The role of Digital Twins in future transportation challenges

Abstract

Students enrolled in technical education programs, such as Aeronautical Engineering Technology, pursue careers in aviation, aerospace, and commercial space industries, encompassing physical and digital work environments. Gaining knowledge in a broader range of subjects, including digital twin settings, is crucial for contextual learning and generating graduates with the level of proficiency the industry demands. Crow and Dabars (2020) highlight the significance of instructional innovation in their analysis of the fifth-wave history of American colleges. There is a demand for the modification of conventional academic processes in order to better cater to the external needs of retraining and upskilling both current workers and recent graduates. The aviation and aerospace sectors have consistently incorporated the Industrial Internet of Things (IIoT), Digital Twins, Big Data frameworks, automation, and robotics in diverse capacities into their routine operations over an extended period. The rapid progress in computer and sensor capabilities has facilitated the widespread adoption of many data science methods, such as the digital thread, digital twin, edge computing, machine-to-machine learning (M2M), and Artificial Intelligence (AI). Educational institutions, including prominent colleges like Purdue, must integrate digital thread and digital twin technologies into the learning framework beyond the introductory levels. For graduates to possess the necessary skills to join the workforce with a high level of preparedness, it is imperative to integrate Digital Twins into the learning cycle. The Purdue University CREATE approach for Augmented, Virtual, and Mixed Reality Simulation and Digital Twins is centered around enhancing the efficacy and efficiency of aviation training programs on a global scale, specifically the Competency-Based Training and Assessment (CBTA) framework. This approach aims to achieve this by offering a more authentic and immersive learning experience proposal, streamlining the training and certification processes, and facilitating the transition to an Artificial Intelligence (AI) – Digital Twins environment. The present study also focuses on reducing residual risk within the 'AI black box.' The analysis and evaluation of the difficulties of implementation of Artificial Intelligence (AI) were conducted within the framework of Digital Twins.