Fault Diagnosis Method Based on Dynamic Axis Nucleation KPLS for Pumping Unit

Wei Zhou,Zuojin Li,Bo Wang,Juan Liu,Jianyang Shi

doi:10.1109/access.2019.2958547

Abstract

Fault diagnosis of pumping unit system has long been a challenging issue owing to the system that exhibits nonlinearity, coupled parameters and time-varying in the production process. In this paper, a novel fault diagnosis method based on dynamic axis nucleation kernel partial least squares (DANKPLS) is proposed for pumping unit. First, the multiple dichotomous regression (MDR) model is established to reflect the hidden dynamic relationship between variables efficiently. Then, a novel axis nucleation kernel partial least squares method is proposed to map the principal axis into a high-dimensional space. In particular, the correlation of the data can be further and clearly represented. Finally, the proposed method is applied to the pumping unit system. Experimental results show the effectiveness and favorable diagnosis rate in false alarm and missing alarm.

Highlights

Pumping unit systems are the most common artificial lift methods used in oil production
Inspired by above analysis of multivariate statistical process monitoring (MSPM), a novel dynamic axis nucleation kernel partial least squares (DANKPLS) algorithm is developed for fault diagnosis in the pumping unit system
DANKPLS ALGORITHM In section 2, a new augmented matrix D can be obtained based on the multiple dichotomous regression (MDR) method; the new input data D have good dynamic performance

Summary

Introduction

Pumping unit systems are the most common artificial lift methods used in oil production. INDEX TERMS Fault diagnosis, axis nucleation partial least squares, multiple dichotomous regression, pumping unit. W. Zhou et al.: Fault Diagnosis Method Based on Dynamic Axis Nucleation KPLS for Pumping Unit industrial processes.

Results

Conclusion