The evolution towards Industry 5.0 (I5.0) has increased the complexity of industrial environments, making effective operator-task matching particularly crucial in maintenance activities. However, existing matching models often fail to incorporate operator features and lack validation in real-world settings. To address these gaps, this study presents an analytical model that integrates expert evaluations and operator self-assessments to assign maintenance activities to the most suitable operators. The developed model was validated through a lab-based case study involving 22 participants, using completion time, number of restart attempts, and reporting accuracy as performance indicators. A global key indicator was then estimated for each operator by normalising the sum of the three indicators to assess the model’s reliability in predicting the correct operator-task matching. The results indicate that, although the model is more accurate in predicting the performance of less experienced operators, its reliability is strongly influenced by the self-assessment test, which, in some cases, led to overestimating the actual performance of the operators. Nonetheless, the model shows promising potential for supporting adaptive operator-task matching in I5.0 work environments.
Grimaldi et al. (Thu,) studied this question.