A Knowledge Based Educational (KBEd) framework for enhancing practical skills in engineering distance learners through an augmented reality environment

Vijay, Venkatesh Chennam (2017) A Knowledge Based Educational (KBEd) framework for enhancing practical skills in engineering distance learners through an augmented reality environment. Doctoral thesis, Birmingham City University.

PhD Thesis.pdf

Download (7MB)


The technology advancement has changed distance learning teaching and learning approaches, for example, virtual laboratories are increasingly used to deliver engineering courses. These advancements enhance the distance learners practical experience of engineering courses. While most of these efforts emphasise the importance of the technology, few have sought to understand the techniques for capturing, modelling and automating the on-campus laboratory tutors’ knowledge. The lack of automation of tutors’ knowledge has also affected the practical learning outcomes of engineering distance learners. Hence, there is a need to explore further on how to integrate the tutor's knowledge, which is necessary for imparting and assessing practical skills through current technological advances in distance learning. One approach to address this concern is through the use of Knowledge Based Engineering (KBE) principles. These KBE principles facilitate the utilisation of standardised methods for capturing, modelling and embedding experts’ knowledge into engineering design applications for the automation of product design. Hence, utilising such principles could facilitate, automating engineering laboratory tutors’ knowledge for teaching and assessing practical skills. However, there is limited research in the application of KBE principles in the educational domain. Therefore, this research explores the use of KBE principles to automate instructional design in engineering distance learning technologies. As a result, a Knowledge Based Educational (KBEd) framework that facilitates the capturing, modelling and automating on-campus tutors’ knowledge and introduces it to distance learning and teaching approaches.

This study used a four-stage experimental approach, which involved rapid prototyping method to design and develop the proposed KBEd framework to a functional prototype. The developed prototype was further refined through internal and external expert group using face validity methods such as questionnaire, observation and discussion. The refined prototype was then evaluated through welding task use-case. The use cases were assessed by first year engineering undergraduate students with no prior experience of welding from Birmingham City University. The participants were randomly separated into two groups (N = 46). One group learned and practised basic welding in the proposed KBEd system, while the other learned and practised in the conventional on-campus environment. A concurrent validity assessment was used in determining the usefulness of the proposed system in learning hands-on practical engineering skills through proposed KBEd system. The results of the evaluation indicate that students who trained with the proposed KBEd system successfully gained the practical skills equivalent to those in the real laboratory environment. Although there was little performance variation between the two groups, it was rooted in the limitations of the system’s hardware. The learning outcomes achieved also demonstrated the successful application of KBE principles in capturing, modelling and transforming the knowledge from the real tutor to the AI tutor for automating the teaching and assessing of the practical skills for distance learners. Further the data analysis has shown the potential of KBEd to be extendable to other taught distance-learning courses involving practical skills.

Item Type: Thesis (Doctoral)
Additional Information: “Dream is not that you see in sleep, dream is something that does not let you sleep” - A.P.J Abdul Kalam I would like first to say a huge thank you to my Director of Studies Professor Mel Lees for all his support and for keeping me hungry to learn new things while undertaking my research. Without his guidance and encouragement, this PhD would not have been achievable. I would also like to thank my second supervisors, Parmjit Chima and Professor Craig Chapman, for their support and constant feedback. In particular, my deepest gratitude goes to Craig for providing me with the best facilities and training in the Knowledge-Based Engineering (KBE) Lab. Thanks are also due to KBE Lab team members Dr Krishna Sapkota, Dr William Byrne, Dr Raju Pathmeswaran and Dr Feroz Farazi for helping me in my implementation. I am thankful to the engineering technicians Martin Reeves and David Philips at Birmingham City University for their endless support in collecting data from the students. My sincere thanks also go to Professor Peter Larkham, Professor Hanifa Shah and Sue Witton, who gave access to the research facilities. Without their precious support, it would not have been possible to conduct this research. I am thankful to Steve Gould for his comments and suggestions in improving my thesis. I am also very grateful to the Faculty of Computing, Engineering and the Built Environment (CEBE) of Birmingham City University for funding the research project. I would like to thank my friends; Dr Gerald Feldman, Dr Mani Seethapathy and Sikander Khan for their continuous encouragement. My special thanks also go to my mum, dad and sister for their support and prayers at every stage of my research. Last, but by no means least, I would like to thank my wife Zhao Man. Without her love and kind words, this thesis would not have been completed. Finally, thank you God, for helping me through all the difficulties
9 February 2017Completed
Uncontrolled Keywords: Knowledge capturing, Knowledge modelling, Knowledge based engineering, Artificial Intelligence, Ontology; Augmented reality, Practical Skills, Engineering laboratory and Engineering distance learning
Subjects: CAH11 - computing > CAH11-01 - computing > CAH11-01-04 - software engineering
CAH11 - computing > CAH11-01 - computing > CAH11-01-05 - artificial intelligence
Divisions: Doctoral Research College > Doctoral Theses Collection
Depositing User: Kip Darling
Date Deposited: 13 Mar 2019 13:28
Last Modified: 12 Jan 2022 12:58
URI: https://www.open-access.bcu.ac.uk/id/eprint/7223

Actions (login required)

View Item View Item


In this section...