![](http://www.meem.com.cn/static/fore_en/images/logo_01.jpg)
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: In shale gas exploitation, fracturing pump check valves were prone to breakage and frequently replaced. The current check valve detection methods had problems such as relying on manual experience, requiring special personnel to monitor, low fault location accuracy, and full inspection and full replacement. Aiming at these problems, taking Sinopec’s diesel-driven fracturing pump as an example, a method based on the combination of multi-feature fusion and multilayer perceptron (multilayer perceptron, MLP) was used to diagnose the fault of the one-way valve to solve the problems in the manual inspection of the pump. Firstly, multiple acceleration sensors and pressure sensors were used to collect the working status of the fracturing pump under different one-way valve failures, and the relevant statistical characteristics in the time domain and frequency domain from the acquired data were calculated. Principal component analysis was used to extract the main feature components to form a new feature vector. Finally, the advantages of multi-layer perceptrons in processing nonlinear data were used for fault classification and identification, and the fault of one-way valve of the fracturing pump was accurately diagnosed. The research results show that the method based on the combination of multifeature fusion and multi-layer perceptron can accurately identify multiple types of faults and is subject to working conditions. The degree of influence is low, and the average diagnostic accuracy rate reaches 99.6%. The features calculated by the multi-sensor are processed to make different one-way valve faults separable.
Key words: fracturing pump; oneway valve; fault detection; feature fusion; multilayer perceptron(MLP)
PAN Ling-yong. Fault diagnosis method of fracturing pump valve based on MLP of multi-feature fusion[J].Journal of Mechanical & Electrical Engineering, 2021,38(10):1299-1304,1310.
![](http://www.meem.com.cn/static/fore_en/images/foot_01.png)