Quality improvement of individual cores of distribution transformers using decision trees

Hatziargyriou, N; Georgilakis, P; Spiliopoulos, D; Bakopoulos, J

dc.contributor.author	Hatziargyriou, N	en
dc.contributor.author	Georgilakis, P	en
dc.contributor.author	Spiliopoulos, D	en
dc.contributor.author	Bakopoulos, J	en
dc.date.accessioned	2014-03-01T01:14:06Z
dc.date.available	2014-03-01T01:14:06Z
dc.date.issued	1998	en
dc.identifier.issn	0969-1170	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/12864
dc.relation.uri	http://www.scopus.com/inward/record.url?eid=2-s2.0-0032154069&partnerID=40&md5=85e8e3cb4f19b38bbec5aba4a491c1b9	en
dc.subject	Decision trees	en
dc.subject	Individual core losses	en
dc.subject	Transformer quality improvement	en
dc.subject.classification	Computer Science, Artificial Intelligence	en
dc.subject.classification	Engineering, Electrical & Electronic	en
dc.subject.other	TRANSIENT STABILITY	en
dc.subject.other	POWER-SYSTEMS	en
dc.title	Quality improvement of individual cores of distribution transformers using decision trees	en
heal.type	journalArticle	en
heal.language	English	en
heal.publicationDate	1998	en
heal.abstract	The estimation of individual core losses of wound core distribution transformers (T/Fs) is very important because these constitute one of the main parameters of their quality and moreover core costs represent about 30% of the total T/F is very important because these constitute one of the main parameters of their quality and moreover core costs represent about 30% of the total T/F material cost. In addition, accurate calculations of individual core actual losses is extremely difficult, since actual losses show a divergence up to +/-20%, in relation with the theoretical individual core losses. In this paper a decision tree (DT) method is presented, suitable for the prediction of individual core losses in wound core distribution transformers (T/Fs) at the early stages of the production process. For the creation of the learning and test set actual industrial measurements are used. Data comprise grain oriented steel electrical characteristics, and quality control measurements of cores production line. The resultant DT presents a success rate of 94 %. Based on this DT, rules comprising the most important parameters and their threshold values can be derived. These are used to improve the quality of individual cores by reducing their actual losses.	en
heal.publisher	C R L PUBLISHING LTD	en
heal.journalName	International Journal of Engineering Intelligent Systems for Electrical Engineering and Communications	en
dc.identifier.isi	ISI:000077569500003	en
dc.identifier.volume	6	en
dc.identifier.issue	3	en
dc.identifier.spage	141	en
dc.identifier.epage	146	en