Open AccessFault Diagnosis of Gear Pump Based on Sparse Representation
Author(s) -
Zhiyin Han
Publication year - 2019
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/563/3/032003
Subject(s) - vibration , fault (geology) , gear pump , signal (programming language) , representation (politics) , sparse approximation , computer science , control theory (sociology) , pattern recognition (psychology) , algorithm , engineering , artificial intelligence , acoustics , mechanical engineering , physics , geology , control (management) , seismology , politics , law , political science , programming language
A fault diagnosis algorithm of gear pump based on sparse representation is proposed in this study. The vibration signals of the faulty gear pumps are different from those of the normal ones. Therefore, by comparing the vibration signal of an unknown gear pump with the training signals form the normal gear pumps, its fault can be analysed and identified. The sparse representation is used in this study and the vibration signal of the test sample is linearly represented based on the dictionary formed by the normal signals. When the reconstruction error is large enough, the present gear pump is judged to be faulty. Otherwise, it is a normal one. Experiments are conducted based on some measured vibrations signals from both faulty and normal gear pumps. The results show the effectiveness of the proposed method.