<p>With the growing complexity of next-generation military aircraft and the transition toward single-pilot operations in civil aviation, pilots are experiencing significantly increased workload across multiple dimensions, including situational awareness and decision-making demands. This creates an urgent need for accurate, real-time workload assessment technology. In this study, an ECG (Electrocardiogram)-based real-time workload assessment model was developed that prioritizes verifiable accuracy, continuous quantification, and real-time performance. The model builds upon fuzzy logic principles while addressing key limitations of traditional fuzzy models, such as the lack of standardized rule bases, poor adaptability, and excessive rule set sizes. Our methodological innovations include: (1) an example driven fuzzy rule generation approach, (2) feature normalization approach using pre-sampled boundary values, and (3) dynamic rule base completion approach based on actual inference inputs. Experimental results demonstrate the model’s effectiveness in providing continuous workload assessments (0–100 scale) based on ECG signal with a mean error of 17.05. The assessments showed strong correlation (<i>r</i> = 0.886) with subjective workload ratings, while achieving classification accuracies of 93.16% (binary) and 81.33% (ternary). These performance metrics compare favorably with existing methods while maintaining superior interpretability and real-time responsiveness, confirming the model’s practical viability for operational aviation environments. The key contribution lies in the synergistic integration of three specific techniques—example-driven rule generation, pre-sample normalization, and dynamic rule supplementation—which collectively enable the fuzzy model to achieve a unique balance of accuracy, interpretability, and computational efficiency for real-time assessment.</p>