IPAC2016 - List of Authors (Qian, Q.S.)

Paper	Title	Page
THPMW009	Data Mining Applied in Management of Heavy Ion Accelerator Power Supplies	3552
SUPSS104	use link to see paper's listing under its alternate paper code
	H. Zhang, D.Q. Gao, Q.S. Qian, P. Sun IMP/CAS, Lanzhou, People's Republic of China
	Scientific and effective management of power supplies could reduce the failure rate and improve the efficiency of the heavy ion accelerator. This paper shows how to introduce data mining into the intelligent management of heavy ion accelerator power supplies. A web site platform was developed to collect raw data. The raw data includes many kinds of information about one power supply's life cycle form its development to operation. Among which the failure records are particularly important. According to the attribute that the records are mostly nominal data, R software and SQL Server 2008 Business Intelligence Development Studio were chose as mining tools. R soft-ware was used to carry on the statistical characteristic analysis and SQL Server 2008 Business Intelligence Development Studio was used to find out association rules. Useful conclusions have been drawn. This work has laid a solid foundation to further establish the intelligent management system of heavy ion accelerator power supplies.
DOI •	reference for this paper ※ DOI:10.18429/JACoW-IPAC2016-THPMW009
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

Paper

Title

Page

THPMW009

Data Mining Applied in Management of Heavy Ion Accelerator Power Supplies

3552

SUPSS104

use link to see paper's listing under its alternate paper code

H. Zhang, D.Q. Gao, Q.S. Qian, P. Sun
IMP/CAS, Lanzhou, People's Republic of China

Scientific and effective management of power supplies could reduce the failure rate and improve the efficiency of the heavy ion accelerator. This paper shows how to introduce data mining into the intelligent management of heavy ion accelerator power supplies. A web site platform was developed to collect raw data. The raw data includes many kinds of information about one power supply's life cycle form its development to operation. Among which the failure records are particularly important. According to the attribute that the records are mostly nominal data, R software and SQL Server 2008 Business Intelligence Development Studio were chose as mining tools. R soft-ware was used to carry on the statistical characteristic analysis and SQL Server 2008 Business Intelligence Development Studio was used to find out association rules. Useful conclusions have been drawn. This work has laid a solid foundation to further establish the intelligent management system of heavy ion accelerator power supplies.

DOI •

reference for this paper ※ DOI:10.18429/JACoW-IPAC2016-THPMW009

Export •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)