Loading
ICSEST-Canada 2026, an international platform connecting researchers, industry leaders, and policymakers to advance sustainable engineering, smart technologies, and interdisciplinary innovation.
Send Email
Venue
Research and Education Promotion Association (REPA) California, USA
Biography
Ph.D., P.Eng., FRSC, FEIC, FCSME, FASME, FIEF, FCAE, FCSSE
Past President, Engineering Institute of Canada
Ontario Tech University
Abstract: Sustainable development is a fundamental objective for human and societal progress, with energy sustainability serving as a central pillar for achieving long-term environmental and economic stability. This keynote examines the critical role of energy in modern societies, emphasizing its pervasive influence on economic development, quality of life, and environmental impact. The presentation explores key factors required to transition toward sustainable energy systems, including the selection of appropriate energy resources based on sustainability criteria, the promotion of sustainable energy carriers, and the enhancement of energy conversion and utilization efficiency. It further highlights the importance of integrating environmental stewardship into energy planning and operations. In addition, broader sustainability dimensions such as economics, equity, land use, lifestyle, sociopolitical factors, and population dynamics are discussed. Practical examples of energy sustainability measures are presented, along with strategic insights into pathways for achieving sustainable development. The keynote concludes by outlining both technological and policy-oriented approaches to advancing global energy sustainability.
Ph.D., MBA, CEng, SMIEEE, MIET
Research & Innovation Chair (RIC)
Research and Education Promotion Association (REPA)
Abstract: This keynote presents an artificial intelligence–driven framework for optimizing emissions and improving energy efficiency in combined-cycle power plants (CCPPs). The proposed approach integrates thermodynamic modeling, data analytics, and neural-network-based optimization to address the critical challenge of reducing nitrogen-oxides (NOx) emissions while maintaining operational performance. The framework utilizes four years of high-resolution operational data from a 150 MW gas-turbine power plant in north-western Türkiye, analyzed using Neural Designer and validated through a Python-based simulation pipeline. It transitions from deterministic parameter-based formulations to data-driven predictive modeling through a structured sequence of design and validation stages. An online surrogate-simulation engine enables rapid prediction of NOx variations without iterative optimization, achieving an optimized gas-turbine-exhaust pressure of PGTE=17.844 mbar and an outlet NOx concentration of CNOx=78.66 mg·m−3. The model employs a quasi-Newton (BFGS) learning algorithm with L2-regularization to ensure high predictive stability across varying operating conditions. Sensitivity analysis identifies turbine inlet temperature and ambient pressure as dominant variables influencing emission intensity. The framework demonstrates strong adaptability to advanced energy configurations, including hydrogen-enriched fuels, biomass co-firing, and carbon capture systems.
