A visual management and augmented-reality-based training module for the enhancement of short and long-term procedural knowledge retention in complex machinery setup

Abstract

• Traditional training lacks in addressing the challenges of modern manufacturing. • This study integrates Visual Management and Augmented Reality for workers training. • A VMAR training is proposed to support complex machinery setup in process industry. • A comparison between the traditional training approach and VMAR is performed. • VMAR overcomes traditional training in short- and long-term knowledge retention. Proper training for operators is essential, given the complexity of modern manufacturing and the challenges posed by diverse worker demographics and high workforce turnover. Since conventional training methods are inadequate when considering the mentioned challenges, digital technologies and assistive devices can be used to improve information management. This work studies how the combination of Augmented Reality (AR) and Visual Management (VM) supports worker training by considering short- and long-term efficacy. The literature gaps on researching the training and knowledge retention of manufacturing workers using combined lean tools and digital technologies indicate that current studies focus on short-term training performed in laboratories, overlooking the integration of VM and AR for industrial training. Thus, the authors developed and validated in practice a VMAR-based training module for the setup of complex machinery in the process industry. To assess its efficacy, a comparison between a test group and a confirmation group of company’s workers has been performed. The number and types of setup error have been collected and analysed to evaluate and compare short- and long-term procedural knowledge retention. The results reveal that the VMAR-based training module better supports workers both in the short- and long-period compared with traditional working procedures. Furthermore, the analysis demonstrates the inefficacy of traditional approaches in properly supporting the training of complex machinery setups considering the study’s application. Future works should address the assessment of knowledge retention by considering a longer period, as well as on physiological data collection to better understand which elements of the training module are most crucial to the transfer of knowledge.

Topics & Concepts