Exploring clustering tools in process systems engineering: Innovations, applications, and future directions

Abstract

Clustering techniques play a transformative role in optimizing complex systems across various domains, including Process Systems Engineering (PSE), healthcare, and network analysis. In PSE, these methods enhance fault detection, renewable energy systems, supply chain management, and chemical process optimization by simplifying large datasets, improving decision-making, and enabling sustainable solutions. Beyond industrial applications, clustering supports medical diagnostics and epidemiological studies, as well as social and technological network optimization, enabling better information flow and resource allocation. Researchers have expanded clustering applications by integrating them with other advanced machine learning techniques and real-time data analytics, fostering resilience and adaptability in dynamic environments. Despite these advancements, challenges persist, particularly in managing computational demands and developing adaptive, real-time clustering frameworks that address evolving landscapes. This review critically examines state-of-the-art clustering methodologies across these fields, comparing their contributions, limitations, and future potential. The discussion highlights interdisciplinary approaches and ethical considerations, emphasizing clustering’s role in tackling global challenges such as sustainability and energy transitions. Finally, the paper outlines emerging trends that will shape clustering applications in next-generation systems, digitalization, and artificial intelligence-driven optimization strategies.