability, and trust among stakeholders. This challenge is particularly significant in safety critical industrial environments where decision reliability directly influences operational efficiency, sustainability, and economic performance. Explainable Artificial Intelligence (XAI) has emerged as a promising solution to enhance transparency and accountability in automated decision making systems. This study proposes an Explainable AI-Based Decision Support System (XAIDSS) for sustainable industrial automation. The proposed framework integrates machine learning algorithms, explainability mechanisms, industrial Internet of Things (IIoT) infrastructures, and sustainability assessment modules to improve operational efficiency while ensuring interpretability. The study develops a conceptual architecture for industrial decision support and evaluates its potential impact on predictive maintenance, energy optimization, production scheduling, and fault diagnosis. Results indicate that incorporating explainability mechanisms significantly improves decision confidence, regulatory compliance, and human-machine collaboration. The proposed framework contributes to the development of transparent, sustainable, and resilient industrial ecosystems capable of supporting next-generation intelligent manufacturing environments.