The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON SYSTEMS
Transactions ID Number: 42-248
Full Name: Zhongqing Wei
Position: Ph.D. Candidate
Age: ON
Sex: Male
Address: P.O. Box. No. 130, 15. Beisanhuan East Road, Beijing 100029 P.R. China
Country: CHINA
Tel:
Tel prefix:
Fax:
E-mail address: wains@126.com
Other E-mails:
Title of the Paper: The slow-changing alarm system of condition monitoring for rotating machinery
Authors as they appear in the Paper: Zhongqing Wei,Zhinong Jiang,Bo Ma,Xin Zhong
Email addresses of all the authors: wains@126.com
Number of paper pages: 10
Abstract: This paper mainly deals with the issue of early fault diagnosis for rotating machinery. An alarm strategy called the slow-changing alarm (SCA) is proposed to predict early fault of equipment timely and effectively. Meanwhile, the SCA system is the integration of adaptive lifting de-noising scheme, adaptive learning algorithm and decision-making strategy of alarm monitoring and diagnosis for the early fault of rotating machinery. In the paper, both the theories and realization of SCA system are thoroughly researched. Firstly, an adaptive lifting de-noising scheme is proposed to eliminate noise, and then the features of early fault are extracted from de-noised signal. Secondly, the key problem to implement on the SCA system is successfully resolved through adaptive learning algorithm and the decision-making strategy of SCA. To be specific, the alarm threshold of SCA system is obtained based on a novel adaptive learning algorithm, and the alarm based on features of!
vibration signals is activated according to decision-making strategy of SCA, while the relevant alarm log and data of SCA are instantly saved into database to analyze the causes of faults effectively, acquiring the early fault result synchronously. The proposed system has been applied in some petrochemical projects. In an engineering case, this system can preferably capture the early fault signal of rotating machinery, and considerably enhance the capability of predicting and diagnosing early fault.
Keywords: Rotating machinery; Condition monitoring; Early fault; Adaptive lifting de-noising scheme; Adaptive learning; Decision-making strategy; Slow-changing alarm
EXTENSION of the file: .doc
Special (Invited) Session:
Organizer of the Session:
How Did you learn about congress:
IP ADDRESS: 221.223.91.21
