关键词: 职业韧性, 民航飞行员, 安全绩效, 模糊集定性比较分析(fsQCA), 机器学习

Abstract:

To enhance the safety performance of civil aviation pilots, this study constructs a three-dimensional analytical framework for career resilience based on affect, behavior, and cognition(ABC). Integrating machine learning with fsQCA, it empirically analyzes 229 questionnaire responses from Chinese civil aviation pilots. Building upon the measurement of antecedent variable importance weights using the random forest algorithm, the fsQCA method is further applied to decipher the impact mechanisms of different condition configurations on safety performance.The results indicated that no single factor constitutes a necessary condition for either high or non-high safety performance; however, learning willingness and cooperation consciousness play key roles in driving civil aviation pilots to achieve high safety performance. Five configurational paths leading to high safety performance are identified and categorized into three patterns: “emotionally empowered-behaviorally oriented,” “resilient collaboration-behaviorally dominant,” and “efficiency driven-intrinsically motivated.” In contrast, two configurational paths leading to non-high safety performance are classified as “behavior-atrophy” and “affection-deficiency” types. Furthermore, substitution relationships exist among conditional variables in the five configurations for high safety performance.

Key words: career resilience, civil aviation pilots, safety performance, fuzzy-set qualitative comparative analysis(fsQCA), machine learning