Founded in 1971 >
Chinese Sci-tech Core Periodicals >
British Science Abstracts (SA, INSPEC) Indexed Journals >
United States, Cambridge Scientific Abstract: Technology (CSA: T) Indexed Journals >
United States, Ulrich's Periodicals Directory(UPD)Indexed Journals >
United States, Cambridge Scientific Abstract: Natural Science (CSA: NS) Indexed Journals >
Poland ,Index of Copernicus(IC) Indexed Journals >
International Standard Serial Number:
ISSN 1001-4551
Sponsor:
Zhejiang University;
Zhejiang Machinery and Electrical Group
Edited by:
Editorial of Journal of Mechanical & Electrical Engineering
Chief Editor:
ZHAO Qun
Vice Chief Editor:
TANG ren-zhong,
LUO Xiang-yang
Tel:
86-571-87041360,87239525
Fax:
86-571-87239571
Add:
No.9 Gaoguannong,Daxue Road,Hangzhou,China
P.C:
310009
E-mail:
meem_contribute@163.com
Abstract: Aiming at the problem that the diagnostic model was difficult to be constructed without fault data in industrial production, an intelligent fault diagnostic method for rotating machinery was proposed, which combined generative adversarial network (GAN) and mechanism character generative model (MCGM). Firstly, source domain data was employed to achieve domain adaptation to target domain data, and the common parameters reflecting the fault state of the equipment in the source domain according to the fault mechanism was extracted by the method. Then, the distribution model was built based on GAN, and the common parameters were extracted from the constructed distribution model. The selfadaptation of the sample generation model to the target domain was realized under the guidance of the fault mechanism which used the extracted common parameters and the target domain normal state data. Then, the fault diagnosis model of the target domain was obtained by inputting the virtual fault samples and the normal state samples of the target domain into the convolutional neural network training. Finally, a series of diagnostic tasks were constructed using standard data sets and laboratory bearing data to validate the intelligent diagnostic method of rotating machinery. The research results show that the average accuracy of the proposed method in diagnostic tasks reaches 92.5%, which is significantly higher than the average accuracy of the comparative methods.
Key words: mechanical operation and maintenance;rotating parts;domain adaptation (DA); fault diagnosis model; generative adversarial nets (GAN); mechanism character generative model (MCGM);failure mechanisms