Thesis supervisor: György Kovács
Location of studies (in Hungarian): Institute of Manufacturing Science Abbreviation of location of studies: GYT
Description of the research topic:
Technical diagnosis and maintenance of machines and mechanisms are very important activities in order to provide continuous and reliable operation of the machines. The aim of the research is to define a lot of different parameters and conditions of machines, which can be part of a knowledge database and used to increase the effectiveness of technical services and investments. Due to it the Operators (engineers or technicians) can determine the adequate time period when the maintenance (or repair) must be performed, which provides the possibility to improve machines’ (or the whole facility) reliability, and the ability to make decisions at the best time.
The process of solving all the issues is related to determine the technical conditions, taking the appropriate decisions, and maintaining high reliability of machines is called “Technical diagnosis and maintenance of machines and mechanisms”.
The first step of the research is to build a knowledge database based on practical experiences of Experts relating to diagnoses of the technical conditions for the investigated machines. After it the most important parameters have to be defined which are relevant from the aspects of the analysis and diagnosis, at the same time the aspects of the improvement strategies and the actual maintenance tasks. Several Artificial Intelligence (AI) technologies (e.g. Expert System, Machine Learning, Deep Learning, etc.) are available to solve the before mentioned research aims.
During the research the following key activities have to be carried out:
1. Literature review and evaluation of the theoretical background.
2. Collection and systematic analysis of the practical experiences of the Experts.
3. A knowledge database has to be built based on the practical experiences and theoretical background.
4. The optimal method (e.g. Expert System, Machine Learning, Deep Learning, etc.) has to be selected which can be the most efficient during the diagnoses and maintenance of the investigated machines.
5. A new methodology will be developed for the reliability improvement of the investigated machines by the application of the selected AI technology.
Suggested publications:
[1] Malik, H.; Iqbal, A.; Yadav, A. K. (eds.): Soft Computing in Condition Monitoring and Diagnostics of Electrical and Mechanical Systems – Novel Methods for Condition Monitoring and Diagnostics, 2020, ISBN 978-981-15-1532-3, Springer
[2] Williams, J. H.; Davis, Neil, Drake, P. R. (eds.): Condition-based Maintenance and Machine Diagnostics, 1994, ISBN 978-0-412-46500-0, Springer
[3] Puppe, F.: Systematic Introduction to Expert Systems – Knowledge Representations and Problem-Solving Methods, 1993, ISBN 978-3-642-77973-2, Springer
[4] Yazdi, M.; Hafezi, P.; Abbassi, R.: A methodology for enhancing the reliability of expert system applications in probabilistic risk assessment. Journal of Loss Prevention in the Process Industries, 2019. (58), pp. 51-59.
[5] Zhou, Z. H.: Machine Learning, 2021, ISBN 978-981-15-1967-3, Springer
[6] Theissler, A.; Velázquez, J.P.; Kettelgerdes, M.; Elger, G.: Predictive maintenance enabled by machine learning: Use cases and challenges in the automotive industry. Reliability Engineering & System Safety, 2021. (215), pp. 1-21.
Number of students who can be accepted: 1
Deadline for application: 2023-06-30
2024. IV. 17. ODT ülés Az ODT következő ülésére 2024. június 14-én, pénteken 10.00 órakor kerül sor a Semmelweis Egyetem Szenátusi termében (Bp. Üllői út 26. I. emelet).
Login
