An adaptive deep learning model towards fault diagnosis of hydraulic piston pump using pressure signal

•An adaptive CNN is constructed for fault diagnosis of hydraulic piston pump.•Intelligent fault diagnosis is based on the ontology representation of pump.•Time-frequency characteristics of pressure signal are maintained simultaneously.•Different severity levels for the same fault type are included i...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Engineering failure analysis Ročník 138; s. 106300
Hlavní autoři:	Tang, Shengnan, Zhu, Yong, Yuan, Shouqi
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier Ltd 01.08.2022
Témata:	Bayesian optimization algorithm Continuous wavelet transform Convolutional neural network Hydraulic piston pump Intelligent fault diagnosis Intelligent fault diagnosis Bayesian optimization algorithm Convolutional neural network Hydraulic piston pump Continuous wavelet transform
ISSN:	1350-6307, 1873-1961
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	•An adaptive CNN is constructed for fault diagnosis of hydraulic piston pump.•Intelligent fault diagnosis is based on the ontology representation of pump.•Time-frequency characteristics of pressure signal are maintained simultaneously.•Different severity levels for the same fault type are included in the analysis.•Bayesian optimization is employed for automatic learning of hyperparameters. Hydraulic pump is a critical component of a hydraulic transmission system. Its normal and stable operation will directly affect the reliability of the whole system. Owing to the complexity and concealment of fault information, it is crucial to explore an effective method for fault diagnosis of hydraulic piston pump. The obvious change of vibration signal can be observed when different fault types occur, and the implied characteristics of pressure signals are also varying. In this research, an adaptive convolutional neural network (CNN) is constructed based on the ontology representation of pump. First, time–frequency characteristics of pressure signals are obtained via continuous wavelet transform. Second, a deep CNN is established by setting initial hyperparameters. Third, Bayesian optimization is employed to achieve automatic learning of main important hyperparameters to construct an adaptive CNN. The proposed method has better performance for fault diagnosis of hydraulic piston pump compared with other modern intelligent methods.
ISSN:	1350-6307 1873-1961
DOI:	10.1016/j.engfailanal.2022.106300