The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON INFORMATION SCIENCE AND APPLICATIONS
Transactions ID Number: 32-779
Full Name: Chenglong Tang
Position: Ph.D. Candidate
Age: ON
Sex: Male
Address: BaoSteel Research Institute,No.655 Fujing Road ,BaoShan District,Shanghai
Country: CHINA
Tel:
Tel prefix:
Fax:
E-mail address: tang_chenglong@sjtu.edu.cn
Other E-mails: tang_chenglong@hotmail.com
Title of the Paper: a kind of generalized fuzzy c-means clustering model and its applications in mining steel strip flatness signals
Authors as they appear in the Paper:
Email addresses of all the authors:
Number of paper pages: 17
Abstract: In this paper, the intelligent techniques are utilized to enhance the quality control precision in the steel strip cold rolling production. Firstly, a new control scheme is proposed, establishing the classifier of the steel strip flatness signals is the basis of the scheme. The fuzzy clustering method is used to establish the classifier. Getting the high quality clustering prototypes is one of the key tasks. Secondly, a kind of new fuzzy clustering model, generalized fuzzy C-means clustering (GeFCM) model, is proposed and used as the mining tools in the real applications. The results, under the comparisons with the results obtained by the basic fuzzy clustering model, show the GeFCM is robust and efficient and it not only can get much better clustering prototypes, which are used as the classifier, but also can easily and effectively mine the outliers. It is very helpful in the steel strip flatness quality control system in one real cold rolling line. Finally, it is!
pointed out that the new model¡¯s efficiency is mainly due to the introduction of a set of adaptive degrees wj (j=1¡n, and n is the number the data objects) and an adaptive exponent p which jointly affect the clustering operations. In nature, the proposed GeFCM model is the generalized version of the existing fuzzy clustering models.
Keywords: Steel strip flatness signals; Generalized fuzzy clustering; Outliers mining; Adaptive degrees; Adaptive exponent
EXTENSION of the file: .pdf
Special (Invited) Session:
Organizer of the Session:
How Did you learn about congress:
IP ADDRESS: 116.228.154.2
