Abstract

The convergence of computational intelligence with engineering practice is catalysing a fundamental transformation in how complex systems are designed, analysed, and operated. This article provides a comprehensive review of the integration of artificial intelligence, machine learning, and advanced simulation methodologies within contemporary engineering applications, with particular emphasis on data-driven design frameworks and smart infrastructure development. Against the backdrop of digital transformation and Industry 4.0 paradigms, the article examines foundational computational intelligence techniques—including deep learning, evolutionary algorithms, and reinforcement learning—and their deployment across engineering domains. Key simulation methodologies, from finite element analysis to multiphysics modelling, are evaluated in terms of their integration with data-driven approaches and their role in creating digital twin environments. The development of smart infrastructure systems, including intelligent transportation networks, smart grids, and structural health monitoring platforms, is analysed through the lens of computational intelligence integration. Real-world industrial applications demonstrate the translational impact of these technologies across manufacturing, energy, and civil infrastructure sectors. The article concludes by identifying persistent challenges related to scalability, data interoperability, and ethical AI deployment, while outlining future research directions that align with sustainable development imperatives. This synthesis underscores the transformative potential of computational intelligence in advancing engineering capability and infrastructure resilience.