Abstract
A fault diagnosis method based on deep belief network (DBN) is to solve the high fault rate of a submersible reciprocating pumping unit, and to address the difficulties in measurement of downhole operation parameters. The running current of the submersible motor is obtained directly through the ground equipment. The running current is used as the characteristic parameter of the operation status of the submersible reciprocating pumping unit. The vector that is extracted from the running current is used as the input data for the fault diagnosis model. The DBN is firstly trained by the original currents, and then the fault feature's gradual extraction is realized through the multi-layered structure, thereby allowing the fault diagnosis of the submersible reciprocating pumping unit. In the experiment, the fault diagnosis model is tested by simulation samples. Results show that the model can extract the fault feature from the running currents of the submersible motor and implement the fault diagnosis effectively.
Highlights
Considering the development of oilfields in China has entered the middle and late stages, a lifting technology of submersible reciprocating pumping unit designed to improve the extraction benefits of oilfields.Rod pumping is one of the traditional methods of oil production in the world petroleum industry, and it is the main method in oil production engineering
The training process of deep belief network (DBN) classifier includes unsupervised layer-bylayer pre-training and supervised fine tuning: First, in the unsupervised pre-training, raw data is sent to the first Restricted Boltzmann Machine (RBM) visual layer as a vector, and the value will pass to the hidden layer through the RBM network
The results show that the DBN can facilitate the feature extraction process of the original data, and effectively distinguish the overlapping eigenvalues
Summary
Considering the development of oilfields in China has entered the middle and late stages, a lifting technology of submersible reciprocating pumping unit designed to improve the extraction benefits of oilfields. Zhang: Fault Diagnosis Method for Submersible Reciprocating Pumping Unit Based on DBN. Hu proposed the algorithm of defect classification of sphere-structured support vector machines, constituting the multi-breakdown sorter to carry on the hydraulic pump’s fault recognition [9] These fault diagnosis methods generally need feature extraction algorithms, such as wavelet analysis, variation modal decomposition, singular value decomposition, empirical mode decomposition, local mean decomposition, and approximate entropy [10]–[13]. VOLUME 8, 2020 can automatically extract the fault feature information from the original running data of the submersible reciprocating pumping unit. Avoid uncertainty of fault feature extraction from human participation and the dependence on expert diagnosis experience This method combines fault feature extraction and classification processes to realize the classification of original fault data
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
