Civil Aircraft Structural Maintenance (CASM) decision-making for out-of-manual repairs is a critical task fraught with uncertainty, relying heavily on subjective expert knowledge. Existing Case-Based Reasoning (CBR) systems, while useful, often struggle to objectively handle the ambiguity and expert hesitation inherent in case data. To address this challenge, this paper proposes a novel CBR framework that integrates a new Intuitionistic Fuzzy Entropy (IFE) measure to objectively determine the weights of case features. Our proposed IFE formula is specifically designed to rationally model the degrees of membership, non-membership, and hesitation, addressing key limitations of existing entropy measures. The framework’s efficacy was demonstrated using real-world CASM cases. The results show that our method not only identified the most similar primary case (similarity = 0.951) with high accuracy, consistent with other methods, but also uniquely retrieved a crucial secondary case (similarity = 0.607) that was overlooked by other approaches. This secondary case, sharing a critical underlying failure mode (frame fatigue), provides engineers with a richer, more diverse set of potential repair solutions. This study establishes a robust methodological foundation for handling uncertainty in engineering CBR systems and demonstrates its potential to enhance the safety and efficiency of aircraft maintenance.
Lin et al. (Thu,) studied this question.