A novel iron loss reduction technique for distribution transformers based on a combined genetic algorithm - Neural network approach

Citation
Ps. Georgilakis et al., A novel iron loss reduction technique for distribution transformers based on a combined genetic algorithm - Neural network approach, IEEE SYST C, 31(1), 2001, pp. 16-34
Citations number
32
Categorie Soggetti
AI Robotics and Automatic Control
Journal title
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART C-APPLICATIONS AND REVIEWS
ISSN journal
10946977 → ACNP
Volume
31
Issue
1
Year of publication
2001
Pages
16 - 34
Database
ISI
SICI code
1094-6977(200102)31:1<16:ANILRT>2.0.ZU;2-0
Abstract
This paper presents an effective method to reduce the iron losses of wound core distribution transformers based on a combined neural network- genetic algorithm approach. The originality of the work presented in this paper is that it tackles the iron loss reduction problem during the transformer prod uction phase, while previous works were concentrated on the design phase. M ore specifically, neural networks effectively use measurements taken at the first stages of core construction in order to predict the iron losses of t he assembled transformers, while genetic algorithms are used to improve the grouping process of the individual cores by reducing iron losses of assemb led transformers. The proposed method has been tested on a transformer manu facturing industry. The results demonstrate the feasibility and practicalit y of this approach. Significant reduction of transformer iron losses is obs erved in comparison to the current practice leading to important economic s avings for the transformer manufacturer.