Fault-Diagnosis for Reciprocating Compressors Using Big Data

Fault-Diagnosis for Reciprocating Compressors Using Big Data

Petroleum industry

Big data

Failure analysis

Learning systems

Fault detection

Reciprocating compressors

Reciprocating compressors are widely used in the petroleum industry, and a small fault in reciprocating compressors may cause serious issues in operation. Monitoring and detecting potential faults help compressors to continue normal operation. This paper proposes a fault-diagnosis system for compressors using machine-learning techniques to detect potential faults. The system has been evaluated using 100TB operation data collected from China National Offshore Oil Corporation, and the data are first de-noised, coded, and then SVM classification is applied, with 50% of data used for training, the remaining for testing. The results demonstrated that the system can efficiently diagnose potential faults in compressors with 80% accuracy. 2016 IEEE.

72-81

Keerqinhu

Qi, Guanqiu

Tsai, Wei-Tek

Hong, Yi

Wang, Wenxiang

Hou, Guangxin

Zhu, Zhiqin

2nd IEEE International Conference on Big Data Computing Service and Applications, BigDataService 2016, March 29, 2016 - April 1, 2016

2016

conferencePaper

10.1109/BigDataService.2016.27

http://dx.doi.org/10.1109/BigDataService.2016.27