A fault diagnosis method based on the Support Vector Machine in rod pumping systems
2021 ◽
Vol 2125
(1)
◽
pp. 012004
Keyword(s):
Abstract Monitoring the working status of the sucker rod pump is an important part in petroleum engineering. With the development of artificial intelligence technology, more methods have been applied to the fault diagnosis of rod pumping systems. An evolutional fault diagnosis method based on Support Vector Machine (SVM) in sucker rod pumping systems is proposed. Fourier descriptors and Light Field compression algorithm are used in this method to extract the graphic features of the indicator diagram. SVM is used to build fault classification model. This method is verified experimentally through data of indicator diagrams and the results show that it has a shorter training time and higher accuracy.
2011 ◽
Vol 66-68
◽
pp. 1982-1987
2020 ◽
Vol 12
(1)
◽
pp. 168781401989956
Keyword(s):
2019 ◽
Vol 2019
(13)
◽
pp. 215-218
◽
Keyword(s):