Research Article
Fault Diagnosis of Vertical Pumping Unit Based on Characteristic Recalibration Residual Convolutional Neural Network
@INPROCEEDINGS{10.1007/978-3-030-72795-6_44, author={Youxiang Duan and Cheng Chang and Qifeng Sun and Chengze Du and Zhengyang Li}, title={Fault Diagnosis of Vertical Pumping Unit Based on Characteristic Recalibration Residual Convolutional Neural Network}, proceedings={Simulation Tools and Techniques. 12th EAI International Conference, SIMUtools 2020, Guiyang, China, August 28-29, 2020, Proceedings, Part II}, proceedings_a={SIMUTOOLS PART 2}, year={2021}, month={4}, keywords={Vertical pumping unit Deep learning Dynamometer card Fault analysis}, doi={10.1007/978-3-030-72795-6_44} }- Youxiang Duan
Cheng Chang
Qifeng Sun
Chengze Du
Zhengyang Li
Year: 2021
Fault Diagnosis of Vertical Pumping Unit Based on Characteristic Recalibration Residual Convolutional Neural Network
SIMUTOOLS PART 2
Springer
DOI: 10.1007/978-3-030-72795-6_44
Abstract
Rod pumping unit is the main equipment of oil exploitation. The automatic and intelligent of the management, control, running of pumping units are important goals for the construction of the smart oil field. The continuous development of network and deep learning technology provides strong support for the realization of intelligent pumping unit systems. The use of real-time collected pumping unit operating data for working condition supervision and intelligent analysis and decision-making has become an important part of the new generation of vertical pumping unit systems. This article is based on the collected operating data such as the dynamometer diagram of the pumping unit, using the deep learning technology, the intelligent working condition analysis, and the fault diagnosis model of the new generation vertical pumping unit are established. The training time of the model is short while the accuracy of identification and classification is high, which meets the practical application requirements well.
