University of West Attica
Συμβολή στην εκτίμηση λειτουργικής κατάστασης εξοπλισμού και εγκαταστάσεων υψηλών τάσεων (Υ.Τ.) με χρήση ειδικών μετρητικών συστημάτων και τεχνικών τεχνητής νοημοσύνης
Abstract
dc:descriptionThis PhD thesis aims to develop an innovative model for the assessment of the operational condition of high-voltage equipment, using artificial intelligence techniques and special measurement systems. In the context of this thesis emphasis is given on high voltage oil power transformers. The proposed model is based on a innovative measuring system of electric current and voltage with the possibility of analyzing harmonic and superharmonic components and additionally the possibility of telemetry. In order to fully document the need for the implementation of such a solution, a literature review is initially carried out (Chapter 1) in the individual scientific areas examined by this PhD thesis. The literature review concerns the critical high voltage equipment and its monitoring using special measurements. This equipment includes cables, insulators, switches, measuring transformers and high voltage oil power transformers. In addition, a literature review is conducted on the use of artificial intelligence techniques that have been applied to date and aim to assess the operational condition of oil power transformers. The phenomena that take place in high-voltage equipment and stress it are then examined (Chapter 2). The description of these phenomena is of great importance and should be included in the proposed model of this PhD thesis. For these reasons, the definitions of conductors and insulators and the ways of polarizing the materials are given. In addition, the losses in dielectrics are examined, the effect of the form of the applied electric field on dielectrics, the basic properties of electrical insulating materials are described as well as the mechanisms of the breakdown of insulating materials. The next chapter (Chapter 3) describes the main parts and categories of power transformers. They are categorized according to the basic insulating material, in proportion to the conservator, to the type of bushings and to the cooling method. The most critical and common failure points of oil power transformers, the types of measurements made on the various parts of the transformers and their acceptable limits are also presented. The chapter finally presents the main categories of partial discharges that occur in power transformers. Chapter 4 presents details, both theoretical and constructional, of the harmonic and supraharmonic analysis system developed and proposed. First, a brief literature review is made on corresponding measurement systems and harmonic analysis systems. Next is the confirmation of the existence of the supraharmonics through real measurements made in the context of this thesis. In the same chapter, the mathematical description of the Fourier transform and the algorithms commonly used for its fast calculation are presented. The sampling system and the importance of the sampling rate of harmonic analysis systems are also described, as well as the implementation of the system in both hardware and software terms. Finally, the chapter presents the results of the tests and a comparison is made with corresponding measurements made using certified laboratory equipment. In Chapter 5, a brief literature review to the scientific field of artificial intelligence and its subcategories is first made. The difference between artificial intelligence and machine learning is described and then the categories of machine learning are analyzed. In addition, the theoretical description of neural networks and their various structures is given, while the basic algorithm is described according to which the structure of the neural network, that was finally used, is optimized. The results of the specific algorithm and the final optimized structure of the neural network are presented, and finally, the description and analysis of another proposed classification system of partial discharges using harmonic analysis in the voltage waveform is described. In Chapter 6, which is also the last chapter of the PhD thesis, the conclusions are presented as well as some suggestions for future improvements.
Degree
thesis:*- Grantor dc:publisher
- University of West Attica
- Year dc:date
- 2025
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Barkas, Dimitrios
- Μπάρκας, Δημήτριος
Subjects
dc:subject × 18- Ανάλυση Αρμονικών
- Διηλεκτρικά υλικά
- Μετασχηματιστές ισχύος
- Νευρωνικά δίκτυα
- Τεχνητή νοημοσύνη
- Υψηλές τάσεις
- Artificial intelligence
- Dielectric materials
- Harmonic analysis
- High voltage
- Neural networks
- Power transformers
- Επιστήμη Ηλεκτρολόγου Μηχανικού, Ηλεκτρονικού Μηχανικού, Μηχανικού Η/Υ
- Επιστήμες Μηχανικού και Τεχνολογία
- Ηλεκτρική και Ηλεκτρονική μηχανική
- Electrical Engineering, Electronic Engineering, Information Engineering
- Engineering and Technology
- Electrical and Electronic Engineering
Rights
- Language dc:language
- gre
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/59436