Akademik Veri Yönetim Sistemi
Engineering Applications of Artificial Intelligence, cilt.159, 2025 (SCI-Expanded)
Electric vehicles (EVs) are the key concepts for advancing sustainable transportation by reducing dependence on fossil fuels and increasing energy efficiency. So, determining optimal locations for electric vehicle charging stations (EVCSs) is critical. This study proposes a two-phase methodology that integrates both qualitative and quantitative data to optimize and prioritize the EVCS locations. In Phase I, an extended Set Covering Model (SCM) is applied to optimize potential alternatives. In Phase II, a prioritization framework is developed for cases where infrastructure cannot be implemented simultaneously. To address uncertainty and subjectivity in expert evaluations, one of critical methods on Artificial Intelligence (AI) named fuzzy logic is used. For this aim, Z-numbers, which is an extension of fuzzy sets is employed, capturing both data vagueness and judgment hesitation. Accordingly, Interpretive Structural Modeling (ISM), Fuzzy Cognitive Mapping (FCM), and Technique for Order Preference by Similarity (TOPSIS) methods are extended with Z-numbers to evaluate and rank the optimized alternatives. The methodology is applied to a real-world case along the İstanbul–Ankara route in Türkiye. Results indicate that the criterion “needs to meet electric vehicle charging station demand” is the most influential, and “Erkanoğlu Resting Facility” is identified as the most suitable location. Sensitivity analysis confirms the robustness of the results under varying conditions. Overall, the proposed approach offers a comprehensive and reliable decision-making framework for intercity EVCS planning by effectively integrating optimization, expert judgment, and uncertainty modeling.