Building and sustaining competence in maintenance: a prescriptive training model

Abstract

In the dynamic landscape of industrial workplaces, the demand for maintenance personnel capable of handling non-routine tasks has become increasingly crucial. However, traditional training programs, structured in pre-established sessions and relying on real equipment with expert technicians working alongside learners, are limited in their ability to establish a connection with the moment of effective performance and maintain effectiveness, which may diminish over time due to the forgetting phenomenon if conducted well in advance. Recognizing the pivotal roles of experience and training in mitigating human errors during maintenance tasks, as well as the limitations in current training practices, this study aims to propose a novel prescriptive training model and discuss practical managerial implications. This model leverages prescriptive analytics and cognitive-based learning models with the aim of generating training sessions tailored to the specific needs of maintenance tasks and calibrated to the operator’s expertise level. The ultimate goal is to develop the basic model for an adaptive training system, utilizing advanced technologies to enhance the performance of workers and reduce the risk of errors in non-routine tasks.