Dr. Oksana Shpak is an Associate Professor in the Department of Computerized Automation Systems at Lviv Polytechnic National University, Ukraine. She earned her Ph.D. in Technical Sciences in 2013, specializing in methods for assessing the quality of diesel and biodiesel fuels. Her research interests include systems analysis, computer engineering, artificial intelligence, machine learning, innovative information technologies, business process modeling, and database systems. Dr. Shpak has authored numerous scientific publications, including SCOPUS-indexed papers, conference proceedings, and educational methodology materials. She is actively involved in research, teaching, curriculum development, and international academic collaborations, contributing to advancements in intelligent transportation systems, fuel quality monitoring, and AI-based engineering applications.      

Application of a Genetic Algorithm for Determining the Optimal Blend of Diesel and Biodiesel Fuel for Various Types of Transportation   The growing need to ensure energy security, reduce greenhouse gas emissions, and transition to sustainable energy sources has intensified the search for effective alternatives to conventional fossil fuels. One of the most promising approaches is the use of biodiesel fuel and its blends with petroleum-based diesel fuel. However, determining the optimal ratio of blend components is a complex multi-criteria problem that depends on vehicle type, operating conditions, engine performance characteristics, environmental indicators, and economic feasibility. This study proposes the application of a genetic algorithm as an artificial intelligence tool for identifying the optimal blend of diesel and biodiesel fuel for different categories of transportation, including passenger vehicles, freight transport, agricultural machinery, and public transportation systems. The developed model incorporates multiple optimization criteria, including fuel efficiency, emission reduction, fuel cost, availability of biodiesel feedstock, and the impact on engine durability. The genetic algorithm implements an evolutionary optimization approach through the processes of selection, crossover, and mutation of candidate fuel blends, enabling the discovery of near-global optimal solutions in the presence of numerous parameters and constraints. The obtained results demonstrate the feasibility of generating recommendations regarding the optimal biodiesel content for specific vehicle types and operating scenarios. The proposed approach integrates artificial intelligence techniques, computational modeling, and energy system analysis and can serve as a decision-support tool for sustainable mobility, bioenergy development, and the enhancement of energy resilience in the transportation sector under contemporary economic, environmental, and geopolitical challenges. Keywords: artificial intelligence, genetic algorithm, biodiesel, diesel fuel, optimization, computational modeling, sustainable development, transportation systems, energy efficiency, bioenergy.