Optimizing AI-Based System Architecture for Industrial Automation in the Industrial Era 5.0

Abstract

The development of Industry 5.0 demands the integration of artificial intelligence (AI) in industrial automation to improve operational efficiency, flexibility, and sustainability. AI-based system architecture needs to be optimized to be able to answer the challenges of production complexity and adaptability to global market dynamics. This research aims to identify key needs, formulate effective strategies, and develop conceptual models of optimizing AI system architecture in the context of modern industry. The research method used is an exploratory qualitative approach through in-depth interviews, participatory observations, and documentation analysis in the manufacturing industry sector that has adopted AI technology. The results show that the key needs include interoperability, scalability, adaptive security, and continuous learning. Effective integration strategies are found through the incorporation of edge-cloud computing, the use of big data for predictive analysis, and the strengthening of blockchain-based data security principles. The proposed conceptual model integrates five main pillars, namely system modularization, cloud-based AI orchestration, adaptive security, standard interoperability, and reinforcement learning-based learning. This study concludes that the optimization of AI architecture is able to encourage the industry to become more adaptive, efficient, and sustainable in the Industry 5.0 era. The implications of the research provide practical contributions for companies in building intelligent production ecosystems, as well as theoretical contributions in the form of developing new integrative frameworks in the study of industrial AI.