Modern engineering systems are becoming increasingly interconnected, data-rich, and autonomous, requiring intelligent methods that can model complex dynamics, make optimal decisions under uncertainty, and enable reliable real-time control. My research lies at the intersection of data-driven intelligence, optimization, control, and sustainable energy systems, with the overarching goal of developing next-generation computational frameworks for intelligent decision-making in dynamical systems.

Our work integrates principles from systems and control theory, machine learning, optimization, and physics-informed modeling to develop predictive models and control strategies for nonlinear engineering systems. Current research focuses on data-driven system identification, Koopman operator theory, physics-informed and sparse learning, digital twins, model predictive control, and dynamic optimization for complex process and energy systems. These methodologies enable the development of interpretable, computationally efficient models that bridge first-principles knowledge with modern artificial intelligence.

A major emphasis of the group is the development of optimization and control algorithms for sustainable energy systems, including renewable energy integration, energy management, battery and hybrid energy storage systems, and intelligent operation of solar photovoltaic plants. We are particularly interested in uncertainty-aware optimization, autonomous decision-making, and learning-enabled control architectures that improve efficiency, reliability, and sustainability.

Ultimately, our vision is to advance data-driven intelligence for autonomous engineering systems, where learning, optimization, and control work together to enable safer, greener, and more resilient industrial and energy infrastructures.

• Data-driven Modeling & System Identification

• Intelligent Optimization & Decision Making

• Learning-based Dynamics and Koopman Operator Theory

• Optimal & Predictive Control

• Process Systems Engineering

• Renewable Energy Systems & Energy Management

• Physics-informed Machine Learning

• Digital Twins & Autonomous Engineering System