Artificial Intelligence and Machine Learning Applications in Smart Infrastructure and Electrical Systems

AI and ML integration within smart infrastructure and electrical systems transforms the way classical engineering works due to improvements brought about in terms of efficiency, accuracy, and sustainability. It discusses the uses of AI-based approaches for predictive maintenance, optimization of energy resources, fault detection, and smart traffic management applications. Infrastructure monitoring and the efficiency of the power system significantly improve through the application of deep learning, reinforcement learning, and neural networks AI models. The data collection involved IoT sensors, AI-based predictive modeling, and real-time performance analysis. The results show that the use of AI-controlled systems outperforms traditional methods in structural monitoring, load forecasting, and grid management. These result in lower costs, increased safety, and efficient use of energy. Artificial intelligence also affects traffic systems, making them better at reducing congestion in the city and lowering emissions. Despite these strengths, challenges continue to be numerous due to the high computation requirements for implementation, high risks of cyber threats, and dependence on available data. These, however, may be overcome with hybrid AI models, blockchain-based security, and XAI explainability. The key integration of AI and sustainable energy is resiliency, as it can make the infrastructure of upgrading the grid structure, turn self-learning over time. The paper presents the opportunity of AI and its ability to revolutionize the practices of civil and electrical engineering for smarter, adaptive, and more sustainable infrastructures in the city. This will lead AI to constantly make its way toward the forefront through intelligent future infrastructures and global energy systems.